Center for Computational Imaging and Personalized Diagnostics (CCIPD)
2012 Annual Report
Director: Dr. Anant MadabhushiAssociate Professor,
Department of Biomedical Engineering
LCIB-CCIPD Transition
LCIB Website
CCIPD LG meeting schedule webpage
We have moved! LCIB is now the Center of Computational Imaging and Personalized Diagnostics (CCIPD) within the Department of Biomedical Engineering at Case Western Reserve University.
Dr. Madabhushi and 12 members relocated to start CCIPD at CWRU.
2
CCIPD in 2012
Faculty Offices Center Space Center Entrance
525 Wickenden BuildingDept. of Biomedical EngineeringCase Western Reserve University2071 Martin Luther King Drive
Cleveland, Ohio 44106-7207
3
Center Members
Farewell dinner in NJ, August 2012
Group dinner in Cleveland, Sept. 2012
4
CCIPD Members
Research Faculty Satish Viswanath, PhD Pallavi Tiwari, PhD
Research Associates Mirabela Rusu, PhD Tao Wan, PhD Haibo Wang, PhD
Undergraduate Students Eileen Huang* Sudha Karthigeyan* Aparna Kannan* Srivathsan Prabhu* Gabriel Ewing
Julian Modesto * Michael Yim*
Graduate Students Andrew Janowczyk (IIT, Bombay) Rachel Sparks (Rutgers, NJ) Ajay Basavanhally (Rutgers, NJ) George Lee (Rutgers, NJ) Rob Toth (Rutgers, NJ) Shoshana Ginsburg Sahir Ali Asha Singanamalli
* At Rutgers University
Center Director: Dr. Anant Madabhushi
5
Center Members
Center DirectorDr. Anant Madabhushi, PhD
Research Faculty
Pallavi Tiwari, PhD Satish Viswanath, PhDResearch Associates
Mirabela Rusu, PhD Tao Wan, PhD Haibo Wang, PhD
6
Center MembersGraduate Students
Ajay Basavanhally Andrew Janowczyk George Lee Shoshana GinsburgSahir Ali
Rachel Sparks Rob Toth Asha Singanamalli
7
Recent Alumni
Jun Xu, PhDProfessor at Nanjing University
Research Faculty
Gaoyu Xiao, PhD
PhD Students
PostDocs
James Monaco, PhDResearch Scientist atVuCOMP
Pallavi Tiwari, PhDGraduated from LCIB in May, 2012Research Faculty at Case Western Reserve University
Satish Viswanath, PhDGraduated from LCIB in May, 2012Research Faculty at Case Western Reserve University
Shannon Agner4th year medical student at UMDNJ-RWJMS
8
Recent AlumniPhD Students
Master Students
Jon Chappelow, PhDResearch Scientist atAccuray Inc.
Scott Doyle, PhDResearch Scientist at Ibris Inc.
Akshay ShridarAssistant ProjectManager at IntegraLife Sciences
Najeeb ChowdhuryHealthcare MarketResearch Analystat AlphaDetail Inc.
Rhonda Breen-SimoneAdministrative Assistant at Dept. of Nutritional Sciences, Rutgers University
Assistant
9
Recent Alumni
Joe GaleroGraduate Student at Johns Hopkins
University
Elaine YuGraduate Student at UC Berkeley
Pratik PatelIntern at BioLite
Abhishek GolugulaEmployee at Accenture
Undergraduate Students
10
Acknowledging just some of our outstanding clinical collaborators
John E. Tomaszewski with Bill ClintonDan Sperling (left), Michael D. Feldman (second from right), B. Nicolas Bloch (right)
CCIPD also acknowledges the larger number of excellent clinical collaborators across CINJ, Rutgers, Case Western, MD Anderson, UT Southwestern Dallas, UCSF, UPENN, SUNY Buffalo, NYU we have been privileged to work with.
11
Student Accomplishments
Pallavi Tiwari and Satish Viswanath at the 2012 Graduate Reception having obtained
their PhDs, May 2012.
Group photo with Pallavi Tiwari & Satish Viswanath immediately after their
successful PhD thesis defense, April 2012
12
Conference Participation 2012
RSNA: Satish Viswanath delivering an oral talk, Nov. 2012.
SPIE 2012 Best Poster (Cum Laude) in CAD: Rachel Sparks
13
Conference Participation 2012
VLPR: Sahir AliVLPR: Rob Toth (left)
Sahir Ali (right)
VLPR: Sahir Ali, Rob Toth, Anant Madabhushi, Jun Xu (alum) with Dr. Xu’s graduate students (standing)
14
CCIPD Workshop 2012
Dr Madabhushi attended and presented at the Radio-omics Workshop organized by Dr. Bob Gillies at the Moffit Cancer Center in Tampa, FL. Also attendance were folks from the Cancer Imaging Program at NCI (Drs Larry Clarke and Nordstrom) and members of the Quantitative Imaging Network (QIN).
15
CCIPD Workshop 2012
The HIMA (Histopathology Image Analysis) workshop – 4th year running of HIMA at MICCAI 2012
16
CCIPD Workshop 2012
The prostate imaging challenge workshop- first prostate segmentation challenge at MICCAI attended by 13 participating teams.
17
Summary of Accomplishments 2012 Lab Members: 20
Faculty: 3 Research Associates: 3 Graduate Students: 8 Undergraduate Students: 7
Theses (3): 2 PhD + 1 MS Books: 1 Journal Papers: 19 Peer-Reviewed Conference Papers: 19 Peer reviewed Abstracts: 7
Issued Patents: 3Grants: 4Ongoing Projects: 31
18
Peer Reviewed Publications for 2012
0
2
4
6
8
10
12
14
16
18
20
Theses Journal Papers Conference Papers Abstracts
Summary
19
Peer Reviewed PublicationsJournal Papers
Shridar, A, Doyle, S, Madabhushi, A, “Content-Based Image Retrieval of Digitized Histopathology in Boosted Spectrally Embedded Spaces”, IEEE Transactions on Information Technology in Biomedicine, Minor Changes.
Toth, R, Gentile, J, Sperling, D, Madabhushi, A, “Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models with Multiple Coupled Levelsets”, Computer Vision and Image Understanding, Minor changes.
Janowczyk, A, Chandran, S, Madabhushi, A, “Quantifying local heterogeneity via morphologic scale: Distinguishing tumoral regions from stromal regions”, Journal of Pathology Informatics, Accepted.
Tiwari, P, Kurhanewicz, J, Madabhushi, A, “Multi-Kernel Graph Embedding for Detection, Gleason Grading of Prostate Cancer via MRI/MRS”, Medical Image Analysis, Accepted.
Doyle, S, Tomaszewski, J, Feldman, M, Shih, N, Madabhushi, A, “Cascaded Multi-Class Pairwise Approach to Automated Classification of Normal, Cancerous, and Confounder Classes of Prostate Tissue”, BMC Bioinformatics, 2012 Oct 30;13(1):282. [Epub ahead of print] PMID: 23110677.
Agner, S, Xu, J, Madabhushi, A, “Spectral Embedding based Active Contour (SEAC) for Lesion Segmentation on Breast Dynamic Contrast Enhanced Magnetic Resonance Imaging”, Medical Physics, Accepted.
Gurcan, M, Madabhushi, A, Medical Imaging 2013: Digital Pathology (Proceedings Volume), Proceedings of SPIE Volume: 8676, ISBN: 9780819494504, 2013.
Books
20
Peer Reviewed PublicationsJournal Papers (Contd.)
Monaco, J, Madabhushi, A, “Class-Specific Weighting for Markov Random Field Estimation: Application to Medical Image Segmentation”, Medical Image Analysis, [Epub ahead of print](PMID: 22986078).
Ali, S, Madabhushi, A, “An Integrated Region, Boundary, Shape based Active Contour for multiple object overlap resolution in histological imagery”, IEEE Transactions on Medical Imaging, vol. 31[7], pp. 1448-60, 2012 (PMID: 22498689).
Toth, R, Madabhushi, A, “Multi-Feature Landmark-Free Active Appearance Models: Application to Prostate MRI Segmentation”, IEEE Transactions on Medical Imaging, vol. 31[8], pp. 1638-50, 2012, (PMID: 22665505).
Viswanath, S, Madabhushi, A, “Consensus Embedding: Theory, Algorithms and Application to Segmentation and Classification of Biomedical Data”, BMC Bioinformatics, 13(1): 26, 2012 (PMID: 22316103) (Highly accessed).
Hipp, J, Monaco, J, Kunju, P Cheng, P, Yagi, Y, Rodriguez-Canales, J, Emmert-Buck, M, Hewitt, S, Feldman, M, Tomaszewski, J, Shih, N, Toner, M, Tompkins, R, Flotte, T, Lucas, D, Gilbertson, Kunju, LP, J, Balis, U, Madabhushi, A, “Integration of architectural and cytologic driven image algorithms for prostate adenocarcinoma identification”, Analytical Cellular Pathology, (PMID: 22425661).
Chowdhury, N, Toth, R, Chappelow, J, Kim, S, Motwani, S, Punekar, S, Lin, H, Both, S, Vapiwala, N, Hahn, S, Madabhushi, A, “Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning”, Medical Physics, vol. 39(4), pp. 2214-28, 2012 (PMID: 22482643) (Editors Pick).
21
Peer Reviewed PublicationsJournal Papers (Contd.) Viswanath, S, Bloch, B, Chappelow, J, Toth, R, Rofsky, N, Genega, E, Lenkinski, R, Madabhushi, A,
“Central Gland and Peripheral Zone Prostate Tumors have Significantly Different Quantitative Imaging Signatures on 3 Tesla Endorectal, In Vivo T2-Weighted Magnetic Resonance Imagery”, Journal of Magnetic Resonance Imaging, 2012 [Epub ahead of print] (PMID: 22337003).
Ghaznavi, D, Evans, A, Madabhushi, A, Feldman, M, “Digital Imaging in Pathology: Whole-Slide Imaging and Beyond”, Annual Review of Pathology: Mechanisms of Disease, vol. 19[3], pp. 331-359, 2012 (PMID: 23157334).
Ali, S, Madabhushi, A, "GPU Implementation of an Integrated Shape Based Active Contour: Application to Digital Pathology", Journal of Pathology Informatics, 2:13, 2012, (PMID: 22811957).
Basavanhally, A, Ganesan, S, Shih, N, Feldman, M, Tomaszewski, J, Madabhushi, A, “Multi-Field-of-View Strategy for Image-Based Outcome Prediction of ER+ Breast Cancer Histopathology Using Spatio-Architectural and Vascular Features”, Journal of Pathology Informatics, 2:1, 2012, (PMID: 22665505).
Bulman, J, Toth, R, Patel, AD, Bloch, BN, McMahon, CJ, Ngo, L, Madabhushi, A, Rofsky, N, Automated Computer-Derived Prostate Volumes from MRI Data: Comparison to Radiologist-Derived MRI Volumes and Pathology Specimen Volumes, Radiology, vol. 262[1], pp. 144-151, 2012 (PMID: 22190657).
Doyle, S, Tomaszewski, J, Feldman, M, Madabhushi, A, A Boosted Bayesian Multi-Resolution Classifier for Prostate Cancer Detection from Digitized Needle Biopsies, IEEE Transactions on Biomedical Engineering, vol. 59(5), pp. 1205-18, 2012 (PMID: 20570758).
Janowczyk, A, Chandran, S, Singh, R, Sasaroli, D, Coukos, G, Feldman, M, Madabhushi, A, “High-Throughput Biomarker Segmentation on Ovarian Cancer Tissue Microarrays via Hierarchical Normalized Cuts”, IEEE Trans on Biomedical Engineering, vol. 59(5), pp. 1240-1252, 2012 (PMID: 22180503).
22
Peer Reviewed PublicationsPeer-reviewed Conference Papers
Janowczyk, A, Chandran, A, Madabhushi, A, “Quantifying local heterogeneity via morphologic scale: Distinguishing tumor from stroma”, Workshop on Histopathologic Image Analysis, In Conjunction with Medical Image Computing and Computer Assisted Interventions (MICCAI), (http://www2.warwick.ac.uk/fac/sci/dcs/events/hima2012/hima2012_programdraft.pdf), 2012.
Toth, R, Madabhushi, A, “Deformable Landmark-Free Active Appearance Models: Application to Segmentation of Multi-institutional Prostate MRI Data”, (http://promise12.grand-challenge.org/Results/Overview), MICCAI Grand Challenge: Prostate MR Image Segmentation (PROMISE) 2012.
Cruz Roa, A, Galero, J, Osorio, FA, Madabhushi, A, Romero, E, “A Visual Latent Semantic Approach for Automatic Analysis and Interpretation of Anaplastic Medulloblastoma Virtual Slides”, In Proc of Medical Image Computing and Computer Assisted Interventions (MICCAI), vol. 1, pp. 157-164, 2012.
Monaco, J, Madabhushi, A, “Image Segmentation with Implicit Color Standardization Using Spatially Constrained Expectation Maximization: Detection of Nuclei”, In Proc of Medical Image Computing and Computer Assisted Interventions (MICCAI), vol. 1, pp. 365-372, 2012.
Monaco, J, Raess, P, Chawla, R, Bagg, A, Weiss, M, Choi, J, Madabhushi, A, “Image Segmentation with Implicit Color Standardization Using Cascaded EM: Detection of Myelodysplastic Syndromes”, IEEE International Symposium on Biomedical Imaging, pp. 740-743, 2012.
Rusu, M, Bloch BN, Jaffe C, Rofsky N, Genega E, Lenkinski R, Madabhushi A, “Statistical 3D Prostate Imaging Atlas Construction via Anatomically Constrained Registration”, SPIE Medical Imaging, 2013.
Rusu M, Wang H, Golden T, Gow A, Madabhushi A, “Multi-Scale, Multi-Modal Fusion of Histological and MRI Lung Volumes for Characterization of Airways”, SPIE Medical Imaging, 2013.
23
Peer Reviewed PublicationsPeer-reviewed Conference Papers (Contd.)
Wan T, Bloch BN, Madabhushi A, “A Novel Point-based Nonrigid Image Registration Scheme Based on Learning Optimal Landmark Configurations”, SPIE Medical Imaging, 2013.
Tiwari, P, Danish, S, Wong, S, Madabhushi A, “Quantitative Evaluation of Multi-parametric MR Imaging Marker Changes Post-laser Interstitial Ablation Therapy (LITT) for Epilepsy”, SPIE Medical Imaging, 2013.
Singanamalli, A, Sparks, R, Rusu, M, Shih, N, Ziober, A, Tomaszewski, JE, Rosen, M, Feldman, M, Madabhushi, A “Correlating in vivo Imaging and ex vivo Vascular Markers to Identify Aggressive Prostate Cancer: Preliminary Results”, SPIE Medical Imaging, 2013.
Prabu SB, Toth R, Madabhushi A, “A Statistical Deformation Model (SDM) based Regularizer for Non-rigid Image Registration: Application to registration of multimodal prostate MRI and histology”, SPIE Medical Imaging, 2013.
Sparks R, Feleppa E, Barratt D, Bloch BN, Madabhushi A, “Fully Automated Prostate MRI and Transrectal Ultrasound(TRUS) Fusion via a Probabilistic Registration Metric”, SPIE Medical Imaging, 2013.
Ginsburg SB, Bloch BN, Rofsky NM, Genega E, Lenkinski RN, Madabhushi A, “Iterative Multiple Reference Tissue Method for Estimating Pharmacokinetic Parameters on Prostate DCE MRI”, SPIE Medical Imaging, 2013.
Ali S, Veltri R, Epstein J, Christudass C, Madabhushi A, “Cell Cluster Graph for Prediction of Biochemical Recurrence in Prostate Cancer Patients from Tissue Microarrays”, SPIE Medical Imaging, 2013.
Wang H, Rusu M, Golden T, Gow A, Madabhushi A, “Mouse Lung Volume Reconstruction from Efcient Groupwise Registration of Individual Histological Slices with Natural Gradient”, SPIE Medical Imaging, 2013.
Basavanhally A, Madabhushi A, “EM-based Segmentation-Driven Color Standardization of Digitized Histopathology”, SPIE Medical Imaging, 2013.
24
Peer Reviewed Publications
2/11/2015 25
Peer-reviewed Conference Papers (Contd.)
Viswanath S, Sperling D, Lepor H, Futterer J, Madabhushi A, “Quantitative evaluation of treatment related changes on multi-parametric MRI after laser interstitial thermal therapy of prostate cancer, SPIE Medical Imaging, 2013.
Incorporating the whole-mount prostate histology reconstruction program Histostitcher© into the extensible imaging platform (XIP) framework, Toth, R, Chappelow, J, Kutter, O, Vetter, C, Russ, C, Feldman, M, Tomaszewski, J, Shih, N, Madabhushi, A, SPIE Medical Imaging, 2012, Accepted.
Gleason grading of prostate histology utilizing statistical shape model of manifolds (SSMM), Sparks, R, Madabhushi, A, SPIE Medical Imaging, 2012, Accepted (Cum Laude, Best Poster in CAD Conference at SPIE Medical Imaging 2012).
Peer Reviewed Abstracts
2/11/2015 26
Lewis, J, Ali, S, Thorstad, W, Madabhushi, A, “A Quantitative Histomorphometric Classifier Identifies Aggressive Versus Indolent p16 Positive Oropharyngeal Squamous Cell Carcinoma”, United States and Canadian Academy of Pathology's 102nd Annual Meeting, 2013, Accepted.
Viswanath, S, Madabhushi, A, “Evaluating the need for intensity artifact correction in multi-parametric MRI for computerized detection of prostate cancer in vivo”, Society for Imaging Informatics in Medicine, 2013.
Viswanath, S, Bloch, N, Lenkinski, R, Rofsky, N, Madabhushi, A, “Computer-aided Detection of Peripheral Zone and Central Gland Prostate Tumors on T2-weighted MRI”, Proceedings of the Radiologic Society of North America 2012, Accepted.
Ali, S, Lewis, J, Madabhushi, A, “Use of quantitative histomorphometrics to classify disease progression in HPV-positive squamous cell carcinoma “, J Clin Oncol 30: 2012 (suppl 30; abstr 73).
Veltri, R, Christudass, C, Epstein, J, Ali, S, Yoon, H-J, Li, C-C, Madabhushi, A, Computer-assisted Gleason grading of Prostate Cancer: Two novel approaches using nuclear shape and texture feature to classify pathologic Gleason grade patterns 3 and 4, American Association for Cancer Research, 2012.
Reiss, P, Monaco, J, Bagg, A, Weiss, M, Madabhushi, A, Choi, J, “Alpha-Hemoglobin Stabilizing Protein Specifically Identifies Nucleated Erythroid Precursors and Enables Identification of Architectural Distortion in Myelodysplastic Syndromes by Computerized Image Analysis”, United States and Canadian Academy of Pathology's 101st Annual Meeting, March 17-23, 2012, Vancouver, BC, Canada.
Hipp, J, Monaco, J, Kunju, P Cheng, P, Yagi, Y, Rodriguez-Canales, J, Emmert-Buck, M, Hewitt, S, Feldman, M, Tomaszewski, J, Shih, N, Toner, M, Tompkins, R, Flotte, T, Lucas, D, Gilbertson, Kunju, LP, J, Balis, U, Madabhushi, A, “Integration of architectural and cytologic driven image algorithms for prostate adenocarcinoma identification”, Modern Pathology, vol. 25[2], pp. 213A-214A, 2012.
PatentsIssued Patents
“Systems and Methods for Classification of Biological Datasets", Anant Madabhushi, Michael D. Feldman, Jianbo Shi, Mark Rosen, John Tomaszewski, United States Serial Number (USSN): 8,204,315.
“Malignancy Diagnosis Using Content-Based Image Retrieval of Tissue Histopathology”, Anant Madabhushi, Michael D. Feldman, John Tomaszewski, Scott Doyle, United States Serial Number (USSN): 8,280,132.
“Computer Assisted Diagnosis (CAD) of cancer using Multi-Functional Multi-Modal in vivo Magnetic Resonance Spectroscopy (MRS) and Imaging (MRI)", Anant Madabhushi, Satish Viswanath, Pallavi Tiwari, Robert Toth, Mark Rosen, John Tomaszewski, Michael D. Feldman, United States Serial Number (USSN): 8,295,575.
Patents Pending
“Method and Apparatus for Shape based deformable segmentation of multiple overlapping objects”, Anant Madabhushi, Sahirzeeshan Ali, PCT/US12/20816, Jan. 2012.
“Local Morphologic Scale with applications to Multi-protocol Registration and Tissue classification”, Anant Madabhushi, Andrew Janowczyk, Sharat Chandran, PCT/US12/21133, Jan. 2012.
“Enhanced Multi-Protocol Analysis via Intelligent Supervised Embedding (EMPrAvISE) for Multimodal Data Fusion”, Anant Madabhushi, Satish Viswanath, PCT/US12/21373.
27
PatentsProvisional Patents Applications
Method and Apparatus for an Integrated, Multivariate Histologic Image-based risk predictor for outcome of ER+ breast cancer”, Anant Madabhushi, Ajay Basavanhally, RU 2011-160.
“Method and Apparatus for Registering Image Data Between Different Types of Image Data”, Anant Madabhushi, Rachel Sparks, P05561US0.
“Color Standardization of Digital Histological Images”, Anant Madabhushi, Ajay Basavanhally, US Provisional Application No: 61/715,645.
Invention Disclosures
“A Texture Based Finite Element Model Registration Scheme For Registering Pre-Treatment Intensity Modulated Radiation Therapy MR Imagery To Post-Treatment MR Imagery”, Anant Madabhushi, Robert Toth, Case 2013-2375.
“Discriminatively weighted multi-scale local binary patterns for object detection”, Anant Madabhushi, Haibo Wang, Case 2013-2391.
“Co-occurring Gland Tensors in Localized Cluster Graphs for Quantitative Histomorphometry”, Anant Madabhushi, George Lee, Sahir Ali, Rachel Sparks, Case 2013-2369.
28
Awards and Accomplishments in 2012Professional, Editorial, Activities, Institutional Service – Anant Madabhushi
Chair, Poster Session Analysis of Microscopic and Optical Images II, MICCAI 2012, October 4th, 2012, Nice, France Member of the MICCAI 2012 Young Scientist Award Committee. Area Chair, Eight Indian Conference on Vision, Graphics, and Image Processing (ICVGIP) 2012. Chair, Prostate Segmentation Challenge, MICCAI 2012. Chair, Workshop on Histopathology Image Analysis, MICCAI 2012. Advisory Committee, Workshop: Bio-computing, Genomics and Epigenomics, DIMAC, Rutgers University,
September 2012. Panelist and Invited Speaker, “Careers in Biomedical Engineering”, Engineering Governing Council, Rutgers
University, March, 2012. Program Committee Member, Imaging Track of the 2nd annual IEEE International Conference on Healthcare
Informatics, Imaging and Systems Biology(HISB), 2012. Associate Editor, IEEE Transactions in Biomedical Engineering 2009-present. Associate Editor, IEEE Transactions in Biomedical Engineering (Letters) 2008-present. Program Committee Member, Asian Conference on Computer Vision (ACCV 2012), 2012. Program Committee Member, ASE/IEEE International Conference on BioMedical Computing, 2012. Program Committee Member, MICCAI 2012. Chair, Conference 8315: Computer Aided Diagnosis, Session on Abdomen Imaging, SPIE Medical Imaging, Feb 2012. Chair, Conference 8315: Computer Aided Diagnosis, Session on Digital Pathology I, SPIE Medical Imaging, Feb 2012. Chair, Conference 8315: Computer Aided Diagnosis, Session on Digital Pathology II, SPIE Medical Imaging, Feb
2012.
29
Awards and Accomplishments
Awards RSNA Abstract “Computer-aided Detection of Peripheral Zone and Central Gland Prostate Tumors on T2-
weighted MRI”, Featured on AuntMinnie.com in the Advanced Visualization preview, 2012. Runner Up for Investors Choice Award, New Jersey Entrepreneurial Network (NJEN), 2012.
Media Recognition “ECE Student awarded travel grant to attend VLPR 2012”, Featured on front page of Rutgers Department of
Electrical Engineering Homepage, July 23, 2012, http://www.ece.rutgers.edu/node/947 “Translational Research: Great Promise and Major Challenges”, LifeSci Trends, March 2012, vol. 11[1], pp.
17. “Building a better predictor”, Page 6, CINJ Oncolyte, Winter 2012 Issue, February 2012. “Startups Present Posters at Packed NJEN Event”, New Jersey Tech Weekly, February 7th, 2012.
Professional, Editorial, Activities, Institutional Service – Anant Madabhushi (Contd.) Program Committee Member, Workshop on Machine Learning in Medical Imaging, MLMI'12. Program Committee Member, International Conference on Image and Signal Processing, ICISP'12. Co-Chair, Workshop on Non-invasive imaging/imaging phenome, American Society for Investigative
Pathology, San Diego, 2012.
30
New Grants-2012
Madabhushi, Anant (PI) Date: 07/01/12-06/31/13Proof of Concept Award, RutgersComputerized Decision Support for Prostate Cancer Detection and Treatment via Multi-parametric MRIRole: PI
Madabhushi, Anant (PI) Date: 9/12/12-8/31/14NIH R21CA167811-01Decision support with MRI for targeting, evaluating laser ablation for prostate cancersRole: PI
Buckler, Andrew (PI)Date: 01/01/13 - 06/01/13NSF SBIR Phase 1Computer assisted prognosis of debilitating diseaseRole: Co-PI (Madabhushi)
Madabhushi, Anant (PI) Date: 01/01/13-12/31/13QED Grant, University City Science CenterProstaCAD™: Computer based detection of Prostate Cancer from MRIRole: PI
31
Student, Post-doctoral Awards and Fellowships Andrew Janowcyz, Travel award ($500) to attend HIMA Workshop in conjunction with MICCAI
2012. Sahirzeeshan Ali, Travel award ($2000) to attend USA-Sino Summer School in Vision,
Learning, Pattern Recognition: VLPR 2012 (Theme: Computer Vision in Biomedical Image Applications: From Micro to Macro), 2012
Robert Toth, Travel award ($2000) to attend USA-Sino Summer School in Vision,Learning, Pattern Recognition: VLPR 2012 (Theme: Computer Vision in Biomedical Image Applications: From Micro to Macro), 2012
Angel Alfonso Cruz Roa, MICCAI Travel Award ($600), 2012. Srivatsan Babu, Aresty 2012-2013 RA Award, “Characterizing Elastic Properties of the Prostate”,
May 2012. Eileen Hwuang, First Place (Overall) for Best Student Research Presentation ($250), SOE Research
Symposium, Rutgers University, 2012 Joseph Galero, Fulbright Fellowship, 2012 Najeeb Chowdhury, “Concurrent segmentation of the prostate on MRI and CT via linked statistical
shape models for radiotherapy planning”, Highlighted in Medical Physics Editors Pick Column. Satish Viswanath, “Consensus Embedding: Theory, Algorithms and Applications to Biomedical
Segmentation and Classification”, BMC Bioinformatics Highly accessed paper. Elaine Yu, NSF Graduate Research Fellowship, 2012 Joseph Galero, Honorable Mention, NSF Graduate Research Fellowship, 2012 Rachel Sparks, Cum laude for Best Poster Presentation at the Computer Aided Diagnosis (CAD)
Conference, SPIE Medical Imaging, 2012
32
Active Research (32 projects)
Methods
Multimodal Data Integration and
Evaluating Therapy
Computer Aided Diagnosis and Prognosis
Image Segmentation
Machine Learning
Image Registration
Radiology
Histopathology
Bioinformatics
Prostate Cancer
Breast Cancer
Brain Glioma
Image Reconstruction
Epilepsy
Medulloblastoma
Oropharyangeal
Carotid Plaque Myelodysplasia
33
IMAGE SEGMENTATION
34
Spectral Embedding based Active Contour (SEAC) for Lesion Segmentation on Breast MRI
(a) Original grayscale post-contrastimage and image representationsderived from (b) FCM and (c) SE.Note that the colormaps displayedfor both methods only reflect thevoxel similarities and determinedby the 2 schemes, voxels withsimilar time-intensity curves beingassigned similar colors. The secondrow of images shows the groundtruth segmentation (e) in red and thehybrid AC segmentation driven by(f) the FCM+AC segmentationoverlaid (yellow line) on groundtruth, (g) PCA+AC segmentation,and (h) SEAC segmentationoverlaid on ground truth.
Quantitative results obtainedfrom the SEAC segmetnationcompared to the FCM+AC, andPCA+AC methods.
Agner S., Madabhushi, A., Xu J., “Spectral Embedding based Active Contour (SEAC) for Lesion Segmentation on Breast Dynamic Contrast Enhanced Magnetic Resonance Imaging,” Proc. SPIE 7963, Medical Imaging 2011: Computer Aided Diagnosis, 796305.
35
Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models with Multiple Coupled Levelsets
• Use of Active Appearance Models (AAM’s) to couple multiple levelsets using PCA
• Simultaneous segmentation of prostate, central gland (CG), peripheral zone (PZ).
Toth, R., Ribault, J., Gentile, J., Sperling, D., Madabhushi, A., “Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models with Multiple Coupled Levelsets,” CVIU, 2013. Pending Minor Revisions.
Figure 1. AAM coupling multiple shapes
Figure 2. Segmentation result for Study #1.
Figure 3. Segmentation result for Study #2.
36
J Monaco, J Hipp, David Lucas, U Balis, S Smith, A Madabhushi, “Image Segmentation with Implicit Color Standardization Using Spatially Constrained Expectation Maximization: Detection of Nuclei,” MICCAI 2012.
Most EM-based algorithms ignore spatial constraints. Thus, we presented spatially-constrained EM (SCEM), a novel approach for incorporating Markov priors into the EM framework. We validated SCEM by integrating it into our computerized system to segment nuclei in H&E stained histopathology.
Image Segmentation with Implicit Color Standardization Using Spatially Constrained
37
J Monaco, P Raess, R Chawla, A Bagg, M Weiss, J Choi, A Madabhushi, “Image Segmentation with Implicit Color Standardization Using Cascaded EM: Detection of Myelodysplastic Syndromes,” ISBI 2012.
Color nonstandardness − the propensity for similar objects to exhibit different color properties across images − poses a significant problem in digital histopathology. We developed a unique instantiation of the expectation maximization (called cascaded EM) to help create a novel color segmentation algorithm which is robust to nonstandardness. We validated our algorithm by detecting myelodysplasticsyndrome on bone marrow specimens.
Image Segmentation with Implicit Color Standardization Using Cascaded EM Detection of Myelodysplastic
Syndromes
38
A Region-boundary and Shape based Active Contour
Ali, Sahirzeeshan and Madabhushi, Anant “An Integrated Region, Boundary, Shape based Active Contour for multiple object overlap resolution in histological imagery”, IEEE Trans on Medical Imaging, 2012.
Hybrid Active Contour scheme that can simultaneously segment overlapping and non-overlapping objects.
39
EM-Based Segmentation-Driven Color Standardization of Digitized Histopathology
0 50 100 150 200 250
0 50 100 150 200 250
Goal: Improve color constancy across histology images by realigning color distributions to match a pre-defined template.
(a) A new histopathology image isstandardized to (b) a template imageusing the (c) Expectation Maximizationalgorithm to decompose the image intotissue classes. (d) Color histograms arealigned separately for each class andsubsequently recombined to form astandardized image. Green outlinesillustrate how standardization yieldsmore consistent segmentation of nuclei.In addition, histograms demonstratingalignment of multiple images (a) beforeand (d) after standardization.
(a)
(b)
(c) (d)
40
Multi-Feature, Landmark-Free Active Appearance Models (MFLAAM)
• Levelset function used to create statistical shape model in an AAM framework.
• Generalized AAM’s to incorporate image derived attributes such as gradient or texture information – only considered intensities previously
• “Registration”-like template matching scheme to locate prostate
Error
Toth, R., Madabhushi, A., “Multi-Feature Landmark-Free Active Appearance Models: Application to Prostate MRI Segmentation,” IEEE Transactions on Medical Imaging 31(8), pp. 1638-1650. June 2012.
41
IMAGE REGISTRATION
42
Prostatome™: Prostate Imaging Atlas via Anatomic Constrained Registration
Statistical Models for the Anatomic Structures:
- Prostate capsule- Central Gland- Peripheral Zone
Distribution of cancer:- High frequency- Medium- Low
M. Rusu, B. N. Bloch, C. C. Jaffe, N. M. Rofsky, E. M. Genega, R. E. Lenkinski, A. Madabhushi , Statistical 3D prostate imaging atlas construction via anatomically constrained registration, Accepted SPIE 2013
43
A Statistical Deformation Model (SDM) based Regularizer for Non-rigid Image Registration: Application to registration of multimodal prostate MRI and histology
Moving ImageTemplate Image Moved Image (FFD) Moved Image (FFD+SDM)
• Regularizer needed in registration to allow for a physically meaning transformation.
• Here, we leverage knowledge of known, valid deformations to train a statistical deformation model (SDM)
• Harness this knowledge alongside FFD to provide an accurate overlay of histology on MRI. M
ean
Def
orm
atio
n Fi
eld
from
Tra
inin
g Se
tS. Babu Prabu,, R. Toth, A. Madabhushi, “A Statistical Deformation Model (SDM) based Regularizer for Non-rigid Image Registration: Application to registration of multimodal prostate MRI and histology,” Proc. SPIE, Medical Imaging: Digital Pathology, 2013.
44
Incorporating the Whole-Mount Prostate Histology Reconstruction Program Histostitcher© into the Extensible
Imaging Platform (XIP) Framework• Histostitcher algorithm incorporated into
professional XIP software framework.• GPU rendering, “Google Maps” – like
zooming, scrolling
Previous version of Histostitcher© graphical user interface usable prototype developed using Matlab.
New version of Histostitcher© graphical user interface developed using XIP.
Toth, R., Chappelow, J., Kutter, O., Vetter, C., Russ, C., Feldman, M., Tomaszewski, J., Shih, N., Madabhushi, A., “Incorporating the Whole-Mount Prostate Histology Reconstruction Program Histostitcher© into the Extensible Imaging Platform (XIP) Framework,” SPIE Medical Imaging 8315, 2012.
45
Fully-Automated T2 W MRI-TRUS FusionObjective: Registration of MRI-TRUS with no manual intervention
Module 1. MRI Prostate
Segmentation (a) Spatial Prior
Module 2. TRUS Probabilistic Model of Prostate Location
(b) Estimation of texture-base pixel-wise probability
Module 3. Register Model to Segmentation
(a) Affine Registration
(b) Elastic Registration
R. Sparks, E. Feleppa, N. Bloch, D. Barratt and A. Madabhushi. Fully Automated Prostate Magnetic Resonance Imaging and Transrectal Ultrasound Fusion via a Probabilistic Registration Metric. In Proc. SPIE 2012, in press.
46
Learning-based Landmark Driven Image Registration
Tao Wan, B.Nicolas Bloch, and Anant Madabhushi, A Novel Point-based Nonrigid Image Registration Scheme Based on Learning Optimal Landmark Configurations, to appear in Proc. SPIE 2013.
The objective of this work is to develop an effective approach to estimate an optimal landmark configuration in order to driving point-based non-rigid image registration schemes.
(a) (b) (c)
The difference map between: (a) the original and deformed images, and (b), (c) the original and registered images using ICP-based, and FFD methods, respectively.
47
Co-registration of MRI via a Learning Based Fiducial-driven registration (LeFiR) Scheme
A B C D E F
G H I J K L
(A)(B), (G)(H) pre- and post-treatment brain images, (C)(I) identified landmarks, (D)(J) uniformly spaced landmarks, and difference images between pre-and registered images using (E)(K) identified landmarks, (F)(L) uniformly spaced landmarks.
T.Wan, B.N.Bloch, A.Madabhushi, Learning based fiducial driven registration (LeFiR): Evaluating laser ablation changes for neurological applications, submitted to ISBI 2013.
48
Mouse Lung Reconstruction from Groupwise Registration of Individual Histological Slices with Natural Gradient
Haibo Wang, etc., Mouse Lung Volume Reconstruction from Efficient Groupwise Registration of Individual Histological Slices with Natural Gradient, SPIE 2013.
Perform groupwise registration of individual histological slices.
Present a fast incremental Lucas-Kanade computation framework.
Integrate natural gradient for faster and more reliable convergence.
Fig. 1 Reconstructed volumes
Fig. 2 Convergence curves of registration approaches
49
Multiscale, multimodal fusion of histological and MRI lung volumes for characterization of airways, M. Rusu, H. Wang, T. Golden, A. Gow, A. Madabhushi, Accepted SPIE 2013
Fusion of histological and MRI lung volumes
50
MACHINE LEARNING
51
Class-specific weighting for Markov random field estimation: Application to medical image segmentation, Medical Image Analysis. 2012 Dec;16(8):1477-89.
Class-Specific Weighting for Markov Random Field Estimation
Methods for varying the performance of MRFs is conspicuously absent from the literature. Thus, we introduced multiplicative weighted MAP estimation for MRFs.
52
“Computer-aided Detection of Peripheral Zone and Central Gland Prostate Tumors on T2-weighted MRI”, RSNA, 2012
Comparing Classifier Schemes for CaP Detection from T2w MRI
Empirically compared 12 different classifier schemes for detecting prostate cancer on a per-voxel basis using textural representations of T2w MRI. Simple QDA classifier performed comparably to popular complex SVM classifier.
53
Variable Ranking for PCA
• Quantify the contributions of individual, high dimensional features to a PCA embedding
• Multi-parametric MR imaging markers for prostate cancer:– Importance of ADC intensity, in contrast to T2w
intensity– Importance of Gabor texture features extracted from
ADC maps and T2w MRI– Importance of choline, polyamine, and citrate
metabolites measured on magnetic resonance spectroscopy
• Facilitates the use and interpretation of high dimensional features while avoiding the curse of dimensionality
Perform PCA
Compute PCA-VIP
Ginsburg, S, Tiwari, P, Kurhanewicz, J, Madabhushi, A. 2011. Variable ranking with PCA: Finding multiparametric MR imaging markers for prostate cancer diagnosis and grading. Workshop on Prostate Cancer Imaging: Computer-Aided Diagnosis, Prognosis, and Intervention (in conjunction with MICCAI). 6963:146-157.
54
Statistical Shape Model of Manifolds
Objective: Accurately model manifold structure
b. Generate manifold for each fold c. Learn Modela. Divide dataset
into K folds
R. Sparks and A. Madabhushi. Gleason grading of prostate histology utilizing statistical shape model of manifolds (SSMM.) In Proc. SPIE 2012, 8315: 83151J-83151J13.
55
MULTIMODAL DATA INTEGRATION AND TREATMENT EVALUATION
56
Radiohistomorphometry™: Correlating DCE-MRI and Microvascular Parameters to Identify in vivo Markers for
Prostate Cancer Aggressiveness
CD31 stained histology quadrants
Stitched section with CaP annotations
DCE MRI
Vascular Feature Extraction
Correlation
Histo-MR registration DCE-MRI Kinetic Feature Extraction
Radio-histomorphometricAnalysis to screen forcandidate Imaging Markers
Singanamalli et al. To appear in SPIE Medial Imaging 2013
57
Quantitative Evaluation of Treatment Related Changes on Multi-Parametric MRI after Laser Interstitial
Thermal Therapy of Prostate CancerPreliminary results of developing a quantitative framework to evaluate treatment-related changes post-LITT on a per-voxel basis (high resolution), via construction of an integrated MP-MRI signature
Above, checkerboard registration results showing alignment of multi-protocol MRI, pre-/post-LITT MRIRight, difference maps showing significant changes in MR parameters within LITT ablation zone
T2/DCE T2/DWI Pre/PostAblation zone T2 difference map
ADC difference map MP-MRI difference
“Quantitative Evaluation of Treatment Related Changes on Multi-Parametric MRI after Laser Interstitial Thermal Therapy of Prostate Cancer”, SPIE, 2013
58
Objective: To quantitatively evaluate changes in MP-MRI imaging markers (T1-w, T2-w, T2-GRE, T2-FLAIR, and ADC) over the epileptogenic foci, pre- and post- laser interstitial thermal therapy (LITT).
Tiwari, P, et al. . Quantitative evaluation of multi-parametric MRI marker changes post laset-interstitial ablation therapy (LITT) for epilepsy, SPIE 2013.
MP-MRI for Evaluating Treatment Related Changes Post-LITT in Epilepsy
59
COMPUTER AIDED DIAGNOSIS AND PROGNOSIS
60
Pharmacokinetic Modeling for Prostate Cancer Localization• Iterative multiple reference
tissue method (IMRTM) for pharmacokinetic (PK) feature extraction from DCE MRI – Patient-specific values
for Ktrans (volume transfer constant) and ve(extravascular-extracellular volume fraction) are iteratively estimated for voxels in tissues A and B.
– No need for arterial input function
– Does not rely on population-based PK parameters
• Preliminary results shown on the right for a CG tumor
KtransGround truth ve
61
Ground Truth – Study 1
Ground Truth – Study 2
Cancer classification – Study 1
Cancer classification – Study 2
Grade classification – Study 1
Grade classification – Study 2
P. Tiwari, A. Madabhushi et al. Medical Image Analysis (MeDiA) – In press.
Hierarchical Prostate Cancer Grade Classification
62
Quantifying Local Heterogeneity via Morphologic Scale (MS) Distinguishing Tumoral Regions from Stromal Regions
Algorithm Output
The MS signature overlaid on a tumor regions in an (a) ovarian,(b) prostate H, (c)breast HE, and (d) prostate HE image, to be compared with the benign signatures in((i)-(l)), respectively. We can see that in the presented non-tumor regions ((i)-(l))the MS signature has fewer and smaller objects to obstruct its path, and thus therays are less tortuous, unlike in the respective tumoral regions ((a)-(d)). This allowsa supervised classifier to be able to separate the two classes.
Results
AUC
Data Type Breast Prostate HE Prostate H Ovarian
AUC +/- Range .80 +/- .01 .88 +/- .01 .87 +/- .02 .88 +/- .01
Matlab/C++/CPU
0.0058 sec/sample
Andrew Janowczyk, Sharat Chandran, and Anant Madabhushi. Quantifying local heterogeneity via morphologic scale: Distinguishing tumor from stroma. HIMA Workshop MICCAI, 2012.
63
Evaluating the need for intensity artifact correction in MP-MRI for computerized detection of prostate cancer in vivo
Demonstrated that explicit correction of intensity inhomogeneity and drift in all 3 MP-MRI protocols (T2w, DCE, DWI) prior to combining them within a classification scheme will yield improved CaP detection accuracy in vivo.
“Evaluating the need for intensity artifact correction in MP-MRI for computerized detection of prostate cancer in vivo”, SIIM, 2013
64
A Visual Latent Semantic Approach for Automatic Analysis and Interpretation of Anaplastic Medulloblastoma Virtual Slices
Goal: Medulloblastoma Tumor Classification (Anaplastic vs Non-anaplastic) with good classification performance and visual interpretability.
c)
d)
a)
b)
e)
f)
(a) New histopathology images are represented as (b) a histogram of Bag of Features (BOF)according to (c) a dictionary of BOF learning using Haar-based descriptors of patches. (d) Aprobabilistic latent semantic analysis (pLSA) model is trained with image representation and theirclasses membership of training dataset in order to (e) predict the probability that a given imagebelongs to Anaplastic or Non-anaplastic type of Medulloblastoma tumor. Finally, (f) a visualprobabilistic map is provided according to regions in the image associated with each subtype.
Angel et al., “A Visual Latent Semantic Approach for Automatic Analysis and Interpretation of Anaplastic Medulloblastoma Virtual Slices”, MICCAI, 2012.
65
Co-occurring Gland Tensors (CGT) in Localized Cluster Graphs for CaP Histology
CGTs describe the ability for glands to orient themselves with respect to prostate stroma
CaP Recurrence
No Recurrence
Calculate Gland Direction Establish Locality CGT
Lee et al. ISBI 2013 Under Review
66
Cell Cluster Graph for Prediction of Biochemical Recurrence in Prostate Cancer Patients from Tissue Microarrays
Novel Cell Cluster graph (CCG) that can quantify tumor morphology
Extracted features from CCG can predict Biochemical recurrence in Prostate Cancer in 80 patients.
Ali, Sahirzeeshan, Veltri, Robert, Epstein, Jonathan, and Madabhushi, Anant “Cell Cluster Graph for Prediction of Biochemical Recurrence in Prostate Cancer Patients from Tissue Microarrays”, SPIE Medical Imaging, 2013.(In Press)
67
Ali, Sahirzeeshan, Lewis, James, Madabhushi, Anant, J Use of quantitative histomorphometrics to classify disease progression in HPV-positive squamous cell carcinoma.J. Clin Oncol 30: 2012 (suppl 30; abstr 73)
Using Cell Cluster graphs to differentiate Progressors vs Non-Progressors in p16+ Oropharyangeal tumors
Use of Quantitative Histomorphometry to Classify Disease Progression in HPV-positive Squamous Cell Carcinoma
68
INTERESTED IN JOINING CCIPD?
We are always looking for enthusiastic and motivated graduate, undergraduate students and research scientists.
If you think you would be a good fit for CCIPD, send over your complete CV and 3 representative publications to “anant.madabhushi” @ “case.edu”
Follow us on Twitter: @CCIPD_Case
69