B. Fei, T. Zhuang, J. Hu and F. Zhou 1998 Frameless stereotactic localization and multimodal image registration using DSA/CT/MRI Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE IEEE 2 683-685 Frameless stereotactic localization and multimodal image registration using DSA/CT/MRI 0780351649 B. Fei, C. Kwoh and W. Ng 1999 The software design for a medical robot for urological applications [Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint IEEE 2 896 vol. 2 The software design for a medical robot for urological applications 0780356748 L. A. Khan, B. Fei, W. Ng and C. Kwoh 1999 X-ray localization technique for total hip replacement operation in augmented reality for therapy (ART) [Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint IEEE 1 649 vol. 1 X-ray localization technique for total hip replacement operation in augmented reality for therapy (ART) 0780356748 B. Fei, W. S. Ng and C. K. Kwoh 2000 The hazard identification and safety insurance control (HISIC) for medical robot Engineering in Medicine and Biology Society, 2000. Proceedings of the 22nd Annual International Conference of the IEEE IEEE 4 3022-3026 The hazard identification and safety insurance control (HISIC) for medical robot 0780364651 L. Kahn, B. Fei, W. Ng and C. Kwoh 2000 The image intensifier (II) distortion calibration method in X-ray localization for total hip replacement (THR) The 17th Symposium for Computer Applications in Radiology, Section A-Digital Imaging Philadelphia, PA June 3-6 The image intensifier (II) distortion calibration method in X-ray localization for total hip replacement (THR) B. Fei, A. Wheaton, Z. Lee, K. Nagano, J. L. Duerk and D. L. Wilson 2001 Robust registration method for interventional MRI-guided thermal ablation of prostate cancer Proc. SPIE 4319 53-60 Robust registration method for interventional MRI-guided thermal ablation of prostate cancer B. Fei, D. T. Boll, J. L. Duerk and D. L. Wilson 2002 Image registration for interventional MRI-guided minimally invasive treatment of prostate cancer The 2nd Joint Meeting of the IEEE Engineering in Medicine and Biology Society and the Biomedical Engineering Society 2 1185 Image registration for interventional MRI-guided minimally invasive treatment of prostate cancer B. Fei, C. Kemper and D. Wilson 2002 Three-dimensional warping registration of the pelvis and prostate [4684-55] PROCEEDINGS-SPIE THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING International Society for Optical Engineering; 1999 1 528-537 Three-dimensional warping registration of the pelvis and prostate [4684-55] 0361-0748 B. Fei, K. Frinkley and D. L. Wilson 2003 Registration algorithms for interventional MRI-guided treatment of the prostate Proceedings of SPIE 5029 192-201 Registration algorithms for interventional MRI-guided treatment of the prostate 0819448303 B. Fei, C. Wietholt, A. V. Clough, C. A. Dawson and D. L. Wilson 2003 Automatic registration and fusion of high resolution micro-CT and lung perfusion SPECT images of the rat Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE IEEE 1 592-594 Automatic registration and fusion of high resolution micro-CT and lung perfusion SPECT images of the rat 0780377893 B. Fei, S. Zhang, O. Savado, J. Suri, J. S. Lewin and D. L. Wilson 2003 Three-dimensional automatic volume registration of carotid MR images Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE IEEE 1 646-648 Three-dimensional automatic volume registration of carotid MR images 0780377893 B. W. Fei, Z. H. Lee, D. T. Boll, J. L. Duerk, J. S. Lewin and D. L. Wilson 2003 Image registration and fusion for interventional MRI guided thermal ablation of the prostate cancer R. E. Ellis and T. M. Peters Medical Image Computing and Computer-Assisted Intervention - Miccai 2003, Pt 2 2879 364-372 Lecture Notes in Computer Science Image registration and fusion for interventional MRI guided thermal ablation of the prostate cancer 0302-9743 3-540-20464-4 WOS:000188180400045 We are investigating interventional MRI (iMRI) guided thermal ablation treatment of the prostate cancer. Functional images such as SPECT can detect and localize tumor in the prostate not reliably seen in MRI. We intend to combine the advantages of SPECT with iMRI-guided treatments. Our concept is to first register the low-resolution SPECT with a high resolution MRI volume. Then by registering the high-resolution MR image with iMRI acquisitions, we can, in turn, map the functional data and high-resolution anatomic information to iMRI images for improved tumor targeting. For the first step, we used a mutual information registration method. For the latter, we developed a robust slice to volume (SV) registration algorithm. Image data were acquired from patients and volunteers. Compared to our volume-to-volume registration that was previously evaluated to be quite accurate, the SV registration accuracy is about 0.5 nun for transverse images covering the prostate. With our image registration and fusion software, simulation experiments show that it is feasible to incorporate SPECT and high resolution MRI into the iMRI-guided treatment. Times Cited: 18 6th International Conference on Medical Image Computing and Computer-Assisted Intervention NOV 15-18, 2003 MONTREAL, CANADA Robarts Res Inst; No Digital Inc Lewin, Jonathan/A-4331-2009; Fei, Baowei /E-6898-2014 Fei, Baowei /0000-0002-9123-9484 0 18 ://WOS:000188180400045 B. W. Fei, Z. H. Lee, J. L. Duerk and D. L. Wilson 2003 Image registration for interventional MRI guided procedures: Interpolation methods, similarity measurements, and applications to the prostate J. C. Gee, J. B. A. Maintz and M. W. Vannier Biomedical Image Registration 2717 321-329 Lecture Notes in Computer Science Image registration for interventional MRI guided procedures: Interpolation methods, similarity measurements, and applications to the prostate 0302-9743 3-540-20343-5 WOS:000187954800034 Nuclear medicine can detect and localize tumor in the prostate not reliably seen in MR. We are investigating methods to combine the advantages of SPECT with interventional MRI (iMRI) guided radiofrequency thermal ablation of the prostate. Our approach is to first register the low-resolution functional images with a high resolution MR volume. Then, by combining the high-resolution MR image with live-time iMRI acquisitions, we can, in turn, include the functional data and high-resolution anatomic information into the iMRI system for improved tumor targeting. In this study, we investigated registration methods for combining noisy, thick iMRI image slices with high-resolution MR volumes. We compared three similarity measures, i.e., normalized mutual information, mutual information, and correlation coefficient; and three interpolation methods, i.e., re-normalized sine, tri-linear, and nearest neighbor. Registration experiments showed that transverse slice images covering the prostate work best with a registration error of approximate to 0.5 mm as compared to our volume-to-volume registration that was previously shown to be quite accurate for these image pairs. Times Cited: 10 2nd International Workshop on Biomedical Image Registration JUN 23-24, 2003 Univ Penn, PHILADELPHIA, PA Siemens Med Solut; Siemens Corp Res; Natl Lib Med; Univ Penn, Vice Provost Res Fei, Baowei /E-6898-2014 Fei, Baowei /0000-0002-9123-9484 0 10 ://WOS:000187954800034 L. White and B. Fei 2003 Failures of GUI Tests on Different Computer Platforms ISSRE 2003 Fast Abstract Failures of GUI Tests on Different Computer Platforms H. Zhang, Z. Bian, Y. Guo, B. Fei and M. Ye 2003 An efficient multiscale approach to level set evolution Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE IEEE 1 694-697 An efficient multiscale approach to level set evolution 0780377893 B. Fei, R. Muzic, Z. Lee, C. Flask, R. Morris, J. L. Duerk and D. Wilson 2004 Registration of micro-PET and high resolution MR images of mice for monitoring photodynamic therapy Proceeding of SPIE on Medical Imaging: Physiology, Function, and Structure from Medical Images 371-379 Registration of micro-PET and high resolution MR images of mice for monitoring photodynamic therapy J. Suri, V. Pappu, O. Salvado, B. Fei, S. Zhang, J. Lewin, J. Duerk, D. Wilson, R. Long, S. Antani, D. Lee, B. Nutter and M. Zhang 2004 Rotational effect on ROI's for accurate lumen quantification in bifurcated MR plaque volumes Proceedings of 17th IEEE Symposium on Computer-Based Medical Systems 414-418 2004 Rotational effect on ROI's for accurate lumen quantification in bifurcated MR plaque volumes WOS:000222998000069 B. Fei, J. Duerk, D. Wilson and N. Oleinick 2005 Multimodality Molecular Imaging for Potential Applications of Image-Guided Treatment for Prostate Cancer: Thermal Ablation and Photodynamic Therapy The 3rd International Public Conference of the AdMeTech Foundation Washington, DC US Congress Oct 27-29, 2005 Multimodality Molecular Imaging for Potential Applications of Image-Guided Treatment for Prostate Cancer: Thermal Ablation and Photodynamic Therapy B. Fei, C. Flask, H. Wang, A. Pi, D. Wilson, J. Shillingford, N. Murcia, T. Weimbs and J. Duerk 2005 Image Segmentation, Registration and Visualization of Serial MR Images for Therapeutic Assessment of Polycystic Kidney Disease in Transgenic Mice Conf Proc IEEE Eng Med Biol Soc 1 467-9 2007/02/07 Image Segmentation, Registration and Visualization of Serial MR Images for Therapeutic Assessment of Polycystic Kidney Disease in Transgenic Mice 1557-170X (Print) 1557-170X (Linking) 17282217 In vivo small animal imaging provides a powerful tool for the study of a variety of diseases. Magnetic resonance imaging (MRI) has become an established technology for the assessment of therapies. In this study, we used high-resolution MRI to evaluate polycystic kidney disease (PKD) in transgenic mice. We used a customized mouse coil to acquire serial MR images from both wide-type and transgenic PKD mice immediately prior to, and 2-week and 4-week after therapy. We developed image segmentation, registration and visualization methods for this novel imaging application. We measured the kidney volumes for each mouse to assess the efficacy of the therapy. The segmentation results show that the kidney volumes are consistent, which are 348.7 ± 19.7 mm3for wild-type mice and 756.3 ± 44.1 mm3for transgenic mice, respectively. The image analysis methods provide a useful tool for this new application. Fei, Baowei Flask, Chris Wang, Hesheng Pi, Ai Wilson, David Shillingford, Jonathan Murcia, Noel Weimbs, Thomas Duerk, Jeffrey R01 CA084433/CA/NCI NIH HHS/United States R01 DK062338/DK/NIDDK NIH HHS/United States United States Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference Conf Proc IEEE Eng Med Biol Soc. 2005;1:467-9. http://ieeexplore.ieee.org/document/1616448/ Department of Radiology, Case Western Reserve University & University Hospitals of Cleveland, USA. Nlm eng B. Fei, X. Chen, H. Wang, J. M. Sabol, E. DuPont and R. C. Gilkeson 2006 Automatic registration of CT volumes and dual-energy digital radiography for detection of cardiac and lung diseases Conf Proc IEEE Eng Med Biol Soc 1 1976-9 2007/10/20 Automatic registration of CT volumes and dual-energy digital radiography for detection of cardiac and lung diseases 1557-170X (Print) 1557-170X (Linking) 2743908 17945687 Algorithms Artificial Intelligence Calcinosis/diagnostic imaging Coronary Angiography/ methods Coronary Artery Disease/ diagnostic imaging Humans Imaging, Three-Dimensional/ methods Lung Diseases/diagnostic imaging Radiographic Image Enhancement/ methods Radiography, Dual-Energy Scanned Projection/ methods Reproducibility of Results Sensitivity and Specificity Subtraction Technique Tomography, X-Ray Computed/ methods We are investigating image processing and analysis techniques to improve the ability of dual-energy digital radiography (DR) for the detection of cardiac calcification. Computed tomography (CT) is an established tool for the diagnosis of coronary artery diseases. Dual-energy digital radiography could be a cost-effective alternative. In this study, we use three-dimensional (3D) CT images as the "gold standard" to evaluate the DR X-ray images for calcification detection. To this purpose, we developed an automatic registration method for 3D CT volumes and two-dimensional (2D) X-ray images. We call this 3D-to-2D registration. We first use a 3D CT image volume to simulate X-ray projection images and then register them with X-ray images. The registered CT projection images are then used to aid the interpretation dual-energy X-ray images for the detection of cardiac calcification. We acquired both CT and X-ray images from patients with coronary artery diseases. Experimental results show that the 3D-to-2D registration is accurate and useful for this new application. Fei, Baowei Chen, Xiang Wang, Hesheng Sabol, John M DuPont, Elena Gilkeson, Robert C R21 CA120536/CA/NCI NIH HHS/United States R21 CA120536-01/CA/NCI NIH HHS/United States R21CA120536/CA/NCI NIH HHS/United States Evaluation Studies Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov't United States Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference Nihms113523 Conf Proc IEEE Eng Med Biol Soc. 2006;1:1976-9. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2743908/pdf/nihms-113523.pdf internal-pdf://0308537105/Fei-2006-Automatic registration of CT volumes.pdf Dept. of Radiol. & Biomed. Eng., Case Western Reserve Univ., Cleveland, OH 44106, USA. baowei.fei@case.edu Nlm eng B. Fei, H. Wang, R. F. Muzic Jr, C. A. Flask, D. Feyes, D. L. Wilson, J. L. Duerk and N. L. Oleinick 2006 Finite element model-based tumor registration of microPET and high-resolution MR images for photodynamic therapy in mice Medical Imaging International Society for Optics and Photonics 61433I-61433I-10 Finite element model-based tumor registration of microPET and high-resolution MR images for photodynamic therapy in mice M. Greer, N. Azar, P. Faulhber and B. Fei 2006 Molecular Imaging for Improved Detection of Gynecologic Cancer- Image Registration and Fusion Visualization The 2006 Biomedical Engineering Society Annual Meeting Chicago, IL October 11-14, 2006 Molecular Imaging for Improved Detection of Gynecologic Cancer- Image Registration and Fusion Visualization E. McKinley, E. Heinzel, D. Johnson, D. Roy, G. Steyer, B. Fei and D. Wilson 2006 High Resolution Magnetic Resonance and Cryo-Imaging for Morphological Phenotyping The 2006 Biomedical Engineering Society Annual Meeting Chicago, IL Oct 11-14, 2006 High Resolution Magnetic Resonance and Cryo-Imaging for Morphological Phenotyping X. Chen, R. Gilkeson and B. Fei 2007 Automatic Intensity-based 3D-to-2D Registration of CT Volume and Dual-energy Digital Radiography for the Detection of Cardiac Calcification Proc SPIE Int Soc Opt Eng 6512 2007/03/03 Mar 03 Automatic Intensity-based 3D-to-2D Registration of CT Volume and Dual-energy Digital Radiography for the Detection of Cardiac Calcification 0277-786X (Print) 0277-786X (Linking) 3877237 24386527 We are investigating three-dimensional (3D) to two-dimensional (2D) registration methods for computed tomography (CT) and dual-energy digital radiography (DR) for the detection of coronary artery calcification. CT is an established tool for the diagnosis of coronary artery diseases (CADs). Dual-energy digital radiography could be a cost-effective alternative for screening coronary artery calcification. In order to utilize CT as the "gold standard" to evaluate the ability of DR images for the detection and localization of calcium, we developed an automatic intensity-based 3D-to-2D registration method for 3D CT volumes and 2D DR images. To generate digital rendering radiographs (DRR) from the CT volumes, we developed three projection methods, i.e. Gaussian-weighted projection, threshold-based projection, and average-based projection. We tested normalized cross correlation (NCC) and normalized mutual information (NMI) as similarity measurement. We used the Downhill Simplex method as the search strategy. Simulated projection images from CT were fused with the corresponding DR images to evaluate the localization of cardiac calcification. The registration method was evaluated by digital phantoms, physical phantoms, and clinical data sets. The results from the digital phantoms show that the success rate is 100% with mean errors of less 0.8 mm and 0.2 degree for both NCC and NMI. The registration accuracy of the physical phantoms is 0.34 +/- 0.27 mm. Color overlay and 3D visualization of the clinical data show that the two images are registered well. This is consistent with the improvement of the NMI values from 0.20 +/- 0.03 to 0.25 +/- 0.03 after registration. The automatic 3D-to-2D registration method is accurate and robust and may provide a useful tool to evaluate the dual-energy DR images for the detection of coronary artery calcification. Chen, Xiang Gilkeson, Robert Fei, Baowei R21 CA120536/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432054 Proc SPIE Int Soc Opt Eng. 2007 Mar 3;6512. doi: 10.1117/12.710192. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6512/1/Automatic-intensity-based-3D-to-2D-registration-of-CT-volume/10.1117/12.710192.short?SSO=1 Case Western Reserve University and Xi'an Jiaotong University. University Hospitals Case Medical Center. Case Western Reserve University. Nlm eng B. Fei, N. Azar, M. Greer, P. Rochon and P. Faulhaber 2007 Automatic Registration and Fusion of Ultrasound Imaging and Positron Emission Tomography (PET) for Improved Diagnosis of Gynecologic Cancer The American Institute of Ultrasound in Medicine 2007 Convention New York, NY March 15-18, 2007 Automatic Registration and Fusion of Ultrasound Imaging and Positron Emission Tomography (PET) for Improved Diagnosis of Gynecologic Cancer B. Fei, J. Duerk and N. Oleinick 2007 Multimodality Molecular Imaging for Photodynamic Therapy of Prostate Cancer US Department of Defense Prostate Cancer Research Program- The Innovative Minds in Prostate Cancer Today (IMPaCT) Inaugural Meeting Atlanta, Georgia Sep. 5-8, 2007 Multimodality Molecular Imaging for Photodynamic Therapy of Prostate Cancer B. Fei, H. Wang, X. Chen, J. Meyers, J. Mulvihill, D. Feyes, N. Edgehouse, J. L. Duerk, T. G. Pretlow and N. L. Oleinick 2007 In Vivo Small Animal Imaging for Early Assessment of Therapeutic Efficacy of Photodynamic Therapy for Prostate Cancer Proc SPIE Int Soc Opt Eng 6511 2007/03/29 Mar 29 In Vivo Small Animal Imaging for Early Assessment of Therapeutic Efficacy of Photodynamic Therapy for Prostate Cancer 0277-786X (Print) 0277-786X (Linking) 3877221 24386525 We are developing in vivo small animal imaging techniques that can measure early effects of photodynamic therapy (PDT) for prostate cancer. PDT is an emerging therapeutic modality that continues to show promise in the treatment of cancer. At our institution, a new second-generation photosensitizing drug, the silicon phthalocyanine Pc 4, has been developed and evaluated at the Case Comprehensive Cancer Center. In this study, we are developing magnetic resonance imaging (MRI) techniques that provide therapy monitoring and early assessment of tumor response to PDT. We generated human prostate cancer xenografts in athymic nude mice. For the imaging experiments, we used a high-field 9.4-T small animal MR scanner (Bruker Biospec). High-resolution MR images were acquired from the treated and control tumors pre- and post-PDT and 24 hr after PDT. We utilized multi-slice multi-echo (MSME) MR sequences. During imaging acquisitions, the animals were anesthetized with a continuous supply of 2% isoflurane in oxygen and were continuously monitored for respiration and temperature. After imaging experiments, we manually segmented the tumors on each image slice for quantitative image analyses. We computed three-dimensional T2 maps for the tumor regions from the MSME images. We plotted the histograms of the T2 maps for each tumor pre- and post-PDT and 24 hr after PDT. After the imaging and PDT experiments, we dissected the tumor tissues and used the histologic slides to validate the MR images. In this study, six mice with human prostate cancer tumors were imaged and treated at the Case Center for Imaging Research. The T2 values of treated tumors increased by 24 +/- 14% 24 hr after the therapy. The control tumors did not demonstrate significant changes of the T2 values. Inflammation and necrosis were observed within the treated tumors 24 hour after the treatment. Preliminary results show that Pc 4-PDT is effective for the treatment of human prostate cancer in mice. The small animal MR imaging provides a useful tool to evaluate early tumor response to photodynamic therapy in mice. Fei, Baowei Wang, Hesheng Chen, Xiang Meyers, Joseph Mulvihill, John Feyes, Denise Edgehouse, Nancy Duerk, Jeffrey L Pretlow, Thomas G Oleinick, Nancy L R21 CA120536/CA/NCI NIH HHS/United States R24 CA110943/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432056 Proc SPIE Int Soc Opt Eng. 2007 Mar 29;6511. doi: 10.1117/12.708718. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6511/1/In-vivo-small-animal-imaging-for-early-assessment-of-therapeutic/10.1117/12.708718.short Department of Radiology, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center ; Department of Biomedical Engineering, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center. Department of Biomedical Engineering, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center. Department of Radiology, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center. Department of Radiation Oncology, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center. Department of Pathology, Case Western Reserve University, University Hospitals of Cleveland, and the Case Comprehensive Cancer Center. Nlm eng H. Wang, D. Feyes, J. Mulvihill, N. Oleinick, G. Maclennan and B. Fei 2007 Multiscale Fuzzy C-Means Image Classification for Multiple Weighted MR Images for the Assessment of Photodynamic Therapy in Mice Proc SPIE Int Soc Opt Eng 6512 2007/03/08 Mar 08 Multiscale Fuzzy C-Means Image Classification for Multiple Weighted MR Images for the Assessment of Photodynamic Therapy in Mice 0277-786X (Print) 0277-786X (Linking) 3877232 24386526 We are investigating in vivo small animal imaging and analysis methods for the assessment of photodynamic therapy (PDT), an emerging therapeutic modality for cancer treatment. Multiple weighted MR images were acquired from tumor-bearing mice pre- and post-PDT and 24-hour after PDT. We developed an automatic image classification method to differentiate live, necrotic and intermediate tissues within the treated tumor on the MR images. We used a multiscale diffusion filter to process the MR images before classification. A multiscale fuzzy C-means (FCM) classification method was applied along the scales. The object function of the standard FCM was modified to allow multiscale classification processing where the result from a coarse scale is used to supervise the classification in the next scale. The multiscale fuzzy C-means (MFCM) method takes noise levels and partial volume effects into the classification processing. The method was validated by simulated MR images with various noise levels. For simulated data, the classification method achieved 96.0 +/- 1.1% overlap ratio. For real mouse MR images, the classification results of the treated tumors were validated by histologic images. The overlap ratios were 85.6 +/- 5.1%, 82.4 +/- 7.8% and 80.5 +/- 10.2% for the live, necrotic, and intermediate tissues, respectively. The MR imaging and the MFCM classification methods may provide a useful tool for the assessment of the tumor response to photodynamic therapy in vivo. Wang, Hesheng Feyes, Denise Mulvihill, John Oleinick, Nancy Maclennan, Gregory Fei, Baowei R21 CA120536/CA/NCI NIH HHS/United States R24 CA110943/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432055 Proc SPIE Int Soc Opt Eng. 2007 Mar 8;6512. doi: 10.1117/12.710188. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6512/1/Multiscale-fuzzy-C-means-image-classification-for-multiple-weighted-MR/10.1117/12.710188.short Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, 44106. Department of Radiation Oncology, Case Western Reserve University, Cleveland, OH, 44106. Department of Pathology, Case Western Reserve University, Cleveland, OH, 44106. Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, 44106 ; Department of Radiology Case Western Reserve University, Cleveland, OH, 44106. Nlm eng O. Bebek, M. J. Hwang, B. Fei and M. Cavusoglu 2008 Design of a small animal biopsy robot Conf Proc IEEE Eng Med Biol Soc 2008 5601-4 2009/01/24 Design of a small animal biopsy robot 1557-170X (Print) 1557-170X (Linking) 2796956 19163987 Biopsy/ instrumentation/methods/ veterinary Equipment Design Equipment Failure Analysis Needles/ veterinary Reproducibility of Results Robotics/ instrumentation/methods Sensitivity and Specificity Surgery, Computer-Assisted/ instrumentation/methods Small animals are widely used in biomedical research studies. They have compact anatomy and small organs. Therefore it is difficult to perceive tumors or cells and perform biopsies manually. Robotics technology offers a convenient and reliable solution for accurate needle insertion. In this paper, a novel 5 degrees of freedom (DOF) robot design for inserting needles into small animal subjects is proposed. The design has a compact size, is light weight, and has high resolution. Parallel mechanisms are used in the design for stable and reliable operation. The proposed robot has two gimbal joints that carry the needle mechanism. The robot can realize dexterous alignment of the needle before insertion. Bebek, Ozkan Hwang, Myun Joong Fei, Baowei Cavusoglu, M R21 CA120536/CA/NCI NIH HHS/United States R21 CA120536-01/CA/NCI NIH HHS/United States R21 CA120536-02/CA/NCI NIH HHS/United States Evaluation Studies Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S. United States Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference Nihms113528 Conf Proc IEEE Eng Med Biol Soc. 2008;2008:5601-4. doi: 10.1109/IEMBS.2008.4650484. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2796956/pdf/nihms113528.pdf internal-pdf://3037231223/Bebek-2008-Design of a small animal biopsy rob.pdf Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, Ohio, 44106, USA. oxb6@case.edu Nlm eng X. Chen, K. Li, R. Gilkeson and B. Fei 2008 Gaussian Weighted Projection for Visualization of Cardiac Calcification Proc SPIE Int Soc Opt Eng 6918 2008/03/15 Mar 15 Gaussian Weighted Projection for Visualization of Cardiac Calcification 0277-786X (Print) 0277-786X (Linking) 3877249 24386529 At our institution, we are using dual-energy digital radiography (DEDR) as a cost-effective screening tool for the detection of cardiac calcification. We are evaluating DEDR using CT as the gold standard. We are developing image projection methods for the generation of digitally reconstructed radiography (DRR) from CT image volumes. Traditional visualization methods include maximum intensity projection (MIP) and average-based projection (AVG) that have difficulty to show cardiac calcification. Furthermore, MIP can over estimate the calcified lesion as it displays the maximum intensity along the projection rays regardless of tissue types. For AVG projection, the calcified tissue is usually overlapped with bone, lung and mediastinum. In order to improve the visualization of calcification on DRR images, we developed a Gaussian-weighted projection method for this particular application. We assume that the CT intensity values of calcified tissues have a Gaussian distribution. We then use multiple Gaussian functions to fit the intensity histogram. Based on the mean and standard deviation parameters, we incorporate a Gaussian weighted function into the perspective projection and display the calcification exclusively. Our digital and physical phantom studies show that the new projection method can display tissues selectively. In addition, clinical images show that the Gaussian-weighted projection method better visualizes cardiac calcification than either the AVG or MIP method and can be used to evaluate DEDR as a screening tool for the detection of coronary artery diseases. Chen, Xiang Li, Ke Gilkeson, Robert Fei, Baowei R21 CA120536/CA/NCI NIH HHS/United States R24 CA110943/CA/NCI NIH HHS/United States U24 CA110943/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432049 Proc SPIE Int Soc Opt Eng. 2008 Mar 15;6918. doi: 10.1117/12.772597. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6918/1/Gaussian-weighted-projection-for-visualization-of-cardiac-calcification/10.1117/12.772597.short Case Western Reserve University and Xi'an Jiaotong University. Case Western Reserve University. University Hospitals Case Medical Center. Nlm eng B. Fei, H. Wang, C. Wu and J. Meyers 2008 Choline molecular imaging with PET for photodynamic therapy of cancer Journal of Nuclear Medicine 49 supplement 1 329P-329P Choline molecular imaging with PET for photodynamic therapy of cancer 0161-5505 K. Li and B. Fei 2008 A new 3D model-based minimal path segmentation method for kidney MR images Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on IEEE 2342-2344 A new 3D model-based minimal path segmentation method for kidney MR images 1424417481 K. Li and B. Fei 2008 A deformable model-based minimal path segmentation method for kidney MR images Proceedings of SPIE NIH Public Access 6914 A deformable model-based minimal path segmentation method for kidney MR images H. Wang and B. Fei 2008 A robust B-Splines-based point match method for non-rigid surface registration Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on IEEE 2353-2356 A robust B-Splines-based point match method for non-rigid surface registration 1424417481 L. Ciancibello, R. Gilkeson and B. Fei 2009 Bismuth Breast Shielding and its Effect on Calcium Score and Dose AMERICAN JOURNAL OF ROENTGENOLOGY AMER ROENTGEN RAY SOC 1891 PRESTON WHITE DR, SUBSCRIPTION FULFILLMENT, RESTON, VA 22091 USA 192 5 Bismuth Breast Shielding and its Effect on Calcium Score and Dose 0361-803X B. Fei, H. Wang, C. Wu, S.-m. Chiu and N. Edgehouse 2009 Monitoring Tumor Cellular and Tissue Response to Photodynamic Therapy by Choline PET imaging and Diffusion-weighted MRI World Molecular Imaging Congress Montreal, Canada Sep. 23-26, 2009 Monitoring Tumor Cellular and Tissue Response to Photodynamic Therapy by Choline PET imaging and Diffusion-weighted MRI This study is to develop multimodality imaging (PET/MRI) as an early biomarker for monitoring tumor response to photodynamic therapy (PDT) at the cellular and tissue levels. Methods: A human prostate cancer cell line (CWR22) was used to generate tumors in athymic nude mice. A second-generation photosensitizing drug Pc 4 (0.6 mg/kg body weight) was delivered to each animal by tail vein injection 48 h before laser illumination (672 nm, 100 mW/cm2 , 150 J/cm2 ). For Group I (N=5), dynamic microPET images with 11C-choline were acquired from each mouse pre-PDT and 24 h and 48 h after PDT. For Group II (N=18), diffusion-weighted MR images were acquired pre- and post-PDT, 24 h, and/or 7 d after PDT. Apparent diffusion coefficient (ADC) maps were obtained and analyzed for each tumor. Prostate specific antigen (PSA) levels were measured 1 d before PDT and 24 h and 7 d after PDT. Results: The PSA values decreased by 30.3% and 64.1% 24 h and 7 d after PDT, respectively, indicating the treatment effect. For Group I, the choline uptakes dramatically decreased 24 h (75.5%) and 48 h (43.5%) after PDT, compared to those pre-PDT. Histologic analysis showed that PDT-treated tumors demonstrated apoptosis, necrosis and inflammation. For Group II, ADC values significantly increased (47.5%) 24 h after PDT. In four mice, the ADC histogram demonstrated a biphasic response 7 d after PDT, i.e. some tissue within the tumor had increased ADC values and other maintained approximately the same values as those before treatment. On MR images, tumor tissue was automatically classified into two tissue types (necrotic and viable), which were well correlated (R=89%) with tissue quantification from histology. The changes in choline uptake and ADC values are consistent with the PSA levels. Conclusions: Changes in tumor choline uptake detected by PET imaging can determine whether or not the tumor responds the therapy within 48 h after PDT. Diffusion-weighted MR imaging can detect and quantify viable and necrotic tumor tissue within one week after the treatment. The noninvasive imaging techniques can provide an assay that could be useful for clinical monitoring of photodynamic therapy at an early stage (1-7 days). B. Fei, H. Wang, C. Wu, J. Meyers, L. Y. Xue, G. Maclennan and M. Schluchter 2009 Choline Molecular Imaging with Small-animal PET for Monitoring Tumor Cellular Response to Photodynamic Therapy of Cancer Proc SPIE Int Soc Opt Eng 7262 726211 2009/01/01 Choline Molecular Imaging with Small-animal PET for Monitoring Tumor Cellular Response to Photodynamic Therapy of Cancer 0277-786X (Print) 0277-786X (Linking) 3546344 23336060 We are developing and evaluating choline molecular imaging with positron emission tomography (PET) for monitoring tumor response to photodynamic therapy (PDT) in animal models. Human prostate cancer (PC-3) was studied in athymic nude mice. A second-generation photosensitizer Pc 4 was used for PDT in tumor-bearing mice. MicroPET images with (11)C-choline were acquired before PDT and 48 h after PDT. Time-activity curves of (11)C-choline uptake were analyzed before and after PDT. For treated tumors, normalized choline uptake decreased significantly 48 h after PDT, compared to the same tumors pre-PDT (p < 0.001). However, for the control tumors, normalized choline uptake increased significantly (p < 0.001). PET imaging with (11)C-choline is sensitive to detect early tumor response to PDT in the animal model of human prostate cancer. Fei, Baowei Wang, Hesheng Wu, Chunying Meyers, Joseph Xue, Liang-Yan Maclennan, Gregory Schluchter, Mark R21 CA120536/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432050 Proc SPIE Int Soc Opt Eng. 2009;7262:726211. Epub 2009 Feb 27. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3546344/pdf/nihms432050.pdf internal-pdf://2182586886/Fei-2009-Choline Molecular Imaging with Small-.pdf Department of Radiology, Emory University, Atlanta, GA ; Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio. Nlm eng B. Fei, X. Yang and H. Wang 2009 An MRI-based Attenuation Correction Method for Combined PET/MRI Applications Proc SPIE Int Soc Opt Eng 7262 2009/02/27 Feb 27 An MRI-based Attenuation Correction Method for Combined PET/MRI Applications 0277-786X (Print) 0277-786X (Linking) 3653447 23682307 We are developing MRI-based attenuation correction methods for PET images. PET has high sensitivity but relatively low resolution and little anatomic details. MRI can provide excellent anatomical structures with high resolution and high soft tissue contrast. MRI can be used to delineate tumor boundaries and to provide an anatomic reference for PET, thereby improving quantitation of PET data. Combined PET/MRI can offer metabolic, functional and anatomic information and thus can provide a powerful tool to study the mechanism of a variety of diseases. Accurate attenuation correction represents an essential component for the reconstruction of artifact-free, quantitative PET images. Unfortunately, the present design of hybrid PET/MRI does not offer measured attenuation correction using a transmission scan. This problem may be solved by deriving attenuation maps from corresponding anatomic MR images. Our approach combines image registration, classification, and attenuation correction in a single scheme. MR images and the preliminary reconstruction of PET data are first registered using our automatic registration method. MRI images are then classified into different tissue types using our multiscale fuzzy C-mean classification method. The voxels of classified tissue types are assigned theoretical tissue-dependent attenuation coefficients to generate attenuation correction factors. Corrected PET emission data are then reconstructed using a three-dimensional filtered back projection method and an order subset expectation maximization method. Results from simulated images and phantom data demonstrated that our attenuation correction method can improve PET data quantitation and it can be particularly useful for combined PET/MRI applications. Fei, Baowei Yang, Xiaofeng Wang, Hesheng R21 CA120536/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432051 Proc SPIE Int Soc Opt Eng. 2009 Feb 27;7262. pii: 726208. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/7262/1/An-MRI-based-attenuation-correction-method-for-combined-PET-MRI/10.1117/12.813755.short Departments of Radiology, Emory University, Atlanta, GA. Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio. Nlm eng S. Guo and B. Fei 2009 A Minimal Path Searching Approach for Active Shape Model (ASM)-based Segmentation of the Lung Proc SPIE Int Soc Opt Eng 7259 2009/03/27 Mar 27 A Minimal Path Searching Approach for Active Shape Model (ASM)-based Segmentation of the Lung 0277-786X (Print) 0277-786X (Linking) 3877238 24386531 We are developing a minimal path searching method for active shape model (ASM)-based segmentation for detection of lung boundaries on digital radiographs. With the conventional ASM method, the position and shape parameters of the model points are iteratively refined and the target points are updated by the least Mahalanobis distance criterion. We propose an improved searching strategy that extends the searching points in a fan-shape region instead of along the normal direction. A minimal path (MP) deformable model is applied to drive the searching procedure. A statistical shape prior model is incorporated into the segmentation. In order to keep the smoothness of the shape, a smooth constraint is employed to the deformable model. To quantitatively assess the ASM-MP segmentation, we compare the automatic segmentation with manual segmentation for 72 lung digitized radiographs. The distance error between the ASM-MP and manual segmentation is 1.75 +/- 0.33 pixels, while the error is 1.99 +/- 0.45 pixels for the ASM. Our results demonstrate that our ASM-MP method can accurately segment the lung on digital radiographs. Guo, Shengwen Fei, Baowei R21 CA120536/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432053 Proc SPIE Int Soc Opt Eng. 2009 Mar 27;7259. doi: 10.1117/12.812575. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/7259/1/A-minimal-path-searching-approach-for-active-shape-model-ASM/10.1117/12.812575.short Quantitative BioImaging Laboratory, Department of Radiology, Emory University, Atlanta, GA 30322. Nlm eng M. J. Hwang, O. Bebek, F. Liang, B. Fei and M. C. Cavusoglu 2009 Kinematic calibration of a parallel robot for small animal biopsies Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on IEEE 4104-4109 Kinematic calibration of a parallel robot for small animal biopsies 1424438039 J. N. Mafi, B. Fei, R. Gilkeson, S. Roble, A. Dota, P. Katrapati, H. Bezerra, H. Wang, J. Coletta, W. Wang, L. Ciancibello, M. Costa, D. I. Simon and C. E. Orringer 2009 Quantification of Coronary Artery Calcium Using Dual-energy Subtraction Digital Radiography RSNA Annual Meeting 2009, Session: Cardiac (CT Angiography: Dual Energy) Chicago, IL Dec. 4, 2009 Quantification of Coronary Artery Calcium Using Dual-energy Subtraction Digital Radiography H. Wang and B. Fei 2009 An MRI-guided PET partial volume correction method Proceedings of SPIE NIH Public Access 7259 An MRI-guided PET partial volume correction method B. Fei, X. Yang, J. Nye, J. Aasrsvold, C. Meltzer and J. Voltaw 2010 PET-MRI Qualification Tools- Registration, Segmentation, Classification, and Attenuation Correction IEEE Nuclear Science Symposium and Medical Imaging Conference - Focused Workshop on PET-MR Knoxville, TN Nov. 1, 2010 PET-MRI Qualification Tools- Registration, Segmentation, Classification, and Attenuation Correction B. Fei, X. Yang, J. Nye, M. Jones, J. Aarsvold, N. Raghunath, C. Meltzer and J. Votaw 2010 MRI-based attenuation correction and quantification tools for combined MRI/PET Journal of Nuclear Medicine 51 supplement 2 81-81 MRI-based attenuation correction and quantification tools for combined MRI/PET 0161-5505 X. Yang and B. Fei 2010 A skull segmentation method for brain MR images based on multiscale bilateral filtering scheme Medical Imaging: Image Processing 76233K A skull segmentation method for brain MR images based on multiscale bilateral filtering scheme H. Akbari, X. Yang, L. V. Halig and B. Fei 2011 3D Segmentation of Prostate Ultrasound images Using Wavelet Transform Proc SPIE Int Soc Opt Eng 7962 79622K 2011/01/01 3D Segmentation of Prostate Ultrasound images Using Wavelet Transform 0277-786X (Print) 0277-786X (Linking) 3314427 22468205 The current definitive diagnosis of prostate cancer is transrectal ultrasound (TRUS) guided biopsy. However, the current procedure is limited by using 2D biopsy tools to target 3D biopsy locations. This paper presents a new method for automatic segmentation of the prostate in three-dimensional transrectal ultrasound images, by extracting texture features and by statistically matching geometrical shape of the prostate. A set of Wavelet-based support vector machines (W-SVMs) are located and trained at different regions of the prostate surface. The WSVMs capture texture priors of ultrasound images for classification of the prostate and non-prostate tissues in different zones around the prostate boundary. In the segmentation procedure, these W-SVMs are trained in three sagittal, coronal, and transverse planes. The pre-trained W-SVMs are employed to tentatively label each voxel around the surface of the model as a prostate or non-prostate voxel by the texture matching. The labeled voxels in three planes after post-processing is overlaid on a prostate probability model. The probability prostate model is created using 10 segmented prostate data. Consequently, each voxel has four labels: sagittal, coronal, and transverse planes and one probability label. By defining a weight function for each labeling in each region, each voxel is labeled as a prostate or non-prostate voxel. Experimental results by using real patient data show the good performance of the proposed model in segmenting the prostate from ultrasound images. Akbari, Hamed Yang, Xiaofeng Halig, Luma V Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362788 Proc SPIE Int Soc Opt Eng. 2011;7962:79622K. Epub 2011 Mar 14. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3314427/pdf/nihms362788.pdf internal-pdf://1935685926/Akbari-2011-3D Segmentation of Prostate Ultras.pdf Department of Radiology, Emory University, 1841 Clifton Rd, NE, Atlanta, GA, USA 30329. Nlm eng B. Fei, V. Master, P. Nieh, H. Akbari, X. Yang, A. Fenster and D. Schuster 2011 A PET/CT Directed, 3D Ultrasound-Guided Biopsy System for Prostate Cancer Prostate Cancer Imaging (2011) 6363 100-108 2011/01/01 A PET/CT Directed, 3D Ultrasound-Guided Biopsy System for Prostate Cancer 4745094 26866061 Prostate cancer affects 1 in 6 men in the USA. Systematic transrectal ultrasound (TRUS)-guided biopsy is the standard method for a definitive diagnosis of prostate cancer. However, this "blind" biopsy approach can miss at least 20% of prostate cancers. In this study, we are developing a PET/CT directed, 3D ultrasound image-guided biopsy system for improved detection of prostate cancer. In order to plan biopsy in three dimensions, we developed an automatic segmentation method based wavelet transform for 3D TRUS images of the prostate. The segmentation was tested in five patients with a DICE overlap ratio of more than 91%. In order to incorporate PET/CT images into ultrasound-guided biopsy, we developed a nonrigid registration algorithm for TRUS and PET/CT images. The registration method has been tested in a prostate phantom with a target registration error (TRE) of less than 0.4 mm. The segmentation and registration methods are two key components of the multimodality molecular image-guided biopsy system. Fei, Baowei Master, Viraj Nieh, Peter Akbari, Hamed Yang, Xiaofeng Fenster, Aaron Schuster, David R21 CA176684/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States P50 CA128613/CA/NCI NIH HHS/United States Germany Prostate cancer imaging : image analysis and image-guided interventions : international workshop held in conjunction with MICCAI 2011, Toronto, Canada, September 22, 2011 : proceedings Nihms716010 Prostate Cancer Imaging (2011). 2011;6363:100-108. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA 30329; Winship Cancer Institute, Emory University, Atlanta, GA 30329; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA 30329. Department of Urology, Emory University, Atlanta, GA 30329. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA 30329. Imaging Research Laboratories, Robarts Research Institute, London, Ontario, Canada, N6A 5K8. Nlm eng D. Schuster, B. Fei, T. Fox and A. O. Osunkoya 2011 Histopathologic Correlation of Prostatic Adenocarcinoma on Radical Prostatectomy with Pre-Operative Anti-18F Fluorocyclobutyl-Carboxylic Acid Positron Emission Tomography/Computed Tomography Laboratory Investigation 91 222A-223A Feb Histopathologic Correlation of Prostatic Adenocarcinoma on Radical Prostatectomy with Pre-Operative Anti-18F Fluorocyclobutyl-Carboxylic Acid Positron Emission Tomography/Computed Tomography 0023-6837 WOS:000291285000379 Times Cited: 2 1 100th Annual Meeting of the United States and Canadian-Academy-of-Pathology FEB 26-MAR 04, 2011 San Antonio, TX Canadian Acad Pathol Schuster, David/D-6156-2011; Fei, Baowei /E-6898-2014 Fei, Baowei /0000-0002-9123-9484 0 2 ://WOS:000291285000379 X. Yang, H. Akbari, L. Halig and B. Fei 2011 3D Non-rigid Registration Using Surface and Local Salient Features for Transrectal Ultrasound Image-guided Prostate Biopsy Proc SPIE Int Soc Opt Eng 7964 79642V 2011/03/01 Mar 01 3D Non-rigid Registration Using Surface and Local Salient Features for Transrectal Ultrasound Image-guided Prostate Biopsy 0277-786X (Print) 0277-786X (Linking) 3766999 24027609 We present a 3D non-rigid registration algorithm for the potential use in combining PET/CT and transrectal ultrasound (TRUS) images for targeted prostate biopsy. Our registration is a hybrid approach that simultaneously optimizes the similarities from point-based registration and volume matching methods. The 3D registration is obtained by minimizing the distances of corresponding points at the surface and within the prostate and by maximizing the overlap ratio of the bladder neck on both images. The hybrid approach not only capture deformation at the prostate surface and internal landmarks but also the deformation at the bladder neck regions. The registration uses a soft assignment and deterministic annealing process. The correspondences are iteratively established in a fuzzy-to-deterministic approach. B-splines are used to generate a smooth non-rigid spatial transformation. In this study, we tested our registration with pre- and post-biopsy TRUS images of the same patients. Registration accuracy is evaluated using manual defined anatomic landmarks, i.e. calcification. The root-mean-squared (RMS) of the difference image between the reference and floating images was decreased by 62.6+/-9.1% after registration. The mean target registration error (TRE) was 0.88+/-0.16 mm, i.e. less than 3 voxels with a voxel size of 0.38x0.38x0.38 mm3 for all five patients. The experimental results demonstrate the robustness and accuracy of the 3D non-rigid registration algorithm. Yang, Xiaofeng Akbari, Hamed Halig, Luma Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362780 Proc SPIE Int Soc Opt Eng. 2011 Mar 1;7964:79642V. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3766999/pdf/nihms362780.pdf internal-pdf://0460784861/Yang-2011-3D Non-rigid Registration Using Surf.pdf Department of Radiology, Emory University. Nlm eng X. Yang and B. Fei 2011 A MR Brain Classification Method Based on Multiscale and Multiblock Fuzzy C-means Int Conf Bioinform Biomed Eng 1-4 2011/01/01 A MR Brain Classification Method Based on Multiscale and Multiblock Fuzzy C-means 2151-7614 (Print) 2151-7614 (Linking) 3552386 23358117 A fully automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with intensity correction for MR images is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and reducing the standard deviation of range function. We separate every scale image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels to overcome the effect of intensity inhomogeneity. The method is robust for noise MR images with intensity inhomogeneity because of its multiscale and multiblock bilateral filtering scheme. Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method on synthesized images, simulated brain MR images, and real MR images. The MsbFCM method achieved an overlap ratio of greater than 91% as validated by the ground truth even if original images have 9% noise and 40% intensity inhomogeneity. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images. Yang, Xiaofeng Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States International Conference on Bioinformatics and Biomedical Engineering : [proceedings]. International Conference on Bioinformatics and Biomedical Engineering Nihms432047 Int Conf Bioinform Biomed Eng. 2011:1-4. Department of Radiology, Emory University, Atlanta, GA 30329. Nlm eng X. Yang, D. Schuster, V. Master, P. Nieh, A. Fenster and B. Fei 2011 Automatic 3D Segmentation of Ultrasound Images Using Atlas Registration and Statistical Texture Prior Proc SPIE Int Soc Opt Eng 7964 2011/01/01 Automatic 3D Segmentation of Ultrasound Images Using Atlas Registration and Statistical Texture Prior 0277-786X (Print) 0277-786X (Linking) 3375607 22708024 We are developing a molecular image-directed, 3D ultrasound-guided, targeted biopsy system for improved detection of prostate cancer. In this paper, we propose an automatic 3D segmentation method for transrectal ultrasound (TRUS) images, which is based on multi-atlas registration and statistical texture prior. The atlas database includes registered TRUS images from previous patients and their segmented prostate surfaces. Three orthogonal Gabor filter banks are used to extract texture features from each image in the database. Patient-specific Gabor features from the atlas database are used to train kernel support vector machines (KSVMs) and then to segment the prostate image from a new patient. The segmentation method was tested in TRUS data from 5 patients. The average surface distance between our method and manual segmentation is 1.61 +/- 0.35 mm, indicating that the atlas-based automatic segmentation method works well and could be used for 3D ultrasound-guided prostate biopsy. Yang, Xiaofeng Schuster, David Master, Viraj Nieh, Peter Fenster, Aaron Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362792 Proc SPIE Int Soc Opt Eng. 2011;7964. pii: 796432. Epub 2011 Mar 1. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/7964/1/Automatic-3D-segmentation-of-ultrasound-images-using-atlas-registration-and/10.1117/12.877888.short Department of Radiology, Emory University, Atlanta, GA, USA. Nlm eng X. Yang, I. Sechopoulos and B. Fei 2011 Automatic Tissue Classification for High-resolution Breast CT Images Based on Bilateral Filtering Proc SPIE Int Soc Opt Eng 7962 79623H 2011/03/14 Mar 14 Automatic Tissue Classification for High-resolution Breast CT Images Based on Bilateral Filtering 0277-786X (Print) 0277-786X (Linking) 3766982 24027608 Breast tissue classification can provide quantitative measurements of breast composition, density and tissue distribution for diagnosis and identification of high-risk patients. In this study, we present an automatic classification method to classify high-resolution dedicated breast CT images. The breast is classified into skin, fat and glandular tissue. First, we use a multiscale bilateral filter to reduce noise and at the same time keep edges on the images. As skin and glandular tissue have similar CT values in breast CT images, we use morphologic operations to get the mask of the skin based on information of its position. Second, we use a modified fuzzy C-mean classification method twice, one for the skin and the other for the fatty and glandular tissue. We compared our classified results with manually segmentation results and used Dice overlap ratios to evaluate our classification method. We also tested our method using added noise in the images. The overlap ratios for glandular tissue were above 94. 7% for data from five patients. Evaluation results showed that our method is robust and accurate. Yang, Xiaofeng Sechopoulos, Ioannis Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362783 Proc SPIE Int Soc Opt Eng. 2011 Mar 14;7962:79623H. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3766982/pdf/nihms362783.pdf internal-pdf://2836566121/Yang-2011-Automatic Tissue Classification for.pdf Department of Radiology, Emory University. Nlm eng H. Akbari and B. Fei 2012 Automatic 3D segmentation of the kidney in MR images using wavelet feature extraction and probability shape model D. R. Haynor and S. Ourselin Proceedings Volume 8314, Medical Imaging 2012: Image Processing San Diego, California SPIE 8314 02/2012 Conference Proceeding Automatic 3D segmentation of the kidney in MR images using wavelet feature extraction and probability shape model Numerical estimation of the size of the kidney is useful in evaluating conditions of the kidney, especially, when serial MR imaging is performed to evaluate the kidney function. This paper presents a new method for automatic segmentation of the kidney in three-dimensional (3D) MR images, by extracting texture features and statistical matching of geometrical shape of the kidney. A set of Wavelet-based support vector machines (W-SVMs) is trained on the MR images. The W-SVMs capture texture priors of MRI for classification of the kidney and non-kidney tissues in different zones around the kidney boundary. In the segmentation procedure, these W-SVMs are trained to tentatively label each voxel around the kidney model as a kidney or non-kidney voxel by texture matching. A probability kidney model is created using 10 segmented MRI data. The model is initially localized based on the intensity profiles in three directions. The weight functions are defined for each labeled voxel for each Wavelet-based, intensity-based, and model-based label. Consequently, each voxel has three labels and three weights for the Wavelet feature, intensity, and probability model. Using a 3D edge detection method, the model is re-localized and the segmented kidney is modified based on a region growing method in the model region. The probability model is re-localized based on the results and this loop continues until the segmentation converges. Experimental results with mouse MRI data show the good performance of the proposed method in segmenting the kidney in MR images. H. Akbari, L. V. Halig, H. Zhang, D. Wang, Z. G. Chen and B. Fei 2012 Detection of Cancer Metastasis Using a Novel Macroscopic Hyperspectral Method Proc SPIE Int Soc Opt Eng 8317 831711 2013/01/22 Detection of Cancer Metastasis Using a Novel Macroscopic Hyperspectral Method 0277-786X (Print) 0277-786X (Linking) 3546351 23336061 The proposed macroscopic optical histopathology includes a broad-band light source which is selected to illuminate the tissue glass slide of suspicious pathology, and a hyperspectral camera that captures all wavelength bands from 450 to 950 nm. The system has been trained to classify each histologic slide based on predetermined pathology with light having a wavelength within a predetermined range of wavelengths. This technology is able to capture both the spatial and spectral data of tissue. Highly metastatic human head and neck cancer cells were transplanted to nude mice. After 2-3 weeks, the mice were euthanized and the lymph nodes and lung tissues were sent to pathology. The metastatic cancer is studied in lymph nodes and lungs. The pathological slides were imaged using the hyperspectral camera. The results of the proposed method were compared to the pathologic report. Using hyperspectral images, a library of spectral signatures for different tissues was created. The high-dimensional data were classified using a support vector machine (SVM). The spectra are extracted in cancerous and non-cancerous tissues in lymph nodes and lung tissues. The spectral dimension is used as the input of SVM. Twelve glasses are employed for training and evaluation. The leave-one-out cross-validation method is used in the study. After training, the proposed SVM method can detect the metastatic cancer in lung histologic slides with the specificity of 97.7% and the sensitivity of 92.6%, and in lymph node slides with the specificity of 98.3% and the sensitivity of 96.2%. This method may be able to help pathologists to evaluate many histologic slides in a short time. Akbari, Hamed Halig, Luma V Zhang, Hongzheng Wang, Dongsheng Chen, Zhuo Georgia Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States P50 CA128613/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms432042 Proc SPIE Int Soc Opt Eng. 2012;8317:831711. Epub 2012 Mar 23. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3546351/pdf/nihms432042.pdf internal-pdf://1042028793/Akbari-2012-Detection of Cancer Metastasis Usi.pdf Department of Radiology and Imaging Sciences, Emory University and Georgia Institute of Technology, Atlanta, GA. Nlm eng B. Fei, H. Akbari and L. V. Halig 2012 Hyperspectral imaging and spectral-spatial classification for cancer detection Biomedical Engineering and Informatics (BMEI), 2012 5th International Conference on IEEE 62-64 Hyperspectral imaging and spectral-spatial classification for cancer detection 1467311839 B. Fei, D. Schuster, V. Master and P. Nieh 2012 Incorporating PET/CT Images Into 3D Ultrasound-Guided Biopsy of the Prostate Medical Physics 39 6 3888-3888 Jun Incorporating PET/CT Images Into 3D Ultrasound-Guided Biopsy of the Prostate 0094-2405 WOS:000308905805331 Times Cited: 4 54th Annual Meeting and Exhibition of the American-Association-of-Physicists-in-Medicine (AAPM) JUL 29-AUG 02, 2012 Charlotte, NC Amer Assoc Physicists Med (AAPM) Fei, Baowei /E-6898-2014 Fei, Baowei /0000-0002-9123-9484 0 4 ://WOS:000308905805331 B. Fei, D. M. Schuster, V. Master, H. Akbari, A. Fenster and P. Nieh 2012 A Molecular Image-directed, 3D Ultrasound-guided Biopsy System for the Prostate Proc SPIE Int Soc Opt Eng 2012 2012/06/19 A Molecular Image-directed, 3D Ultrasound-guided Biopsy System for the Prostate 0277-786X (Print) 0277-786X (Linking) 3375601 22708023 Systematic transrectal ultrasound (TRUS)-guided biopsy is the standard method for a definitive diagnosis of prostate cancer. However, this biopsy approach uses two-dimensional (2D) ultrasound images to guide biopsy and can miss up to 30% of prostate cancers. We are developing a molecular image-directed, three-dimensional (3D) ultrasound image-guided biopsy system for improved detection of prostate cancer. The system consists of a 3D mechanical localization system and software workstation for image segmentation, registration, and biopsy planning. In order to plan biopsy in a 3D prostate, we developed an automatic segmentation method based wavelet transform. In order to incorporate PET/CT images into ultrasound-guided biopsy, we developed image registration methods to fuse TRUS and PET/CT images. The segmentation method was tested in ten patients with a DICE overlap ratio of 92.4% +/- 1.1 %. The registration method has been tested in phantoms. The biopsy system was tested in prostate phantoms and 3D ultrasound images were acquired from two human patients. We are integrating the system for PET/CT directed, 3D ultrasound-guided, targeted biopsy in human patients. Fei, Baowei Schuster, David M Master, Viraj Akbari, Hamed Fenster, Aaron Nieh, Peter R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States P50 CA128613/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362795 Proc SPIE Int Soc Opt Eng. 2012;2012. pii: 831613. Epub 2012 Feb 16. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/8316/1/A-molecular-image-directed-3D-ultrasound-guided-biopsy-system-for/10.1117/12.912182.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA 30329. Nlm eng S. S. J. Feng, K. Bliznakova, X. Qin, B. Fei and I. Sechopoulos 2012 Characterization of the Homogeneous Breast Tissue Mixture Approximation for Breast Image Dosimetry Medical Physics 39 6 3878-3878 Jun Characterization of the Homogeneous Breast Tissue Mixture Approximation for Breast Image Dosimetry 0094-2405 WOS:000308905805294 Times Cited: 1 54th Annual Meeting and Exhibition of the American-Association-of-Physicists-in-Medicine (AAPM) JUL 29-AUG 02, 2012 Charlotte, NC Amer Assoc Physicists Med (AAPM) Fei, Baowei /E-6898-2014 Fei, Baowei /0000-0002-9123-9484 0 1 ://WOS:000308905805294 T. MacDonald, J. Liu, J. Munson, J. Park, K. Wang, B. Fei, R. Bellamkonda and J. Arbiser 2012 THE APPLICATION OF NANOPARTICLE LIPOSOME-IMPRAMINE BLUE IN THE TREATMENT OF MEDULLOBLASTOMA IN THE SmoA1 TRANSGENIC MICE Neuro-Oncology 14 83-83 Jun THE APPLICATION OF NANOPARTICLE LIPOSOME-IMPRAMINE BLUE IN THE TREATMENT OF MEDULLOBLASTOMA IN THE SmoA1 TRANSGENIC MICE 1522-8517 WOS:000308394400309 Times Cited: 0 1 15th International Symposium on Pediatric Neuro-Oncology (ISPNO) JUN 24-27, 2012 Toronto, CANADA Fei, Baowei /E-6898-2014; MacDonald, Tobey/D-4554-2013 Fei, Baowei /0000-0002-9123-9484; 0 ://WOS:000308394400309 P. Taleghani, R. Amzat, A. Osunkoya, B. Savir-Baruch, P. Nieh, V. Master, B. Fei, T. Fox, M. Goodman and D. Schuster 2012 Increased expression of Ki-67 correlates with synthetic amino acid PET radiotracer uptake in prostate cancer Journal of Nuclear Medicine 53 supplement 1 1097-1097 Increased expression of Ki-67 correlates with synthetic amino acid PET radiotracer uptake in prostate cancer 0161-5505 P. Taleghani, R. Amzat, A. Osunkoya, B. Savir-Baruch, P. Nieh, V. Master, B. Fei, T. Fox, M. Goodman and D. Schuster 2012 Synthetic amino acid PET in primary prostate carcinoma: Correlation of pre-surgical imaging with radical prostatectomy specimens Journal of Nuclear Medicine 53 supplement 1 117-117 Synthetic amino acid PET in primary prostate carcinoma: Correlation of pre-surgical imaging with radical prostatectomy specimens 0161-5505 X. Yang and B. Fei 2012 3D Prostate Segmentation of Ultrasound Images Combining Longitudinal Image Registration and Machine Learning Proc SPIE Int Soc Opt Eng 8316 83162O 2012/02/23 Feb 23 3D Prostate Segmentation of Ultrasound Images Combining Longitudinal Image Registration and Machine Learning 0277-786X (Print) 0277-786X (Linking) 3767004 24027622 We developed a three-dimensional (3D) segmentation method for transrectal ultrasound (TRUS) images, which is based on longitudinal image registration and machine learning. Using longitudinal images of each individual patient, we register previously acquired images to the new images of the same subject. Three orthogonal Gabor filter banks were used to extract texture features from each registered image. Patient-specific Gabor features from the registered images are used to train kernel support vector machines (KSVMs) and then to segment the newly acquired prostate image. The segmentation method was tested in TRUS data from five patients. The average surface distance between our and manual segmentation is 1.18 +/- 0.31 mm, indicating that our automatic segmentation method based on longitudinal image registration is feasible for segmenting the prostate in TRUS images. Yang, Xiaofeng Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362793 Proc SPIE Int Soc Opt Eng. 2012 Feb 23;8316:83162O. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3767004/pdf/nihms362793.pdf internal-pdf://0172828148/Yang-2012-3D Prostate Segmentation of Ultrasou.pdf Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Nlm eng X. Yang, P. Ghafourian, P. Sharma, K. Salman, D. Martin and B. Fei 2012 Nonrigid Registration and Classification of the Kidneys in 3D Dynamic Contrast Enhanced (DCE) MR Images Proc SPIE Int Soc Opt Eng 8314 83140B 2012/04/03 Nonrigid Registration and Classification of the Kidneys in 3D Dynamic Contrast Enhanced (DCE) MR Images 0277-786X (Print) 0277-786X (Linking) 3314431 22468206 We have applied image analysis methods in the assessment of human kidney perfusion based on 3D dynamic contrast-enhanced (DCE) MRI data. This approach consists of 3D non-rigid image registration of the kidneys and fuzzy C-mean classification of kidney tissues. The proposed registration method reduced motion artifacts in the dynamic images and improved the analysis of kidney compartments (cortex, medulla, and cavities). The dynamic intensity curves show the successive transition of the contrast agent through kidney compartments. The proposed method for motion correction and kidney compartment classification may be used to improve the validity and usefulness of further model-based pharmacokinetic analysis of kidney function. Yang, Xiaofeng Ghafourian, Pegah Sharma, Puneet Salman, Khalil Martin, Diego Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362796 Proc SPIE Int Soc Opt Eng. 2012;8314:83140B. Epub 2012 Feb 13. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3314431/pdf/nihms362796.pdf internal-pdf://1173117626/Yang-2012-Nonrigid Registration and Classifica.pdf Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Nlm eng H. Akbari and B. Fei 2013 Automatic 3D Segmentation of the Kidney in MR Images Using Wavelet Feature Extraction and Probability Shape Model Proc SPIE Int Soc Opt Eng 8314 83143D 2013/09/13 Feb 23 Automatic 3D Segmentation of the Kidney in MR Images Using Wavelet Feature Extraction and Probability Shape Model 0277-786X (Print) 0277-786X (Linking) 3766988 24027620 Numerical estimation of the size of the kidney is useful in evaluating conditions of the kidney, especially, when serial MR imaging is performed to evaluate the kidney function. This paper presents a new method for automatic segmentation of the kidney in three-dimensional (3D) MR images, by extracting texture features and statistical matching of geometrical shape of the kidney. A set of Wavelet-based support vector machines (W-SVMs) is trained on the MR images. The W-SVMs capture texture priors of MRI for classification of the kidney and non-kidney tissues in different zones around the kidney boundary. In the segmentation procedure, these W-SVMs are trained to tentatively label each voxel around the kidney model as a kidney or non-kidney voxel by texture matching. A probability kidney model is created using 10 segmented MRI data. The model is initially localized based on the intensity profiles in three directions. The weight functions are defined for each labeled voxel for each Wavelet-based, intensity-based, and model-based label. Consequently, each voxel has three labels and three weights for the Wavelet feature, intensity, and probability model. Using a 3D edge detection method, the model is re-localized and the segmented kidney is modified based on a region growing method in the model region. The probability model is re-localized based on the results and this loop continues until the segmentation converges. Experimental results with mouse MRI data show the good performance of the proposed method in segmenting the kidney in MR images. Akbari, Hamed Fei, Baowei R01 CA156775-02/CA/NCI NIH HHS/United States R01 CA156775-01/CA/NCI NIH HHS/United States R01 CA156775-03/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States UL1 RR025008/RR/NCRR NIH HHS/United States P50 CA128301/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms362797 Proc SPIE Int Soc Opt Eng. 2013 Feb 23;8314:83143D. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3766988/pdf/nihms-362797.pdf internal-pdf://2392950519/Akbari-2013-Automatic 3D Segmentation of the K.pdf Department of Radiology and Imaging Sciences, Emory University and Georgia Institute of Technology, Atlanta, GA. Nlm eng X. Chen, J. Jin and B. Fei 2013 Histogram Processing-based Image Enhancement of Digital Radiography for Detection of Cardiac Calcification World Congress on Medical Physics and Biomedical Engineering May 26-31, 2012, Beijing, China Springer, Berlin, Heidelberg 939-942 Histogram Processing-based Image Enhancement of Digital Radiography for Detection of Cardiac Calcification L. V. Halig, D. Wang, A. Y. Wang, Z. G. Chen and B. Fei 2013 Biodistribution Study of Nanoparticle Encapsulated Photodynamic Therapy Drugs Using Multispectral Imaging Proc SPIE Int Soc Opt Eng 8672 2013/11/16 Mar 29 Biodistribution Study of Nanoparticle Encapsulated Photodynamic Therapy Drugs Using Multispectral Imaging 0277-786X (Print) 0277-786X (Linking) 3824266 24236230 Photodynamictherapy (PDT) uses a drug called a photosensitizer that is excited by irradiation with a laser light of a particular wavelength, which generates reactive singlet oxygen that damages the tumor cells. The photosensitizer and light are inert; therefore, systemic toxicities are minimized in PDT. The synthesis of novel PDT drugs and the use of nanosized carriers for photosensitizers may improve the efficiency of the therapy and the delivery of the drug. In this study, we formulated two nanoparticles with and without a targeting ligand to encapsulate phthalocyanines 4 (Pc 4) molecule and compared their biodistributions. Metastatic human head and neck cancer cells (M4e) were transplanted into nude mice. After 2-3 weeks, the mice were injected with Pc 4, Pc 4 encapsulated into surface coated iron oxide (IO-Pc 4), and IO-Pc 4 conjugated with a fibronectin-mimetic peptide (FMP-IO-Pc 4) which binds specifically to integrin beta1. The mice were imaged using a multispectral camera. Using multispectral images, a library of spectral signatures was created and the signal per pixel of each tumor was calculated, in a grayscale representation of the unmixed signal of each drug. An enhanced biodistribution of nanoparticle encapsulated PDT drugs compared to non-formulated Pc 4 was observed. Furthermore, specific targeted nanoparticles encapsulated Pc 4 has a quicker delivery time and accumulation in tumor tissue than the non-targeted nanoparticles. The nanoparticle-encapsulated PDT drug can have a variety of potential applications in cancer imaging and treatment. Halig, Luma V Wang, Dongsheng Wang, Andrew Y Chen, Zhuo Georgia Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R21 CA120536/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms514146 Proc SPIE Int Soc Opt Eng. 2013 Mar 29;8672. doi: 10.1117/12.2006492. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/8672/1/Biodistribution-study-of-nanoparticle-encapsulated-photodynamic-therapy-drugs-using-multispectral/10.1117/12.2006492.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Nlm eng X. Qin, Z. Cong, L. V. Halig and B. Fei 2013 Automatic Segmentation of Right Ventricle on Ultrasound Images Using Sparse Matrix Transform and Level Set Proc SPIE Int Soc Opt Eng 8669 2013/11/16 Mar 13 Automatic Segmentation of Right Ventricle on Ultrasound Images Using Sparse Matrix Transform and Level Set 0277-786X (Print) 0277-786X (Linking) 3824270 24236228 An automatic framework is proposed to segment right ventricle on ultrasound images. This method can automatically segment both epicardial and endocardial boundaries from a continuous echocardiography series by combining sparse matrix transform (SMT), a training model, and a localized region based level set. First, the sparse matrix transform extracts main motion regions of myocardium as eigenimages by analyzing statistical information of these images. Second, a training model of right ventricle is registered to the extracted eigenimages in order to automatically detect the main location of the right ventricle and the corresponding transform relationship between the training model and the SMT-extracted results in the series. Third, the training model is then adjusted as an adapted initialization for the segmentation of each image in the series. Finally, based on the adapted initializations, a localized region based level set algorithm is applied to segment both epicardial and endocardial boundaries of the right ventricle from the whole series. Experimental results from real subject data validated the performance of the proposed framework in segmenting right ventricle from echocardiography. The mean Dice scores for both epicardial and endocardial boundaries are 89.1%+/-2.3% and 83.6+/-7.3%, respectively. The automatic segmentation method based on sparse matrix transform and level set can provide a useful tool for quantitative cardiac imaging. Qin, Xulei Cong, Zhibin Halig, Luma V Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms514138 Proc SPIE Int Soc Opt Eng. 2013 Mar 13;8669. doi: 10.1117/12.2006490. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/8669/1/Automatic-segmentation-of-right-ventricle-on-ultrasound-images-using-sparse/10.1117/12.2006490.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Nlm eng X. Qin, Z. Cong, R. Jiang, M. Shen, M. B. Wagner, P. Kishbom and B. Fei 2013 Extracting Cardiac Myofiber Orientations from High Frequency Ultrasound Images Proc SPIE Int Soc Opt Eng 8675 2014/01/07 Mar 29 Extracting Cardiac Myofiber Orientations from High Frequency Ultrasound Images 0277-786X (Print) 0277-786X (Linking) 3877319 24392208 Cardiac myofiber plays an important role in stress mechanism during heart beating periods. The orientation of myofibers decides the effects of the stress distribution and the whole heart deformation. It is important to image and quantitatively extract these orientations for understanding the cardiac physiological and pathological mechanism and for diagnosis of chronic diseases. Ultrasound has been wildly used in cardiac diagnosis because of its ability of performing dynamic and noninvasive imaging and because of its low cost. An extraction method is proposed to automatically detect the cardiac myofiber orientations from high frequency ultrasound images. First, heart walls containing myofibers are imaged by B-mode high frequency (>20 MHz) ultrasound imaging. Second, myofiber orientations are extracted from ultrasound images using the proposed method that combines a nonlinear anisotropic diffusion filter, Canny edge detector, Hough transform, and K-means clustering. This method is validated by the results of ultrasound data from phantoms and pig hearts. Qin, Xulei Cong, Zhibin Jiang, Rong Shen, Ming Wagner, Mary B Kishbom, Paul Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms514141 Proc SPIE Int Soc Opt Eng. 2013 Mar 29;8675. doi: 10.1117/12.2006494. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/8675/1/Extracting-cardiac-myofiber-orientations-from-high-frequency-ultrasound-images/10.1117/12.2006494.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Pediatrics, Emory University School of Medicine, Atlanta, GA. Department of Surgery, Emory University School of Medicine, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA ; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology ; Department of Mathematics & Computer Science, Emory University, Atlanta, GA. Nlm eng W. J. Wooten III, J. A. Nye, D. M. Schuster, P. T. Nieh, V. A. Master, J. R. Votaw and B. Fei 2013 Accuracy evaluation of a 3D ultrasound-guided biopsy system Proceedings of SPIE NIH Public Access 8671 Accuracy evaluation of a 3D ultrasound-guided biopsy system B. Fei, G. Lu, R. Pike, D. Wang and G. Chen 2014 WE-D-9A-05: Medical Hyperspectral Imaging for the Detection of Head and Neck Cancer in Animal Models Medical Physics American Association of Physicists in Medicine 41 6Part29 500-501 WE-D-9A-05: Medical Hyperspectral Imaging for the Detection of Head and Neck Cancer in Animal Models 2473-4209 Medical imaging Cancer Tissues Biomedical modeling Animals Comparative animal models Image analysis Tissue engineering Fluorescence Experiment design Purpose:: The objective of this study is to develop hyperspectral imaging technology and advanced image analysis methods for the detection of head and neck cancer. Methods:: A head and neck tumor xenograft model was used in the experiment. The M4E head and neck cancer cells with green fluorescence protein (GFP) were injected into nude mice. Hyperspectral images were acquired from the tumor-bearing mice using a CRI Maestro invivo imaging camera. The wavelength setting was defined within the range of 450–950 nm with 2 nm increments. Two advanced image classification methods were developed to classify normal and cancer tissue on hyperspectral images. In the first method, a tensor-based computation and modeling framework was proposed for the analysis of hyperspectral images for cancer detection. In the second classification method, support vector machines were incorporated into a minimum spanning forest algorithm for differentiating cancer tissue from normal tissue. The classification results were validated by the GPP images of the same animals. Results:: The tensor-based classification method can distinguish between malignant tissue and healthy tissue with an average sensitivity of 97.0% and an average specificity of 91.4% in tumor-bearing mice. The minimum spanning forest algorithm also achieved a high accuracy of more than 97.0% in the animal model. Conclusion:: The hyperspectral imaging and classification technology has been demonstrated in animal models and can have many potential applications in cancer research and management. This research is supported in part by NIH grants (R01CA156775, R21CA176684, and P50CA128301) and Georgia Cancer Coalition Distinguished Clinicians and Scientists Award. http://dx.doi.org/10.1118/1.4889421 B. Fei, P. Nieh, D. Schuster and V. Master 2014 Multimodality molecular imaging for targeted biospy of prostate cancer The 2nd International Conference of Biomedical Engineering Beijing, China June 13-15, 2014 Multimodality molecular imaging for targeted biospy of prostate cancer B. Fei, X. Qin, S. Wang, M. Shen, M. Wagner and X. Zhang 2014 TU-F-12A-07: Cardiac Fiber Imaging Using High-Frequency Ultrasound in Animal Models Medical Physics American Association of Physicists in Medicine 41 6Part28 482-482 TU-F-12A-07: Cardiac Fiber Imaging Using High-Frequency Ultrasound in Animal Models 2473-4209 Ultrasonography Heart Magnetic resonance imaging Animals Comparative animal models Ultrasonic transducers Heart disease Mechanical properties Audiometry Purpose:: Cardiac fibers directly affect the mechanical and electrophysiological properties of the heart. The objective of this study is to explore high-frequency ultrasound imaging for measuring cardiac fiber orientation in an animal model. Methods:: An ex vivo heart model was used in this study. The hearts of male rats were excised, perfused, fixed, and embedded in agar phantoms for two imaging procedures. First, the hearts were first imaged by the Vevo 2100 ultrasound system with a 30 MHz transducer. Second, the hearts were then scanned using a Biospec 7 T MRI system for high-resolution MRI and diffusion tensor imaging (DTI). The geometry of the heart extracted from the MRI is registered with the 3D ultrasound using deformable registration. After registration, deformation fields between both geometries from MRI and ultrasound are obtained. The cardiac fiber orientations imaged by DTI are mapped to ultrasound volumes based on the extracted deformation fields. The registration between 3D ultrasound and MRI of different hearts, e.g. one from the atlas, was further tested. The DTI fiber orientation from the atlas was then mapped to the ultrasound image of a different heart. By this way, we provide a DTI atlas based framework to estimate cardiac fiber orientations from 3D ultrasound images. Results:: After MRI/ultrasound image registration, the Dice similarity scores were more than 90% and the corresponding target errors were less than 0.25 mm. For the atlas-based method, the evaluation results demonstrated the feasibility of determining cardiac fiber orientations from 3D ultrasound. Conclusion:: An atlas-based fiber orientation estimation method was proposed and evaluated for the extraction of cardiac fiber orientation in an animal model. This method and its further improvements in vivo could contribute to understand the cardiac mechanism and help the diagnosis and therapy of heart disease. This research is supported in part by NIH grants (R01CA156775 and R21CA176684), Georgia Research Alliance Distinguished Scientists Award, and the Emory Molecular and Translational Imaging Center (NIH P50CA128301). http://dx.doi.org/10.1118/1.4889362 G. Lu, L. Halig, D. Wang, Z. G. Chen and B. Fei 2014 Hyperspectral imaging for cancer surgical margin delineation: registration of hyperspectral and histological images Proceedings of SPIE NIH Public Access 9036 90360S Hyperspectral imaging for cancer surgical margin delineation: registration of hyperspectral and histological images https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4201054/pdf/nihms613556.pdf internal-pdf://1635925713/Lu-2014-Hyperspectral imaging for cancer surgi.pdf G. Lu, L. Halig, D. Wang, Z. G. Chen and B. Fei 2014 Spectral-spatial classification using tensor modeling for cancer detection with hyperspectral imaging Proceedings of SPIE NIH Public Access 9034 903413 Spectral-spatial classification using tensor modeling for cancer detection with hyperspectral imaging https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4201059/pdf/nihms-613551.pdf internal-pdf://0079515804/Lu-2014-Spectral-spatial classification using.pdf R. Pike, S. K. Patton, G. Lu, L. V. Halig, D. Wang, Z. G. Chen and B. Fei 2014 A minimum spanning forest based hyperspectral image classification method for cancerous tissue detection Proceedings of SPIE NIH Public Access 9034 90341W A minimum spanning forest based hyperspectral image classification method for cancerous tissue detection https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4241346/pdf/nihms613555.pdf internal-pdf://1577815265/Pike-2014-A minimum spanning forest based hype.pdf X. Qin, G. Lu, I. Sechopoulos and B. Fei 2014 Breast Tissue Classification in Digital Tomosynthesis Images Based on Global Gradient Minimization and Texture Features Proc SPIE Int Soc Opt Eng 9034 90341V 2014/11/27 Mar 21 Breast Tissue Classification in Digital Tomosynthesis Images Based on Global Gradient Minimization and Texture Features 0277-786X (Print) 0277-786X (Linking) 4241347 25426271 Digital breast tomosynthesis (DBT) is a pseudo-three-dimensional x-ray imaging modality proposed to decrease the effect of tissue superposition present in mammography, potentially resulting in an increase in clinical performance for the detection and diagnosis of breast cancer. Tissue classification in DBT images can be useful in risk assessment, computer-aided detection and radiation dosimetry, among other aspects. However, classifying breast tissue in DBT is a challenging problem because DBT images include complicated structures, image noise, and out-of-plane artifacts due to limited angular tomographic sampling. In this project, we propose an automatic method to classify fatty and glandular tissue in DBT images. First, the DBT images are pre-processed to enhance the tissue structures and to decrease image noise and artifacts. Second, a global smooth filter based on L0 gradient minimization is applied to eliminate detailed structures and enhance large-scale ones. Third, the similar structure regions are extracted and labeled by fuzzy C-means (FCM) classification. At the same time, the texture features are also calculated. Finally, each region is classified into different tissue types based on both intensity and texture features. The proposed method is validated using five patient DBT images using manual segmentation as the gold standard. The Dice scores and the confusion matrix are utilized to evaluate the classified results. The evaluation results demonstrated the feasibility of the proposed method for classifying breast glandular and fat tissue on DBT images. Qin, Xulei Lu, Guolan Sechopoulos, Ioannis Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R01 CA163746/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms613554 Proc SPIE Int Soc Opt Eng. 2014 Mar 21;9034:90341V. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4241347/pdf/nihms613554.pdf internal-pdf://3322851385/Qin-2014-Breast Tissue Classification in Digit.pdf Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA ; Winship Cancer Institute, Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA ; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA ; Department of Mathematics & Computer Science, Emory University, Atlanta, GA ; Winship Cancer Institute, Emory University, Atlanta, GA. Nlm eng X. Qin, S. Wang, M. Shen, X. Zhang, M. B. Wagner and B. Fei 2014 Mapping Cardiac Fiber Orientations from High-Resolution DTI to High-Frequency 3D Ultrasound Proc SPIE Int Soc Opt Eng 9036 90361O 2014/10/21 Mar 12 Mapping Cardiac Fiber Orientations from High-Resolution DTI to High-Frequency 3D Ultrasound 0277-786X (Print) 0277-786X (Linking) 4201058 25328641 The orientation of cardiac fibers affects the anatomical, mechanical, and electrophysiological properties of the heart. Although echocardiography is the most common imaging modality in clinical cardiac examination, it can only provide the cardiac geometry or motion information without cardiac fiber orientations. If the patient's cardiac fiber orientations can be mapped to his/her echocardiography images in clinical examinations, it may provide quantitative measures for diagnosis, personalized modeling, and image-guided cardiac therapies. Therefore, this project addresses the feasibility of mapping personalized cardiac fiber orientations to three-dimensional (3D) ultrasound image volumes. First, the geometry of the heart extracted from the MRI is translated to 3D ultrasound by rigid and deformable registration. Deformation fields between both geometries from MRI and ultrasound are obtained after registration. Three different deformable registration methods were utilized for the MRI-ultrasound registration. Finally, the cardiac fiber orientations imaged by DTI are mapped to ultrasound volumes based on the extracted deformation fields. Moreover, this study also demonstrated the ability to simulate electricity activations during the cardiac resynchronization therapy (CRT) process. The proposed method has been validated in two rat hearts and three canine hearts. After MRI/ultrasound image registration, the Dice similarity scores were more than 90% and the corresponding target errors were less than 0.25 mm. This proposed approach can provide cardiac fiber orientations to ultrasound images and can have a variety of potential applications in cardiac imaging. Qin, Xulei Wang, Silun Shen, Ming Zhang, Xiaodong Wagner, Mary B Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms613557 Proc SPIE Int Soc Opt Eng. 2014 Mar 12;9036:90361O. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4201058/pdf/nihms613557.pdf internal-pdf://0499192623/Qin-2014-Mapping Cardiac Fiber Orientations fr.pdf Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Yerkes National Primate Research Center, Emory University, Atlanta, GA. Department of Pediatrics, Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA ; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA. Nlm eng D. Wang, X. Qin, G. Qian, L. Halig, B. Fei, Z. Chen, Z. G. Chen, N. F. Saba, D. M. Shin and H. Xu 2014 EGFR targeted iron-oxide nanoparticles for photodynamic therapy in head and neck cancer American Association for Cancer Research EGFR targeted iron-oxide nanoparticles for photodynamic therapy in head and neck cancer 0008-5472 S. Wang, X. Qin, X. Zhang, M. Wagner and B. Fei 2014 Imaging and visualization of cardiac muscle microstructure in rats using high-resolution MRI Annual Meeting of The Internation Society for Magnetic Resonance in Medicine (ISMRM) 2014 Milan, Italy May 10-16, 2014 Imaging and visualization of cardiac muscle microstructure in rats using high-resolution MRI G. Lu, X. Qin, D. Wang, Z. G. Chen and B. Fei 2015 Quantitative Wavelength Analysis and Image Classification for Intraoperative Cancer Diagnosis with Hyperspectral Imaging Proc SPIE Int Soc Opt Eng 9415 2015/11/03 Feb 21 Quantitative Wavelength Analysis and Image Classification for Intraoperative Cancer Diagnosis with Hyperspectral Imaging 0277-786X (Print) 0277-786X (Linking) 4625919 26523083 Complete surgical removal of tumor tissue is essential for postoperative prognosis after surgery. Intraoperative tumor imaging and visualization are an important step in aiding surgeons to evaluate and resect tumor tissue in real time, thus enabling more complete resection of diseased tissue and better conservation of healthy tissue. As an emerging modality, hyperspectral imaging (HSI) holds great potential for comprehensive and objective intraoperative cancer assessment. In this paper, we explored the possibility of intraoperative tumor detection and visualization during surgery using HSI in the wavelength range of 450 nm - 900 nm in an animal experiment. We proposed a new algorithm for glare removal and cancer detection on surgical hyperspectral images, and detected the tumor margins in five mice with an average sensitivity and specificity of 94.4% and 98.3%, respectively. The hyperspectral imaging and quantification method have the potential to provide an innovative tool for image-guided surgery. Lu, Guolan Qin, Xulei Wang, Dongsheng Chen, Zhuo Georgia Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms716024 Proc SPIE Int Soc Opt Eng. 2015 Feb 21;9415. pii: 94151B. Epub 2015 Mar 18. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9415/1/Quantitative-wavelength-analysis-and-image-classification-for-intraoperative-cancer-diagnosis/10.1117/12.2082284.short The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Hematology and Medical Oncology, Emory University, Atlanta, GA. The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA ; Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA ; Department of Mathematics & Computer Science, Emory University, Atlanta, GA ; Winship Cancer Institute of Emory University, Atlanta, GA. Nlm eng G. Lu, X. Qin, D. Wang, Z. G. Chen and B. Fei 2015 Estimation of tissue optical parameters with hyperspectral imaging and spectral unmixing Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9417 Estimation of tissue optical parameters with hyperspectral imaging and spectral unmixing X. Qin, S. Wang, M. Shen, X. Zhang, S. Lerakis, M. B. Wagner and B. Fei 2015 Register cardiac fiber orientations from 3D DTI volume to 2D ultrasound image of rat hearts Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9415 Register cardiac fiber orientations from 3D DTI volume to 2D ultrasound image of rat hearts X. Qin, S. Wang, M. Shen, X. Zhang, S. Lerakis, M. B. Wagner and B. Fei 2015 3D in vivo imaging of rat hearts by high frequency ultrasound and its application in myofiber orientation wrapping Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9419 3D in vivo imaging of rat hearts by high frequency ultrasound and its application in myofiber orientation wrapping F. Tade, O. Odewole, R. Halkar, P. Mittal, P. Nieh, P. Rossi, B. Fei, B. Savir-Baruch, M. Goodman and D. Schuster 2015 Anti-[18F] FACBC (FACBC) PET-CT and multiparametric MR (mp-MR) imaging in the detection of recurrent prostate cancer Journal of Nuclear Medicine 56 supplement 3 456-456 Anti-[18F] FACBC (FACBC) PET-CT and multiparametric MR (mp-MR) imaging in the detection of recurrent prostate cancer 0161-5505 Z. Tian, L. Liu and B. Fei 2015 A supervoxel-based segmentation method for prostate MR images Proc SPIE Int Soc Opt Eng 9413 2016/02/06 Mar 20 A supervoxel-based segmentation method for prostate MR images 0277-786X (Print) 0277-786X (Linking) 4736748 26848206 Accurate segmentation of the prostate has many applications in prostate cancer diagnosis and therapy. In this paper, we propose a "Supervoxel" based method for prostate segmentation. The prostate segmentation problem is considered as assigning a label to each supervoxel. An energy function with data and smoothness terms is used to model the labeling process. The data term estimates the likelihood of a supervoxel belongs to the prostate according to a shape feature. The geometric relationship between two neighboring supervoxels is used to construct a smoothness term. A three-dimensional (3D) graph cut method is used to minimize the energy function in order to segment the prostate. A 3D level set is then used to get a smooth surface based on the output of the graph cut. The performance of the proposed segmentation algorithm was evaluated with respect to the manual segmentation ground truth. The experimental results on 12 prostate volumes showed that the proposed algorithm yields a mean Dice similarity coefficient of 86.9%+/-3.2%. The segmentation method can be used not only for the prostate but also for other organs. Tian, Zhiqiang Liu, LiZhi Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms716021 Proc SPIE Int Soc Opt Eng. 2015 Mar 20;9413. pii: 941318. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9413/1/A-supervoxel-based-segmentation-method-for-prostate-MR-images/10.1117/12.2082255.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology. Nlm eng Z. Tian, L. Liu and B. Fei 2015 A fully automatic multi-atlas based segmentation method for prostate MR images Proc SPIE Int Soc Opt Eng 9413 2016/01/23 Mar 20 A fully automatic multi-atlas based segmentation method for prostate MR images 0277-786X (Print) 0277-786X (Linking) 4717836 26798187 Most of multi-atlas segmentation methods focus on the registration between the full-size volumes of the data set. Although the transformations obtained from these registrations may be accurate for the global field of view of the images, they may not be accurate for the local prostate region. This is because different magnetic resonance (MR) images have different fields of view and may have large anatomical variability around the prostate. To overcome this limitation, we proposed a two-stage prostate segmentation method based on a fully automatic multi-atlas framework, which includes the detection stage i.e. locating the prostate, and the segmentation stage i.e. extracting the prostate. The purpose of the first stage is to find a cuboid that contains the whole prostate as small cubage as possible. In this paper, the cuboid including the prostate is detected by registering atlas edge volumes to the target volume while an edge detection algorithm is applied to every slice in the volumes. At the second stage, the proposed method focuses on the registration in the region of the prostate vicinity, which can improve the accuracy of the prostate segmentation. We evaluated the proposed method on 12 patient MR volumes by performing a leave-one-out study. Dice similarity coefficient (DSC) and Hausdorff distance (HD) are used to quantify the difference between our method and the manual ground truth. The proposed method yielded a DSC of 83.4%+/-4.3%, and a HD of 9.3 mm+/-2.6 mm. The fully automated segmentation method can provide a useful tool in many prostate imaging applications. Tian, Zhiqiang Liu, LiZhi Fei, Baowei P50 CA128301/CA/NCI NIH HHS/United States R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms716023 Proc SPIE Int Soc Opt Eng. 2015 Mar 20;9413. pii: 941340. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9413/1/A-fully-automatic-multi-atlas-based-segmentation-method-for-prostate/10.1117/12.2082229.short Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology. Nlm eng H. Chung, G. Lu, Z. Tian, D. Wang, Z. G. Chen and B. Fei 2016 Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9788 Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging J. Dormer, X. Qin, M. Shen, S. Wang, X. Zhang, R. Jiang, M. B. Wagner and B. Fei 2016 Determining Cardiac Fiber Orientation Using FSL and Registered Ultrasound/DTI volumes Proc SPIE Int Soc Opt Eng 9790 2016/09/24 Feb 27 Determining Cardiac Fiber Orientation Using FSL and Registered Ultrasound/DTI volumes 0277-786X (Print) 0277-786X (Linking) 5029420 27660384 Accurate extraction of cardiac fiber orientation from diffusion tensor imaging is important for determining heart structure and function. However, the acquisition of magnetic resonance (MR) diffusion tensor images is costly and time consuming. By comparison, cardiac ultrasound imaging is rapid and relatively inexpensive, but it lacks the capability to directly measure fiber orientations. In order to create a detailed heart model from ultrasound data, a three-dimensional (3D) diffusion tensor imaging (DTI) with known fiber orientations can be registered to an ultrasound volume through a geometric mask. After registration, the cardiac orientations from the template DTI can be mapped to the heart using a deformable transformation field. This process depends heavily on accurate fiber orientation extraction from the DTI. In this study, we use the FMRIB Software Library (FSL) to determine cardiac fiber orientations in diffusion weighted images. For the registration between ultrasound and MRI volumes, we achieved an average Dice similarity coefficient (DSC) of 81.6+/-2.1%. For the estimation of fiber orientations from the proposed method, we achieved an acute angle error (AAE) of 22.7+/-3.1 degrees as compared to the direct measurements from DTI. This work provides a new approach to generate cardiac fiber orientation that may be used for many cardiac applications. Dormer, James Qin, Xulei Shen, Ming Wang, Silun Zhang, Xiaodong Jiang, Rong Wagner, Mary B Fei, Baowei R01 CA156775/CA/NCI NIH HHS/United States R21 CA120536/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms816058 Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9790. pii: 979015. Epub 2016 Apr 1. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9790/1/Determining-cardiac-fiber-orientation-using-FSL-and-registered-ultrasound-DTI/10.1117/12.2217296.short Department of Nuclear and Radiological Engineering, George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Pediatrics, Emory University, Atlanta, GA. Yerkes National Primate Research Center, Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA. Nlm eng G. Lu, X. Qin, D. Wang, S. Muller, H. Zhang, A. Chen, Z. G. Chen and B. Fei 2016 Quantitative Diagnosis of Tongue Cancer from Histological Images in an Animal Model Proc SPIE Int Soc Opt Eng 9791 2016/09/23 Feb 27 Quantitative Diagnosis of Tongue Cancer from Histological Images in an Animal Model 0277-786X (Print) 0277-786X (Linking) 5028209 27656036 We developed a chemically-induced oral cancer animal model and a computer aided method for tongue cancer diagnosis. The animal model allows us to monitor the progress of the lesions over time. Tongue tissue dissected from mice was sent for histological processing. Representative areas of hematoxylin and eosin (H&E) stained tissue from tongue sections were captured for classifying tumor and non-tumor tissue. The image set used in this paper consisted of 214 color images (114 tumor and 100 normal tissue samples). A total of 738 color, texture, morphometry and topology features were extracted from the histological images. The combination of image features from epithelium tissue and its constituent nuclei and cytoplasm has been demonstrated to improve the classification results. With ten iteration nested cross validation, the method achieved an average sensitivity of 96.5% and a specificity of 99% for tongue cancer detection. The next step of this research is to apply this approach to human tissue for computer aided diagnosis of tongue cancer. Lu, Guolan Qin, Xulei Wang, Dongsheng Muller, Susan Zhang, Hongzheng Chen, Amy Chen, Zhuo Georgia Fei, Baowei R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms816055 Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9791. pii: 97910L. Epub 2016 Mar 23. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9791/1/Quantitative-diagnosis-of-tongue-cancer-from-histological-images-in-an/10.1117/12.2217286.short The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Hematology and Medical Oncology, Emory University, Atlanta, GA. Department of Otolaryngology, Emory University School of Medicine, Atlanta, GA. The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA; Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Mathematics & Computer Science, Emory University, Atlanta, GA; Winship Cancer Institute of Emory University, Atlanta, GA. Nlm eng G. Lu, X. Qin, D. Wang, S. Muller, H. Zhang, A. Chen, Z. G. Chen and B. Fei 2016 Hyperspectral Imaging of Neoplastic Progression in a Mouse Model of Oral Carcinogenesis Proc SPIE Int Soc Opt Eng 9788 2016/09/23 Feb 27 Hyperspectral Imaging of Neoplastic Progression in a Mouse Model of Oral Carcinogenesis 0277-786X (Print) 0277-786X (Linking) 5028204 27656034 Hyperspectral imaging (HSI) is an emerging modality for medical applications and holds great potential for noninvasive early detection of cancer. It has been reported that early cancer detection can improve the survival and quality of life of head and neck cancer patients. In this paper, we explored the possibility of differentiating between premalignant lesions and healthy tongue tissue using hyperspectral imaging in a chemical induced oral cancer animal model. We proposed a novel classification algorithm for cancer detection using hyperspectral images. The method detected the dysplastic tissue with an average area under the curve (AUC) of 0.89. The hyperspectral imaging and classification technique may provide a new tool for oral cancer detection. Lu, Guolan Qin, Xulei Wang, Dongsheng Muller, Susan Zhang, Hongzheng Chen, Amy Chen, Zhuo Georgia Fei, Baowei R01 CA156775/CA/NCI NIH HHS/United States R21 CA176684/CA/NCI NIH HHS/United States United States Proceedings of SPIE--the International Society for Optical Engineering Nihms816056 Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9788. pii: 978812. Epub 2016 Mar 29. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9788/1/Hyperspectral-imaging-of-neoplastic-progression-in-a-mouse-model-of/10.1117/12.2216553.short The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA. Department of Hematology and Medical Oncology, Emory University, Atlanta, GA. Department of Otolaryngology, Emory University School of Medicine, Atlanta, GA. The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA; Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Mathematics & Computer Science, Emory University, Atlanta, GA; Winship Cancer Institute of Emory University, Atlanta, GA. Nlm eng L. Ma, R. Guo, Z. Tian, R. Venkataraman, S. Sarkar, X. Liu, P. T. Nieh, V. V. Master, D. M. Schuster and B. Fei 2016 Random walk based segmentation for the prostate on 3D transrectal ultrasound images Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9786 Random walk based segmentation for the prostate on 3D transrectal ultrasound images L. Ma, R. Guo, Z. Tian, R. Venkataraman, S. Sarkar, X. Liu, F. Tade, D. M. Schuster and B. Fei 2016 Combining population and patient-specific characteristics for prostate segmentation on 3D CT images Proceedings of SPIE--the International Society for Optical Engineering NIH Public Access 9784 Combining population and patient-specific characteristics for prostate segmentation on 3D CT images O. Akin-Akintayo, F. Tade, P. Mittal, C. Moreno, P. Nieh, P. Rossi, H. Raghuveer, B. Fei, M. Goodman and D. Schuster 2017 MP18-08 COMPARISON OF FLUCICLOVINE (18F) PET-CT AND MRI IN DETECTION OF RECURRENT PROSTATE CANCER The Journal of Urology 197 4 e222-e223 MP18-08 COMPARISON OF FLUCICLOVINE (18F) PET-CT AND MRI IN DETECTION OF RECURRENT PROSTATE CANCER 0022-5347 J. Dormer, R. Jiang, M. B. Wagner and B. Fei 2017 A new method to quantify fiber orientation similarity in registered volumes SPIE Medical Imaging International Society for Optics and Photonics 101361I-101361I-6 A new method to quantify fiber orientation similarity in registered volumes J. D. Dormer, Y. Meng, X. Zhang, R. Jiang, M. B. Wagner and B. Fei 2017 Estimating cardiac fiber orientations in pig hearts using registered ultrasound and MR image volumes SPIE Medical Imaging International Society for Optics and Photonics 101391G-101391G-6 Estimating cardiac fiber orientations in pig hearts using registered ultrasound and MR image volumes B. Fei, G. Lu, X. Wang, H. Zhang, J. V. Little, K. R. Magliocca and A. Y. Chen 2017 Tumor margin assessment of surgical tissue specimen of cancer patients using label-free hyperspectral imaging Proc. of SPIE Vol 10054 100540E-1 Tumor margin assessment of surgical tissue specimen of cancer patients using label-free hyperspectral imaging L. Ma, R. Guoa, G. Zhanga, F. Tadea, D. M. Schustera, P. Niehc, V. Masterc and B. Fei 2017 Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion SPIE Medical Imaging International Society for Optics and Photonics 101332O-101332O-9 Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion L. Ma, G. Luc, D. Wangd, X. Wangd, Z. G. Chend, S. Mullere, A. Chene and B. Fei 2017 Deep Learning based Classification for Head and Neck Cancer Detection with Hyperspectral Imaging in an Animal Model SPIE Medical Imaging International Society for Optics and Photonics 101372G-101372G-8 Deep Learning based Classification for Head and Neck Cancer Detection with Hyperspectral Imaging in an Animal Model C. Ormenisan-Gherasim, F. Tade, O. O. Akin-Akintayo, B. Bilir, W. G. Wiles, G. Lu, B. Fei, C. S. Moreno, M. M. Goodman and D. M. Schuster 2017 Does Injection of 2-Aminobicyclo-(2, 2, 1)-Heptane-2-Carboxylic Acid (BCH) Affect Amino Acid Transporter Density in Prostate Cancer Xenografts? LABORATORY INVESTIGATION NATURE PUBLISHING GROUP 75 VARICK ST, 9TH FLR, NEW YORK, NY 10013-1917 USA 97 247A-247A Does Injection of 2-Aminobicyclo-(2, 2, 1)-Heptane-2-Carboxylic Acid (BCH) Affect Amino Acid Transporter Density in Prostate Cancer Xenografts? 0023-6837 Z. Tian, L. Liu and B. Fei 2017 Deep convolutional neural network for prostate MR segmentation SPIE Medical Imaging International Society for Optics and Photonics 101351L-101351L-6 Deep convolutional neural network for prostate MR segmentation