Center for Computational Imaging and Personalized ......Prateek Prasanna, Runner Up, Young Scientist...

Center for Computational Imaging and

Personalized Diagnostics (CCIPD)

2014 Annual Report

Director: Anant Madabhushi, PhD

Professor,

Department of Biomedical Engineering

CCIPD Website: http://ccipd.case.edu

CCIPD in 2014

Faculty Offices, Room

523

Center Space, Room 525

Wickenden Building

Dept. of Biomedical Engineering

Case Western Reserve University

2071 Martin Luther King Drive

Cleveland, Ohio 44106-7207

Center Space, Room 517

Center Members

CCIPD Members

Research Faculty

Satish Viswanath

Pallavi Tiwari

Research Associates

Mirabela Rusu Mahdi Orooji

Haibo Wang Andrew Janowczyk

Asha Singanamalli George Lee

Jon Whitney Rakesh Shiradkar

Scientific Software Engineer

Ahmad Algohary

Yu Zhou

Administrative Staff

Ann Tillet

Francisco Aguila

Graduate Students

Shoshana Ginsburg

Sahir Ali

Prateek Prasanna

Gregory Penzias

Lin Li

Xiangxue Wang

Jacob Antunes

Undergraduate Students

Patrick Leo Ania Gawlik

Nikita Agrawal Jay Patel

Thomas Liao Eaton Guo

Ross O’Hagan

Visiting Scientists

Angel Cruz (Colombia) Jun Xu (China)

Tao Wan (China) Mehdi Alilou (Iran)

Center Director: Anant Madabhushi, PhD

Center Members

Center Director Research Faculty

Pallavi Tiwari,

PhD

Satish Viswanath,

PhD

Anant

Madabhushi,

PhD

Center MembersResearch Scientists

Mirabela Rusu,

PhD

Mahdi Orooji,

PhD

Haibo Wang,

PhD

Andrew

Janowczyk,

PhD

George Lee,

PhDAsha Singanamalli,

MS

Rakesh

Shrikadkar, PhD

Jon Whitney,

PhD

Center MembersGraduate Students

Shoshana Ginsburg,

MS

Sahir Ali, MS Prateek

Prasanna, MS

Greg Penzias,

BS

Jacob AntunesLin Li, BSXiangxue Wang,

BS

Administrative Staff

Ann Tillett, BS Francisco Aguila,

BS

Center Members

Scientific Software Programmers

Ahmad

Algohary, MS

Visiting Scientists

Tao Wang, PhD Jun Xu, PhD Mehdi Alilou, PhD

Yu Zhou, MS

Angel Cruz, MS

Center MembersUndergraduate Students

Ania GawlikPatrick Leo Jay Patel

Ross O’HaganEaton GuoNikita AgrawalThomas Liao

Recent Alumni

Ajay Basavanhally,

PhD, Diagnostic

Precision, Inc.

Rachel Sparks, PhD, Post Doc at

University College of London

Rob Toth, PhD, CEO,

Toth Technology

Andrew Janowczyk, PhD,

Research Associate, CCIPD

George Lee, PhD, Research

Associate, CCIPD

Eileen Hwang, Cum Laude Award in SPIE

Medical Imaging, 2014

Awards and Accomplishments

Prateek Prasanna, Runner Up, Young Scientist Award, MICCAI,

2014

Jacob Antunes, Reviewers

Choice Award, SPIE Medical

Imaging, 2014

Geert Litjens, 2nd place SPIE

Medical Imaging Student Paper

Award, 2014

Pallavi Tiwari, Cum Laude Award in SPIE

Medical Imaging, 2014

Conference Participation 2014

Angel Roa-Cruz: SIPIAM in Cartagen,

Colombia

Angel Roa-Cruz: SPIE in San Diego

Left to Right: Larry Clarke, Director of the NCI Cancer Imaging

Program, Navenka Dimitrova, Phillips Research, Dr. Madabhushi,

CCIPD, and Dr. Tiwari, CCIPD: Radiomics Meeting, Houston, TX

Conference Participation 2014

Pallavi Tiwari: SPIE in San Diego, CA

Mirabela Rusu: SPIE in San Diego, CAAnant Madabhushi: SPIE in San Diego, CA

Ibris, IncCCIPD Startup, showcased on Bioenterprise Wall

Summary of Accomplishments 2014

Center Members: 32Faculty: 3

Research Associates: 8

Graduate Students: 6

Undergraduate Students: 7

Theses (1): 1 PhD

Books: 1

Book Chapters: 2

Peer-Reviewed Journal Papers: 21

Peer-Reviewed Conference Papers: 15

Peer Reviewed Abstracts: 14

Awarded Grants: 6

Awarded Fellowships: 2

Ongoing Projects: 30

Issued Patents: 2

Provisional Patents: 1

Invention Disclosures: 8

Technologies Licensed: 6

Scientific Software Engineers: 2

Administrative Assistants: 2

Visiting Scientists: 4

Peer Reviewed Publications for 2014

Summary

0

4

8

12

16

20

24

Books Book Chapters Journal Papers Conference

Papers

Abstracts

Books


Journal Papers

Gurcan, M, Madabhushi, A, Medical Imaging 2014: Digital Pathology (Proceedings Volume),

Proceedings of SPIE Volume: 904108, ISBN: 9780819498342, doi:10.1117/12.2043683, 2014.

Veta, M, van Diest, PJ, Willems, SM, Wang, H, Madabhushi, A, Cruz-Roa, A, Gonzalez, F, Larsen, ABL,

Vestergaard, JS, Dahl, AB, Cireșan, DC, Schmidhuber, J, Giusti, A, Gambardella, LM, Tek, FB, Walter,

T, Wang, CW, Kondo, S, Matuszewski, BJ, Precioso, F, Snell, V, Kittler, J, de Campos, TE, Khan, AM,

Rajpoot, NM, Arkoumani, E, Lacle, MM, Viergever, MA, Pluim, JPW, “Assessment of algorithms for

mitosis detection in breast cancer histopathology images”, Medical Image Analysis, In Press.

Tiwari, P, Shabbar, D, Madabhushi, A, “Identifying MRI Markers Associated with Early Response

following Laser Ablation for Neurological Disorders: Preliminary Findings”, PLOS One, Accepted.

Ali, S, Veltri, R, Epstein, J, Christudas, C, Madabhushi, A, “Selective Invocation of Shape Priors for

Deformable Segmentation and Morphologic Classification of Prostate Cancer Tissue Microarrays”,

Computerized Medical Imaging and Graphics, Accepted

Tomaszewski, J, Hipp, J, Tangrea, M, Madabhushi, A, “Machine Vision and Machine Learning in

Digital Pathology. In: Linda M. McManus, Richard N. Mitchell, editors. Pathobiology of Human

Disease: A Dynamic Encyclopedia of Disease Mechanisms,” San Diego: Elsevier, pp. 3711-3722, 2014.

Veltri, RW, Zhu, G, Lee, G*, Ali, S*, Madabhushi, A, “Histomorphometry of Digital Pathology: Case

Study in Prostate Cancer”, Frontiers in Medical Imaging, 2014.

Book Chapters

Peer Reviewed Publications for 2014Journal Papers (Contd.)

Basanvally, A, Viswanath, S, Madabhushi, A, “Predicting Classifier Performance with Limited Training

Data: Applications to Computer-Aided Diagnosis in Breast and Prostate Cancer”, PLOS One,

Accepted.

Colen, R, Foster, I, Gatenby, R, Giger, M, Gillies, R, Gutman, D, Heller, M, Jain, R, Madabhushi, A,

Madhavan, S, Napel, S, Rao, A, Saltz, J, Tatum, J, Verhaak, R, Whitman, G, “NCI Workshop Report:

Clinical and Computational Requirements for Correlating Imaging Phenotypes with Genomics

Signatures,” Translational Oncology, vol. 7[5], pp. 556-569, 2014. (PMID: 25389451).

Sparks, R, Bloch, N, Moses, D, Ponsky, L, Barratt, D, Feleppa, E, Madabhushi, A, “Multi-Attribute

Probabilistic Prostate Elastic Registration (MAPPER): Application to Fusion of Ultrasound and

Magnetic Resonance Imaging”, Medical Physics, Accepted pending minor changes.

Litjens, G, Huisman, H, Elliot, R, Shih, N, Feldman, M, Viswanath, S, Futterer, J, Bomers, J,

Madabhushi, A, “Quantitative identification of MRI features of prostate cancer response following

laser ablation and radical prostatectomy”, Journal of Medical Imaging, vol. 1[3], 2014.

Wang, H, Cruz, A, Basavanhally, A, Gilmore, H, Shih, N, Feldman, M, Tomaszewski, J, Gonzalez, F,

Madabhushi, A, “Mitosis Detection in Breast Cancer Pathology Images by Combining Handcrafted and

Convolutional Neural Network Features”, J. Med. Imag., vol. 1[3], pg. 034003, 2014.

Lee, G, Singanamalli, A, Wang, H, Feldman, M, Master, SR, Shih, N, Spangle, E, Rebbeck, T,

Tomaszewski, J, Madabhushi, A, “Supervised Multi-View Canonical Correlation Analysis (sMVCCA):

Integrating histologic and proteomic features for predicting recurrent prostate cancer”, IEEE

Transactions on Medical Imaging, IEEE Trans Med Imaging, 2014, (PMID: 25203987).

Ginsburg, S, Bloch, BN, Genega, E, Lenkinsky, R, Feleppa, E, Rofsky, N, Madabhushi, A, “A Novel

PCA-VIP Scheme for Ranking MRI Protocols and Identifying Computer Extracted MRI Measurements

Associated with Central Gland and Peripheral Zone Prostate Tumors”, Journal of Magnetic

Resonance Imaging, 2014. doi: 10.1002/jmri.24676. (PMID: 24943647).

Peer Reviewed Publications for 2014Journal Papers (Contd.) Rusu, M, Bloch, BN, Jaffe, C, Genega, E, Lenkinsky, R, Feleppa, E, Rofsky, N, Madabhushi, A,

“Prostatome: A combined anatomical and disease based MRI atlas of the prostate”, Medical Physics,

vol. 41[7], pg. 072301, 2014 (PMID: 24989400).

Lee, G, Sparks, R, Ali, S, Feldman, M, Master, S, Shih, N, Tomaszewski, J, Madabhushi, A, “Co-

occurring Gland Tensors in Localized Subgraphs: Predicting Biochemical Recurrence in Intermediate-

risk Prostate Cancer Patients”, PLOS ONE, vol. 9[5], e97954, 2014 (PMID: 24875018).

Viswanath S, Sperling D, Lepor H, Futterer J, Madabhushi A “Identifying Quantitative In Vivo Multi-

Parametric MRI Features For Treatment Related Changes after Laser Interstitial Thermal Therapy of

Prostate Cancer” Neurocomputing, Special Issue on Image Guided Interventions, vol. 144, pp. 13-23,

2014 (PMID: 25346574).

Shridar, A, Doyle, S, Madabhushi, A, “Content-Based Image Retrieval of Digitized Histopathology in

Boosted Spectrally Embedded Spaces”, Journal of Pathology Informatics, Accepted.

Wan, T, Madabhushi, A, Phinikaridou, A, Hamilton, J, Hua, N, Pham, T, Danagoulian, J, Buckler, A,

“Spatio-temporal texture (SpTeT) for distinguishing vulnerable from stable atherosclerotic plaque on

DCE-MRI in a rabbit model”, Medical Physics, vol. 41[4], pg. 042303, 2014 (PMID: 24694153).

Agner, S, Rosen, M, Englander, S, Thomas, K, Tomaszewski, J, Feldman, M, Zhang, P, Mies, C Schnall,

M, Madabhushi, A, “Computerized Image Analysis for Identifying Triple Negative Breast Cancers and

Distinguishing Triple Negative Breast Cancers from Other Molecular Subtypes of Breast Cancer on

DCE-MRI: A Feasibility Study”, Radiology, vol. 272[1], pp. 91-9, 2014 (PMID: 24620909).

Toth, R, Feldman, M, Yu, D, Tomaszewski, J, Madabhushi, A, “Histostitcher™: An Informatics Software

Platform for Reconstructing Whole-Mount Prostate Histology using the Extensible Imaging Platform

(XIP™) Framework,” Journal of Pathology Informatics, vol. 5, pg. 8, 2014 (PMID: 24843820, PMCID:

PMC4023035).

Peer Reviewed Publications for 2014Journal Papers (Contd.) Toth, R, Traughber, B, Ellis, R, Kurhanewicz, J, Madabhushi, A, “A Domain Constrained Deformable

(DoCD) Model for Co-registration of Pre- and Post-Radiated Prostate MRI,” Neurocomputing, Special

Issue on Image Guided Interventions, vol. 144, pp. 3-12, 2014 (PMID: 25267873, PMCID:

PMC4175430).

Litjens, G, Toth, R, van de Ven, W, Hoeks, C, Kerkstra, S, van Ginneken, B, Reisaeter, L, Graham, V,

Guillard, G, Birbeck, N, Zhang, J, Strand, R, Malmberg, F, Ou, Y, Davatzikos, C, Kirschner, M, Jung,

F, Yuan, J, Qui, W, Gao, Q, Edwards, P, Maan, B, van der Heijden, F, Ghose, S, Mitra, J, Dowling, J,

Barratt, D, Huisman, H, Madabhushi, A, “Evaluation of prostate segmentation algorithms for MRI:

the PROMISE12 challenge”, Medical Image Analysis, pp. 359-73, vol. 18[2], 2014 (PMID: 24418598).

Wan, T, Bloch, BN, Shabbar, D, Madabhushi, A, “A Learning Based Fiducial-driven Registration

Scheme for Evaluating Laser Ablation Changes in Neurological Disorders”, Neurocomputing, Special

Issue on Image Guided Interventions, vol. 144, pp. 24-37, 2014 (PMID:25225455).

Lewis, J, Ali, S, Luo, J, Thorstad, W, Madabhushi, A, “A Quantitative Histomorphometric Classifier

(QuHbIC) Identifies Aggressive Versus Indolent p16 Positive Oropharyngeal Squamous Cell

Carcinoma”, American Journal of Surgical Pathology, pp. 128-37, vol. 38[1], 2014 (PMID:

24145650).

Peer Reviewed Publications for 2014Peer-reviewed Conference Papers

Cruz Roa, A, Osorio, FA, Madabhushi, A, Gonzalez, F, “A comparative evaluation of supervised and

unsupervised representation learning approaches for anaplastic medulloblastoma differentiation”,

In 10th International Symposium on Medical Information Processing and Analysis, Accepted.

Wang, H, Singanamalli, A, Ginsberg, S, Madabhushi, A, “Selecting Features with Group-sparse

Nonnegative supervised CCA (GNCCA): Multimodal Prostate Cancer Prognosis,” In Proc of Medical

Image Computing and Computer Assisted Interventions (MICCAI), vol. 17[3], pp. 385-92, 2014 (PMID:

25320823).

Prasanna, P, Tiwari, P, Madabhushi, A, “Co-occurrence of Local Anisotropic Gradient Orientations

(CoLlAGe): Distinguishing tumor confounders and molecular subtypes on MRI,” In Proc of Medical

Image Computing and Computer Assisted Interventions (MICCAI), vol. 17[3], pp. 73-80, 2014 (PMID:

25320784).

Singanamalli, A, Pisipati, S., Ali, A., Wang, V., Tang, C.T., Taouli, B., Tewari, A., and Madabhushi, A,

"Correlating gland orientation patterns on ex vivo 7 Tesla MRI with corresponding histology for

prostate cancer diagnosis: Preliminary results," The International Society for Optics and Photonics

(SPIE) Medical Imaging, 2015.

Rusu, M, Kurhanewicz, J, Madabhushi, A, “A prostate MRI atlas of biochemical failure following

radiotherapy“, The International Society for Optics and Photonics (SPIE) Medical Imaging, 2014.

Hwuang, E, Karthigeyan, S, Agner, S, Rusu, M, Sparks, R, Shih, N, Tomaszewski, J, Rosen, M,

Feldman, M, Madabhushi, A, “Spectral Embedding-based Registration (SERg) for Aligning Multimodal

Prostate Histology and MRI“, The International Society for Optics and Photonics (SPIE) Medical

Imaging, 2014.

Orooji, M, Madabhushi, A, “Joint image segmentation and feature parameter estimation using

expectation maximization: application to transrectal ultrasound prostate imaging”, The

International Society for Optics and Photonics (SPIE) Medical Imaging, 2014.

Peer Reviewed Publications for 2014Peer-reviewed Conference Papers (Contd.)

Litjens, G, Huisman, H, Elliot, R, Shih, N, Feldman, M, Viswanath, S, Bomers, J, Madabhushi, A,

“Distinguishing prostate cancer from benign confounders via a cascaded classifier on multi-

parametric MRI”, The International Society for Optics and Photonics (SPIE) Medical Imaging, 2014.

Litjens, G, Huisman, H, Elliot, R, Shih, N, Feldman, M, Viswanath, S, Futterer, J, Bomers, J,

Madabhushi, A, “Distinguishing benign confounding treatment changes following laser ablation

therapy from residual prostate cancer on MRI”, The International Society for Optics and Photonics

(SPIE) Medical Imaging, 2014.

Ginsburg, S, Rusu, M, Kurhanewicz, J, Madabhushi, A, “Computer-extracted texture features on T2w

MRI to predict biochemical recurrence following radiation therapy for prostate cancer“, The

International Society for Optics and Photonics (SPIE) Medical Imaging, 2014.

Singanamalli, A, Wang, H, Lee, G, Shih, N, Ziober, A, Rosen, M, Master, S, Tomaszewski, J, Feldman,

M, Madabhushi, A, “Supervised Multi-View Canonical Correlation Analysis: Fused Multimodal

Prediction of Disease Prognosis“, The International Society for Optics and Photonics (SPIE) Medical

Imaging, 2014.

Wang, H, Cruz-Roa, A, Basavanhally, A, Gilmore, H, Shih, N, Feldman, M, Tomaszewski, J, Gonzalez,

F, Madabhushi, A, “Cascaded Ensemble of Convolutional Neural Networks and Handcrafted Features

for Mitosis Detection“, The International Society for Optics and Photonics (SPIE) Medical Imaging,

2014.

Cruz-Roa, A, Basavanhally, A, Gonzalez, F, Gilmore, H, Feldman, M, Ganesan, S, Shih, N,

Tomaszewski, J, Madabhushi, A, “Automatic detection of invasive ductal carcinoma in whole slide

images with Convolution Neural Networks“, The International Society for Optics and Photonics (SPIE)

Medical Imaging, 2014.

Peer Reviewed Publications for 2014Peer-reviewed Conference Papers (Contd.)

Tiwari, P, Rogers, L, Wolansky, L, Madabhushi, A, “Differentiating recurrent glioblastoma multiforme

from radiation induced effects via texture analysis on multi-parametric MRI”, The International

Society for Optics and Photonics (SPIE) Medical Imaging, 2014.

Tiwari, P, Shabbar, D, Madabhushi, A, “Identifying MRI markers to evaluate early treatment related

changes post laser ablation for cancer pain management”, The International Society for Optics and

Photonics (SPIE) Medical Imaging, 2014. (PMID: 25075271, PMCID: PMC4112118)


Ali S, Basavanhally, A, Madabhushi, A, “Histogram of Hosoya Indices for Assessing Similarity Across

Subgraph Populations: Breast Cancer Prognosis Prediction From Digital Pathology” United States and

Canadian Academy of Pathology's 104th Annual Meeting, Boston, MA, March 21-27, 2015.

Ali S, Lewis J, and Madabhushi, A “A Quantitative Histomorphometric Classifier Identifies Role of

Stromal and Epithelial Features in Prediction of Disease Recurrence in p16+ Oropharyngeal

Squamous Cell Carcinoma” United States and Canadian Academy of Pathology's 104th Annual

Meeting, Boston, MA, March 21-27, 2015.

Cruz-Roa A, Basavanhally A, Gonzalez F, Feldman M, Ganesan S, Shih N, Tomaszewsky J, Gilmore H,

Madabhushi, A “A Feature Learning Framework for Reproducible Invasive Tumor Detection of Breast

Cancer in Whole-Slide Images” United States and Canadian Academy of Pathology's 104th Annual


Lee G, Veltri, Zhu G, Epstein J, and Madabhushi, A “Computerized Nuclear Shape Analysis of

Prostate Biopsy Images Predict Favorable Outcome in Active Surveillance Patients” United States

and Canadian Academy of Pathology's 104th Annual Meeting, Boston, MA, March 21-27, 2015.

Lee G, Veltri R, Ali S, Epstein J, Christudass C, and Madabhushi, A “Prostate cancer recurrence can

be predicted by measuring cell graph and nuclear shape parameters in the benign cancer-adjacent

field of surgical specimens” United States and Canadian Academy of Pathology's 104th Annual


Penzias G, Janowczyk A, Singanamalli A, Rusu M, Shih N, Feldman M, Viswanath S and Madabhushi, A

“AutoStitcher©: An Automated Program for Accurate Reconstruction of Digitized Whole Histological

Sections From Tissue Fragments” United States and Canadian Academy of Pathology's 104th Annual


Peer-reviewed Abstracts


Rusu M, Yang M, Rajiah P, Jacono F, Gilkeson R, Linden P, and Madabhushi, A “Histology – CT Fusion

Facilitates the Characterization of Suspicious Lung Lesions with No, Minimal, and Significant Invasion

on CT” United States and Canadian Academy of Pathology's 104th Annual Meeting, Boston, MA, March

21-27, 2015.

Viswanath S, Paspulati R, Delaney C, Willis J, and Madabhushi, A “A Novel Pathology-Radiology Fusion

Workflow for Predicting Treatment Response and Patient Outcome in Rectal Cancers” United States

and Canadian Academy of Pathology's 104th Annual Meeting, Boston, MA, March 21-27, 2015.

Tiwari, P, Prasanna, P, Barholtz-Sloan, J, Sloan, A, Ostrom, Q, Jiang, B, Madabhushi, A, “Quantitative

texture descriptors on baseline-MRI can predict patient survival in newly diagnosed glioblastoma

multiforme patients,” Annual Society for Neuro-oncology Scientific Meeting, 2014, Accepted.

Tiwari, P, Prasanna, P, Rogers, L, Wolansky, Leo, Madabhushi, A, “Computer extracted oriented

texture features on T1-Gadolinium MRI for distinguishing radiation necrosis from recurrent brain

tumors,” Annual Society for Neuro-oncology Scientific Meeting, 2014, Accepted.

Orooji, M, Linden, P, Gilkeson, R, Prabhakar, R, Yang, M, Jacono, F, Rusu, M, Madabhushi, A,

“Computer Extracted Texture Features on CT Predict Level of Invasion in Ground Glass Non-Small Cell

Lung Nodules,” Proceedings of the Radiologic Society of North America, 2014, Accepted (Oral).

Patel, J, Prasanna, P, Tiwari, P, Madabhushi, A, “Identifying MRI Markers On Newly Diagnosed

Glioblastoma Multiforme To Distinguish Patients With Long And Short Term Survival,” Biomedical

Engineering Society (BMES), 2014.

Antunes, J, Viswanath, S, Sher, A, Avril, N, Madabhushi, A, “Identifying PET/MRI Parameters for Early

Treatment Response in Renal Cell Carcinoma,” Biomedical Engineering Society (BMES), 2014.

Odgers, T, Massa, C, Rusu, M, Wang, H, Madabhushi, A, and Gow, A, “Structural And Functional

Modeling Of Pulmonary Function In Heterogenous Lung Pathology,” Novel and Traditional Lung

Function Assessment. May 1, A3572-A3572, 2014.

Peer-reviewed Abstracts (Contd.)

Invited Lectures

“Computational Knowledge Fusion and sub-visual image features for personalizing medicine”,

Department of Electrical and Computer Engineering, University of British Colombia, Vancouver, BC,

Canada, December 1, 2014. (Anant Madabhushi)

“Computer Extracted Texture Features on CT Predict Level of Invasion in Ground Glass Non-Small Cell

Lung Nodules,” Radiology Society Of North America, Chicago, IL, December 1st, 2014. (Mirabela Rusu)

“Computational MRI analysis for treatment evaluation and survival prediction in brain tumors,”

Imaging Seminar Series, Department of Biomedical Engineering, CWRU, November 25th, 2014. (Pallavi

Tiwari)

“Computational data convergence: Applications in diagnosis and prognosis of prostate cancer”,

Department of Urology, Cleveland Clinic, Cleveland, OH, October 22nd, 2014. (Anant Madabhushi)

“Careers in Computational Imaging: Interface of computer science and biomedical engineering”,

Invited Talk, Department of Electrical Engineering, Nacionale Universidad de Colombia, Bogota,

Colombia, Oct. 17th, 2014. (Anant Madabhushi)

“‘Radiomics’ risk score: Image based risk assessment for presence of recurrent tumor or radiation

effects on MRI,” Grand rounds in Oncology, University Hospitals, Cleveland, October 15th, 2014.

(Pallavi Tiwari)

Dr. Madabhushi

just after his

talk at

Teleradiology

Solutions in

Bangalore, India

https://www.youtube.com/watch?v=gH-mXQ7jt7E

Dr. Madabhushi

giving lecture at

University of

British Colombia,

Vancouver, BC,

Canada. (youtube

link under

picture)

Invited Lectures (Contd.)

“Computational Imaging and mining sub-visual image features for personalized medicine: Use cases in

breast, prostate, oropharyngeal and lung cancers”, Plenary Talk, 10th International Symposium on

Medical Information Processing and Analysis, Cartagena, Colombia, Oct. 14th, 2014. (Anant

Madabhushi)

“Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A domain-inspired descriptor to

distinguish ‘similar appearing’ pathologies on imaging”, Workshop on Radiomics, MD Anderson, Texas,

October 1st, 2014.

“Computational convergence of imaging, pathology, and omics data: Use case in prostate cancer”,

Workshop on Radiogenomics, MD Anderson Cancer Center, Houston, TX, September 29th, 2014. (Anant

Madabhushi)

“Multi-scale, sub-visual features for personalizing medicine”, Biomedical and Health Informatics

Workshop, Case Western Reserve University, Cleveland, OH, September 16th, 2014. (Anant Madabhushi)

“Radiology-pathology correlation: enriching imaging to enable disease signature discovery,” Imaging

Hour, Case Western Reserve University, Cleveland, OH, September 9th, 2014 (Mirabela Rusu)


breast, prostate, oropharyngeal and lung cancers”, Case Comprehensive Cancer Center, Cleveland,

OH, September 5th, 2014. (Anant Madabhushi)

“Multi-scale Data Enrichment in Prostate Cancer: Diagnosis, Prognosis and Population Based

Analytics,” International MRI Summer School, Iasi, Romania, August 5th, 2014. (Mirabela Rusu)

“Computational Breast Imaging and mining sub-visual image features for personalized medicine”,

Tata Memorial Hospital, Mumbai, India, July 24th, 2014. (Anant Madabhushi)

“Computational Imaging: Blending computer science and biomedical engineering”, Indian Institute of

Technology Bombay, Mumbai, India, July 21st, 2014. (Anant Madabhushi)



breast, prostate, oropharyngeal and lung cancers”, Tata Memorial Hospital, Mumbai, India, July 17th,

2014. (Anant Madabhushi)

“Computational Imaging and mining sub-visual image features for personalized medicine”, General

Electric, Bangalore, India, July 16th, 2014. (Anant Madabhushi)

“Computational Imaging and mining sub-visual image features for personalized medicine”,

Teleradiology Solutions, Bangalore, India, July 16th, 2014. (Anant Madabhushi)

“Computational Imaging and the Personalized Image based Risk Score”, Case Comprehensive Cancer

Center Retreat, Cleveland, OH, July 11th, 2014. (Anant Madabhushi)

“Multi-scale and sub-visual features: Applications in Personalized Medicine”, Workshop on Image

Ontologies, SUNY Buffalo, Buffalo, NY, June 25th, 2014. (Anant Madabhushi)

“3D Printing To Facilitate Prostate Cancer Diagnosis and Prognosis” Rapid, Detroit, MI, June 10th, 2014.

(Mirabela Rusu)

“Computer assisted diagnosis, prognosis, and treatment evaluation of prostate cancer from MRI and

digital pathology”, Prostate Cancer Seminar Series, Cleveland Clinic, Cleveland, OH, May 15th, 2014.

(Anant Madabhushi)

“Preparing yourself for a career in non-academic environments?”, Graduate Student Senate

Professional Development Conference, Case Western Reserve University, Cleveland, OH, May 2nd, 2014.

(Anant Madabhushi)

“Computational convergence of radiology and pathology data”, Joint workshop on Radiology-Pathology

Fusion by Radiological Society of North America (RSNA) and American Society of Clinical Pathology

(ASCP), Chicago, IL, April 22nd, 2014. (Anant Madabhushi)


“Radiology-Pathology Convergence: Application to Biological Quantitation and Disease

Characterization”, R25T Seminar Series, Memorial Sloan Kettering Institute Dept of Radiochemistry,

New York, NY, April 18th, 2014. (Satish Viswanath

“Computational Imaging and Personalized Medicine”, Department of Thoracic Oncology, Cleveland

Clinic, Cleveland, OH, April 16th, 2014. (Anant Madabhushi)

“Computational pathology: Personalized Medicine and Enriching Radiology and molecular data”,

Department of Rheumatology, Cleveland Clinic, Cleveland, OH, April 15th, 2014. (Anant Madabhushi)

“Computational pathology: Squeezing the most out your pathology images”, Imaging Hour, Case

Western Reserve University, Cleveland, OH, April 15th, 2014. (Anant Madabhushi)

“Computational pathology: Squeezing the most out your pathology images”, University of Uppsala,

Center for Medical Image Analysis, Uppsala, Sweden, April 10th, 2014. (Anant Madabhushi)

“Computational Imaging and Big Data Convergence in Personalized Medicine”, Grand Rounds in

Urology, University of Cincinnati, Cincinnati, OH, April 7th, 2014. (Anant Madabhushi)

“Computer-extracted texture features on T2w MRI to predict biochemical recurrence following radiation

therapy for prostate cancer” SPIE Medical Imaging, San Diego, CA, March 24th, 2014. (Mirabela Rusu)

“Computational pathology: Image analysis for Big Pathology Data”, American Society for Clinical

Pathology, Miami, FL, March 20th, 2014. (Anant Madabhushi)

“A prostate MRI atlas of biochemical failures following radiotherapy,” SPIE Medical Imaging, San Diego,

CA, March 18th, 2014. (Mirabela Rusu)

“Computational Imaging and Big Data Convergence in Personalized Medicine of Prostate Cancers”,

Grand Rounds in Department of Urology, Mount Sinai Medical Center, New York City, NY, March 5th,

2014. (Anant Madabhushi)

“Computational Imaging and Big Data Convergence in Personalized Medicine”, Executive Council

Meeting, Case Comprehensive Cancer Center, Cleveland, OH, February 27th, 2014. (Anant Madabhushi)


“Quantitative Data Convergence: Applications to Personalized Medicine”, Department of Mathematics,

Case Western Reserve University, Cleveland, OH, February 26th, 2014. (Anant Madabhushi)

“Computational pathology: Personalized Medicine and Enriching Imaging”, Translational Hematology

and Oncology Research (THOR) Seminar Series, Cleveland Clinic, Cleveland, OH, February 25th, 2014.

(Anant Madabhushi)

“Computational pathology: Personalized Medicine and Enriching Imaging”, Department of

Epidemiology and Biostatistics, Case Western Reserve University, Cleveland, OH, February 20th, 2014.

(Anant Madabhushi)

“Image based risk score: Application to ER+ breast cancers”, Department of Biomedical Engineering

Seminar Series, Case Western Reserve University, Cleveland, OH, February 10th, 2014. (Anant

Madabhushi)

“Computational pathology: Personalized Medicine and Enriching Imaging”, Department of Pathology

and Anatomic Medicine, University of Pennsylvania, Philadelphia, PA, January 21st, 2014. (Anant

Madabhushi)

PatentsIssued Patents

“System and Method for Accurate and Rapid Identification of Diseased Regions on

Biological Images with Applications to Disease Diagnosis and Prognosis”, Anant Madabhushi,

James Monaco, John E Tomaszewski, Michael D. Feldman, Ajay Basavanhally, United States

Serial Number (USSN): 8,718,340.

"System and Method for Automated Segmentation, Characterization, and Classification of

possibly malignant Lesions and Stratification of Malignant tumors”, Anant Madabhushi,

Shannon Agner, Mark Rosen, United States Serial Number (USSN): 8,774,479.

Provisional Patent Applications

“Methodology for textural analysis of nodules on imaging to determine extent of invasion”

Invention Disclosures

“Cascaded Ensemble of Convolutional Neural Networks and Handcrafted Features For Breast Cancer

Diagnosis”, Case No. 2014-2572.

“Histogram of Hosoya Index (HoH) features for Quantitative Histomorphometry”, Case No. 2014-2657

“A Group-Sparse Feature Selection Method for Multi-Modal Disease Prognosis”, Case No. 2014-2656

“Co-Occurrence of Local Anisotropic Gradient Orientations (CoLIAGe)”, Case No. 2014-2655

“Tumor+Adjacent Benign Signature (TABS) For Quantitative Histomorphometry”, Case No. 2014-2654

“Computational Scalpel: Treatment Planning for Rectal Cancer via Image Analytics”, Case No. 2014-

2684.

“Methodology for creation of a differential atlas”, Case No. 2015-2775

“Methodology for fusion of pathology and radiology data for disease characterization”, Case No.

2015-277

Awards and Accomplishments in 2014

Media Recognition

“Undergraduate wins Research Choice Award at biomedical engineering conference”, The Daily,

November 13th, 2014.

“Texture analysis shows level of invasion of ground-glass lung nodules”, AuntMinnie.com, November

10th, 2014.

Innovation

Award, Case

School of

Engineering,

2014

Awards and Accomplishments in 2014Media Recognition (cont.)

“CCIPD/BME Graduate Student Wins Young Scientist Runners up at MICCAI

2014”, Case Comprehensive Cancer Center News Letter, November 10th, 2014.

“Featured Faculty Member”, case.edu/faculty, October 30th, 2014.

“Madabhushi Awarded Two-year NIH Grant on Predicting Aggressive Head &

Neck Cancers from Digital Pathology”, Case Comprehensive Cancer Center

News Letter, September 2nd, 2014.

“Bioengineering’s Anant Madabhushi, team awarded patent relating to

radiologic imaging of tumors”, Case School of Engineering, July 28th, 2014.

“The Prostatome – a Novel Prostate Atlas Combining Anatomic and Disease

Pathology Data Founded”, Labmedica.com, July 24th, 2014.


“Prostate Cancer: Crunching the Numbers”, Biomedical Computation

Review, July 11th, 2014.

“Dr. Anant Madabhushi Awarded Phase II Coulter Grant on Brain Tumor”,

The Daily, July 7th, 2014

“Precision Medicine depends on big data”, Tech Page One, June 25th, 2014.

“Biomedical engineering’s Anant Madabhushi and team awarded V

Foundation Translational Research Grant”, The Daily, June 20th, 2014.

“CTSC/Coulter grant awarded to biomedical engineering, medicine

faculty”, The Daily, May 30th, 2014.


“Anant Madabhushi to Serve on Editorial Board for New IEEE "Journal of Translational Engineering

in Health and Medicine", Case Comprehensive Cancer Center Newsletter, May 26th, 2014.

“Madabhushi team awarded patent in digital pathology, cancer detection”, The Daily, May 16th,

2014.

“Biomedical engineering’s Anant Madabhushi and team receive innovation research grant”, The

Daily, April 25th, 2014.

“vascuVis Inc., a wholly owned subsidiary of Elucid Bioimaging, has been awarded a two-year,

$696,200 Small Business Innovation Research (SBIR) Phase II Grant from the National Science

Foundation”, Press Release, March 31, 2014.

“Using big data to identify triple-negative breast, oropharyngeal, and lung cancers”, Press Release,

Eurekalert.org, March 18th, 2014.


“HPV: Computerized Image Analysis May Distinguish Potentially Progressive Disease”,

DermatologistsBlog.com

“Computational imaging/Madabhushi team takes home honors at SPIE Medical Imaging 2014”, The

Daily, February 28th, 2014.

“Teaching Computers to Tell Cancer Cells Apart”, Prostate Cancer Discovery, A Publication of the

Patrick C. Walsh Prostate Cancer Research Fund, vol. 10, Winter 2014.

Professional/Editorial Activities in 2014Chairing, Membership Program Committees of Conferences, Workshops, Special issues

Session Chair, Cancer Imaging Track, 10th International Symposium on Medical Information Processing

and Analysis, Cartagena, Colombia, Oct. 14th, 2014 (Anant Madabhushi).

Program Committee Member, Ontology and Imaging Informatics, SUNY Buffalo, June 23rd, 2014

(Anant Madabhushi).

Program Committee Member, 10th International Symposium on Medical Information Processing and

Analysis, Cartagena, Colombia, Oct. 14-16, 2014 (Anant Madabhushi).

Session Chair, Conference 9401: Digital Pathology, Keynote Session, International Society for Optics

and Photonics (SPIE) Medical Imaging, Feb 18th, 2014, San Diego, CA (Anant Madabhushi).

Co-organizer and Co-Chair, Workshop: What do pathologists see on a slide? Implications for digital

pathology, International Society for Optics and Photonics (SPIE) Medical Imaging, Feb 18th, 2014, San

Diego, CA (Anant Madabhushi).

Editorial Boards

Associate Editor, IEEE International Symposium on Biomedical Imaging (ISBI) 2015 (Anant

Madabhushi).

Associate Editor, IEEE Journal of Translational Engineering in Health and Medicine, May 2014-Present

(Anant Madabhushi).

Editorial Board, IEEE Journal of Translational Engineering in Health and Medicine, May 2014-Present

(Anant Madabhushi).

New Grants Awarded in 2014 Madabhushi, Anant (Co-I) 01/01/14 - 10/31/14

V Foundation

Use of PET and MR Imaging Biomarkers to Predict Response of Renal Cell Carcinoma to Tyrosine

Kinase Inhibitor Therapy

Madabhushi, Anant (Co-I) 01/01/14 - 12/31/15

NSF

Computer assisted prognosis of debilitating disease

Madabhushi, Anant (PI) 06/01/14-05/30/15

CTSC Coulter Annual Pilot Grant

Computerized Histologic Image-based predictor of recurrence in breast cancers following treatment

Madabhushi, Anant (PI) 09/01/14-08/31/16

DOD CDMRP Lung Cancer Research Idea Development Award New Investigator (LC130463)

Computer extracted CT features for distinguishing suspicious lung lesions with no, minimal, and

significant invasion

Tiwari, Pallavi (PI) 09/01/14 - 08/31/15

Coulter Research Translational Partnership

NeuroRadVisionTM: Image based risk score prediction of recurrent brain tumors (Phase 2)

Madabhushi, Anant (PI) 9/01/14 - 8/30/16

NIH 1R21CA179327-01A1

Histologic image-based aggressiveness prediction in p16+ oropharyngeal carcinoma

Student Fellowships in 2014

Patel, Jay (PI) 06/01/14-09/01/14

SOURCE CAA 2014 Summer Research Scholar


Segmentation and Shape Based Feature Modeling for Treatment Evaluation of Glioblastoma Multiforme

Penzias, Gregory (PI) 06/01/14-09/01/14

SOURCE CAA 2014 Summer Research Scholar


Automatic Fusion of Prostate Histology, Multi-Parametric MRI, and PET for Improved Characterization of

Prostate Cancer

Student, Post-doctoral Awards and Accomplishments

Jacob Antunes, Reviewers Choice Award, Biomedical Engineering Society Department of Imaging

and Optics Chair (5% of all submissions receive this commendation), 2014

Jacob Antunes, Biomedical Engineering Society Scholarship for involvement in a professional

integrity workshop focused on ethics of authorship, 2014

Jacob Antunes, Case Western Reserve University Biomedical Engineering Society Executive Board

Travel Award, 2014

Jay Patel, SOURCE CAA Travel Award, Case Western Reserve University, 2014

Prateek Prasanna, Runner Up, Young Scientist Award, Medical Image Computing and Computer

Assisted Intervention Society (MICCAI), 2014

Andrew Janowczyk, Excellence in PhD Thesis Award, Indian Institute of Technology Bombay, 2014

Prateek Prasanna, Medical Image Computing and Computer Assisted Intervention Society (MICCAI)

Travel Award, 2014

Gregory Penzias, SOURCE CAA Summer Research Scholar, Case Western Reserve University, 2014

Prateek Prasanna, Semi-finalist Launchtown Competition, 2014

Jay Patel, SOURCE CAA Summer Research Scholar, Case Western Reserve University, 2014

Eileen Hwuang, NSF Graduate Research Fellowship, 2014

Eileen Hwuang, Cum Laude for Best Poster Presentation at the Image Processing Conference,

International Society for optics and Photonics (SPIE) Medical Imaging, 2014

Geert Litjens, Robert F. Wagner Best Student Paper Award, Runner up, International Society for

optics and Photonics (SPIE) Medical Imaging, 2014

Eileen Hwuang, SPIE Medical Imaging Student Grant, 2014

RESEARCH PORTFOLIO

PROSTATE CANCER

BREAST CANCER

BRAIN TUMORS

OROPHARYNGEAL CANCER

LUNG CANCER

COLORECTAL CANCER

IMAGE SEGMENTATION

MACHINE LEARNING

CO-REGISTRATION

MULTIMODAL DATA FUSION

RADIOLOGY

HISTOPATHOLOGY

BIOINFORMATICS

RADIATION ONCOLOGY

APPLICATION DOMAINS

DISEASE SITES

METHODS

IMAGE REGISTRATION AND

SEGMENTATION

Biomechanical Model for Pre-, Post-Treatment Prostate

Registration

• Model of prostate tissue

properties (e.g. elasticity,

compressibility)

• Physically-real deformations

applied to prostate & internal

zones

• Spatial alignment of pre-, post-

treatment prostate volumes

• RMS error of alignment: 2.99 mm

• Traditional biomechanical model

(not considering internal zones)

RMS error: 5.07 mm

Toth, R., Traughber, B., Ellis, R., Kurhanewicz, J., Madabhushi, A., “A Domain Constrained Deformable (DoCD) Model

for Co-registration of Pre- and Post-Radiated Prostate MRI.” Neurocomputing 144(20) Nov 2014. pp. 3-12,

doi: 10.1016/j.neucom.2014.01.058.

Pre-Treatment MRI Aligned Post-Treatment MRI

http://dx.doi.org/10.4103/2153-3539.129441

Spatially Aware Expectation-Maximization and Statistical Shape

Model for Prostate Segmentation in Transrectal Ultrasound

Orbital Boarder Model: New Statistical Shape Model for Prostate Segmentation in

Transrectal Ultrasound ImagerySpatially Aware

EM

Laplasian Shape

Prior Prob

Orbital Boarder

Model

50 100 150 200 250 300 350 400 450

50

100

150

200

250

300

350

Calculate Prob. of

each ray

50 100 150 200 250 300 350 400 450

50

100

150

200

250

300

350

50 100 150 200 250 300 350 400 450

50

100

150

200

250

300

350

Preliminary Results

Orooji, M., Blochc, N.; Feleppad, E.; Barratte, D.; Madabhushia, A.; “ Orbital Boarder Model: A New Algorithm for Prostate Segmentation on

Transrectal Ultrasound Imagery”, SPIE 2014

Multi-Attribute Probabilistic Prostate Elastic

Registration (MAPPER)

1. Segment

Prostate on MRI

2. Construct

Model on TRUS3. Align MRI Mask

to TRUS Model

Methods Results

0

2

4

6

Intensity Multifeature Rayleigh

Feature

Ro

ot

Me

an

Sq

ua

red

Err

or

(mm

)

Ta

Te

R. Sparks, B. N. Bloch, E. Feleppa, D. Barratt, L. Ponsky, A. Madabhushi. Multi-attribute Probabilistic Prostate Elastic Registration

(MAPPER): Application to Fusion of Ultrasound and Magnetic Resonance Imaging. Medical Physics, in press.

Histology – CT Fusion Facilitates the Characterization of Suspicious Lung

Lesions with No, Minimal, and Significant Invasion on CT

Rusu et. al. (Accepted Annual Meeting of the United States and Canadian Association of Pathology)

Ground glass nodule histology-CT fusion; (a) 3D view of nodule with axial (blue) and oblique (red) cutting plane; (b) CT

intensities (oblique cut); (c) CT intensities (axial cut); (d) H&E section corresponding to the oblique cut (b); invasion

(black) and adenocarcinoma in situ + invasion (yellow); (e) the interactive alignment of histology and CT allows to map

extent of invasion from histology onto CT; (f) CT-based textures will be included in a predictor

(c)(b)

(f)

(a)

(e)(d)

MACHINE LEARNING AND FEATURE ANALYSIS

Computerized Nuclear Shape Analysis of Prostate Biopsy Images

Predict Favorable Outcome in Active Surveillance Patients

• Active surveillance (AS), an accepted monitoring program, may be offered for men with very low risk (VLR)

CaP in lieu of immediate intervention to reduce unnecessary treatment and improve quality of life.

• Our objective is to identify computationally derived features from digitized biopsy core images which can

predict favorable and unfavorable outcomes for VLR AS patients.

Lee et al. Accepted for presentation at United States and Canadian Academy of Pathology (USCAP) 2015

65 H&E stained biopsy core

images (30 Favorable, 35

Unfavorable) obtained from 51 AS

CaP patients

Nuclear shape features (AUC =

0.78)

Gleason Score (AUC = 0.60).

Mitosis Detection in Breast Cancer Images by Combining

Handcrafted and Convolutional Neural Network Features

Goal: To detect mitosis figures in high power fields of breast cancer tissues.

(a) Our mitosis detection framework detect nuclei

candidates from a high-power field (HPF) using blue-

ration color transformation as segmentation method and

then each candidate is used to train and classify whether

is a mitotic figure or not by a handcrafted based

classifier and a feature learning classifier using a

Convolutional Neural Network. When both classifiers

disagree about the classification, other classifier

combine both features, handcrafted and learned, to the

final classification of these confounding cases. (b)

Evaluation results show that our combined feature

strategy outperform the performance of each feature

independently and most of the previous baseline. (c) An

example of mitosis detection in a HPF is presented with

TP (green), FN(yellow) and FP(red)..

Haibo Wang, Angel Cruz-Roa, Ajay Basavanhally, Hannah Gilmore, Natalie Shih, Mike Feldman, John Tomaszewski, Fabio Gonzalez, and Anant Madabhushi.

Mitosis Detection in Breast Cancer Pathology Images by Combining Handcrafted and Convolutional Neural Network Features. Journal of Medical Imaging.

1(3):034003 (2014). ISSN: 2329-4302. doi:10.1117/1.JMI.1.3.034003

a)

c)b)

Assessment of Algorithms for Mitosis Detection in Breast

Cancer Histopathology ImagesGoal: To evaluate and compare different computational methods for mitosis detection.

(a) By taking a set of high-power fields (HPF), different methods for mitosis detection were evaluated in the AMIDA challenge 2013

(http://amida13.isi.uu.nl/). (b) Evaluation results show the best results for IDSIA and DTU algorithms outperforming the performance

measures (Precision, Recall and F-measure) of others approaches. (c) Sumarize the performance measure of each approach in the final

evaluation of the challenges where our approach (CCIPD/MINDLAB) occupied the 6th place but without significant statistical difference with

the third one.

Mitko Veta, Paul J. van Diest, Stefan M. Willems, Haibo Wang, Anant Madabhushi, Angel Cruz-Roa, Fabio Gonzalez, Anders B. L. Larsen, Jacob S.

Vestergaard, Anders B. Dahl, Dan C. Cireșan, Jürgen Schmidhuber, Alessandro Giusti, Luca M. Gambardella, F. Boray Tek, Thomas Walter, Ching-Wei Wang,

Satoshi Kondo, Bogdan J. Matuszewski, Frederic Precioso, Violet Snell, Josef Kittler, Teofilo E. de Campos, Adnan M. Khan, Nasir M. Rajpoot, Evdokia

Arkoumani, Miangela M. Lacle, Max A. Viergever, Josien P.W. Pluim. Assessment of algorithms for mitosis detection in breast cancer histopathology images.

Journal of Medical Image Analysis. 2014. (In press)

a) b) c)

Extracted Texture Features on CT Predict Level of

Invasion in Ground Glass Lung Nodules

Quantitative characterization of spatial heterogeneity

using computerized methods

Textural analysis could identify subtle cues of invasion on

CT that might not be visible

25% of positive nodules on baseline CT are Ground Glass

or Semi-solid nodules

The extent of invasion is correlated with prognosis

Disease free survival at 5 years when resected:

– 100 % : Minimally invasive

• Adenocarcinoma in situ

• Minimally Invasive Adenocarcinoma (≤ 5 mm invasion)

– 67-90 %: Frank invasion

• Invasive Adenocarcinoma (> 5 mm invasion)

Currently radiologists are unable to distinguish the level

of invasion from in situ on CT

CT

Contr

ast

Invers

e

Mom

ent

Contr

ast

Vari

ance

Minimal InvasionFrank Invasion

Orooji, M.; Rusu, M.; Rajiah, P.; Yang, M.; Jacono, F.; Gilkeson, R.; Linden, P.;

Madabhushi, A.; “Computer Extracted Texture Features on CT Predict Level of

Invasion in Ground Glass Non-Small Cell Lung Nodules”, Radiological Society of

North America (RSNA), Chicago, IL.

Distinguishing Recurrent GBMs from Radiation Necrosis Using Co-

occurrence of Localized Gradient Orientations (CoLlAGe)

Radiation Necrosis

Recurrent GBM

Lower density of high entropy regions

Higher Density of high

entropy regions

Prasanna, Tiwari et al. SNO (2014)

ER+

HER2+

Fibroadenoma

(a)

(d)

(g)

(b) (c)

(e) (f)

(i)(h)

Differential Expression of CoLlAGe Features for

Different Molecular Subtypes of Breast Cancer

Prasanna, Tiwari, Madabhushi, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): Distinguishing Tumor Confounders and

Molecular Subtypes on MRI, Conference: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014

A B

E

C D

HGF

Example of both local and global graphs built into a TMA image of OCSCC which was previously segmented by

automatic thresholding into blue ratio colour space for nuclei detection. Cell Cluster Graphs (A and E), Voronoi

Diagram (B and F), Delaunay Triangulation (C and G), and Minimum Spanning Tree (D and H). First row shows

the graphs over TMA image (A-D) and second row details only the graphs (E-H). Notice that all graphs were built

using the same nuclei segmentation method.

Evaluating stability and discriminability of graph features for

digital pathology classification

Angel Cruz-Roa, Jun Xu, Anant Madabhushi, "A note on the stability and discriminability of graph based features for classification problems in digital pathology",

SIPAIM 2014

A Comparative evaluation of supervised and unsupervised representation

learning approaches for anaplastic medulloblastoma differentiation

Goal: To evaluate and compare different methods of representation and deep

learning for anaplastic medulloblastoma tumor differentiation.

(a) A representation learning framework is proposed

to train and classify square tissue regions from

medulloblastoma tumors. In order to evaluate which

kind of representation learning, unsupervised or

supervised, we evaluate the representation learning

module by using different methods. Unsupervised

feature learning methods used were: Sparse Auto-

encoders (sAE), Topographic Independent Component

Analysis Autoencoders (TICA), and Supervised feature

learning method was: Convolutional Neural Network

(CNN). All methods were trained and evaluated using

the same experimental setup to classify between

anaplastic and non-anaplastic tumor. (b) Evaluation

results show how unsupervised feature learning

method TICA obtained the best results for different

configuration followed by a large supervised feature

learning method of CNN. TICA has the advantage that

introduce invariant properties of visual features that

can be useful for this task. Interestingly, all

representation learning methods, unsupervised and

supervised, outperform the data-driven baseline

methods based on bag of features (BOF).

Angel Cruz-Roa, John Arévalo, Ajay Basavanhally, Anant Madabhushi, Fabio González. (2014, October 14-16). A comparative evaluation of supervised and

unsupervised representation learning approaches for anaplastic medulloblastoma differentiation. Tenth International Symposium on Medical Information

Processing and Analysis (SIPAIM 2014), Cartagena, Colombia.

a)

b)

MULTI-MODAL DATA FUSION

Supervised Multi-View Canonical Correlation Analysis (sMVCCA):

Integrating Histologic and Proteomic Features for Predicting

Recurrent Prostate Cancer

• Our new data integration methodology, supervised Multi-view Canonical Correlation Analysis

(sMVCCA), aims to integrate infinite views of highdimensional data to provide more

amenable data representations for disease classification.

• Additionally, we demonstrate sMVCCA using Spearman’s rank correlation which, unlike

Pearson’s correlation, can account for non-linear correlations and outliers.

Lee et al. IEEE Trans Med Imaging (2014)

IPMI'13Group-Sparse Multi-modal Feature Selection for

Prostate Cancer Prognosis

Wang et al., Selecting Features with Group-sparse Nonnegative Supervised Canonical Correlation Analysis: Multi-modal Prostate Cancer Prognosis, MICCAI 2014.

T2w MRI

DCE MRI

Multi-m

odal fe

atu

re se

lectio

n

classification

112-D features

56-D features

Characterizing Pulmonary Inflammation on in vivo MRI via 3D

Histological Reconstruction and Fusion in a Mouse Model

Rusu et. al. (submitted), Medical Physics

(a) (b) (c)

(d) (e) (f)

Multi-modal fusion to characterize the appearance of lung inflammation in a mouse model: (a) 3D reconstructed histology shows the

extent of inflammation in 3D; (b) fusion of 3D histology and in vivo MRI; (c) 3D inflammation is mapped from histology onto in vivo MRI;

Gabor feature in (d) wild type control mouse, (e) SPDKO inflammation caring mouse; (f) within the inflammation region

Prediction of

Prostate Cancer

5-year

Biochemical

RecurrencesMVCCA Histology Proteomics

0.5

0.55

0.6

0.65

0.7

0.75

0.8

0.85

Are

a U

nd

er

RO

C C

urv

e

Fusion vs. Individual Modalities

*

*

Histology Proteomics

In vivo

prediction of

prostate

cancer risk

sMVCCA T2w MRI DCE MRI0.5

0.55

0.6

0.65

0.7

0.75

0.8

Are

a U

nd

er

RO

C C

urv

e

Fused and Individual Predictors of Prostate Cancer Grade

*

*

T2w MRI DCE MRI

Early Diagnosis

of Alzheimer’s

Disease

sMVCCA T1w MRI Proteomics

0.55

0.6

0.65

0.7

0.75

0.8

0.85

0.9

Are

a U

nd

er

RO

C C

urv

e

Fused and Individual Predictors of Alzheimers Disease

*

*

-1

0

1

2

3

4

Alp

ha-1

-Mic

roglo

bulin

Alp

ha-2

-Macro

glo

bulin

Alp

ha-1

-Antichym

otr

ypsin

Alp

ha-1

-Antitr

ypsin

Angio

tensin

-Convert

ing E

nzym

e

Adip

onectin

Alp

ha-F

eto

pro

tein

Agouti-R

ela

ted P

rote

in

Angio

poie

tin-2

Angio

tensin

ogen

Apolip

opro

tein

A-I

Apolip

opro

tein

A-I

I

Apolip

opro

tein

A-I

V

Apolip

opro

tein

B

Apolip

opro

tein

C-I

T1w MRI Plasma Proteomics

Supervised Multiview CCA: Data Fusion Strategy

Goal: Fusion of multi-modal data to improve prediction of disease diagnosis and prognosis

Singanamalli, A., Lee, G., Wang, H., et al. “Supervised multi-view canonical correlation analysis: fused multimodal prediction of disease diagnosis and

prognosis”, SPIE 2014

TREATMENT EVALUATION AND

OUTCOME PREDICTION

Pre-treatment

MRI Follow-up (t1) Follow-up (t2) Follow-up (t3) Follow-up (t4)

Quantifying Temporal Changes in MRI to Evaluate

Treatment Changes Post-LITT in Epilepsy Patients

Tiwari et al, PlosOne (in press)

A Novel Pathology-Radiology Fusion Workflow for Predicting

Treatment Response and Patient Outcome in Rectal Cancers

Correlate rectal surgical specimens with pre-operative MRI, identify imaging

signatures for chemoradiation response and different treatment effects

Viswanath et al, “A Novel Pathology-Radiology Fusion Workflow for Predicting Treatment

Response and Patient Outcome in Rectal Cancers”, USCAP 2015 (accepted)

Identifying PET/MRI Parameters for Early Treatment

Response in Renal Cell Carcinoma

Antunes, J., Viswanath, S., Rusu, M., Sher, A., Hoimes, C., Avril, N., and Madabhushi, A, “Identifying PET/MRI Parameters for

Early Treatment Response in Renal Cell Carcinoma,” Annual National Biomedical Engineering Society Conference, 2014

Normal tissue:

No expected changeRCC:

Expected change

Pre- Post- Pre- Post-

PET

AD

C-M

ap

Sum

Avera

ge

PET

AD

C-M

ap

Sum

Avera

ge

Goal: Identify quantitative PET/MRI

parameters that reflect early response

in metastatic RCC to tyrosine kinase

inhibitor treatment

Quantified SUV, ADC, and T2W sum

average parameters appear to be

reflective of early changes due to

cytostatic drug treatment response

Quantitative Identification of MRI Features of Prostate Cancer

Response Following Laser Ablation and Radical Prostatectomy

Co-registration of

radiological and

histopathological data can

help determine differentially

expressing features in pre-

and post therapy MRI to

assess laser-interstitial

thermotherapy success in

prostate cancer ablation

Co-registration of post-LITT MRI and

histopathology

Co-registration of post- and pre-LITT

MRI MRI feature extraction

Determining changes in features from pre- to

post-treatment MRI in ablated areas and residual

disease

Clustering to determine residual disease

extent using differentially expressing

features obtained in previous steps

Geert JS Litjens, Henkjan J Huisman, Robin M Elliott, Natalie Nc Shih, Michael D Feldman, Satish Viswanath, Jurgen J Fütterer, Joyce GR Bomers, Anant

Madabhushi. Journal of Medical Imaging 1 (3), 035001-035001

Short-

term

survival

Long-

term

survival

Radiomic Markers on Treatment-Naïve MRI can

Predict Survival in GBM PatientsIntensity Sum Entropy Correlation

Tiwari et al, SNO (2014)

FLAIR-MRI

0 10 20 30 40 500

0.2

0.4

0.6

0.8

1

Sur

viva

l Rat

e

Time (months)

p-value: 0.77773

Short Term

Long Term

0 10 20 30 40 500

0.2

0.4

0.6

0.8

1

Sur

viva

l Rat

e

Time (months)

p-value: 5.716e-07

Short Term

Long Term

Signal Intensity

Radiomic Features

Kaplan Meier (KM) survival

curves for long and short-term

survival GBM patients

COMPUTER AIDED DIAGNOSIS AND PROGNOSIS

Prostate Cancer Recurrence can be Predicted by Measuring Cell

Graph and Nuclear Shape Parameters in the Benign Cancer-

Adjacent Field of Surgical Specimens

• The 'field effect' describes the micro-environment around the site of the tumor which may

lead to a progression of disease.

• Combined features extracted from images corresponding to tumor regions with that of images

corresponding to benign adjacent regions to create a Tumor + Adjacent Benign Signature

Lee et al. Accepted for presentation at United States and Canadian Academy of Pathology (USCAP) 2015

140 H&E stained

biopsy core

images from 70

patients (22

progressors, 48

non-

progressors)

Gland Orientation Patterns on ex vivo 7 Tesla MRI for

Prostate Cancer Diagnosis

Singanamalli, A., Pisipati, S., Ali, A., Wang, V., Tang, C.Y., ,Taouli, B., Tewari, A., Madabhushi, A., “Correlating gland orientation patterns on ex vivo 7

Tesla MRI with corresponding histology for prostate cancer diagnosis: Preliminary analysis”, To appear in proc SPIE 2015

Overview: Disorder in orientation of visible glands on ex vivo 7T prostate MRI can predict cancer presence

and are correlated with disorder in gland orientations on pathology

(a) Co-registration of histology and (b) ex vivo 7T MRI; Co-occurring gland tensors of (b, f) benign and (c, g) tumor

tissues on (b, c) pathology and (f, g) 7T MRI ; Entropy of gland orientations as computed from (d) pathology and from (h)

7T MRI distinguish between benign and tumor tissues

Benign Tumor

1

2

3

4

5

entr

opy,

Benign Tumor1

1.5

2

2.5

3

3.5

entr

opy,

(a) (b) (c) (d)

(e) (f) (g) (h)

(f)

T2w

MRI

DCE

MRI

ADC

Map

T2w + DCE

+ ADC

Texture

Features

Multi-Parametric MRI for Prostate

Cancer Localization

S Ginsburg, et al. Novel PCA-VIP scheme for ranking MRI protocols and

identifying computer-extracted MRI measurements associated with central gland

and peripheral zone prostate tumors. JMRI available online.

Purpose: To identify computer-extracted features from multi-

parametric MRI that are useful for detecting and localizing prostate

tumors in the central gland or peripheral zone of the prostate.

Histogram of Hosoya Indices for Assessing Similarity Across

Subgraph Populations: Breast Cancer Prognosis Prediction from

Digital Pathology

Identifying similar subgraph structures that are recurring across the

population and their effect on overall tumor morphology remains

unexplored.

Hosoya index (HI) (originally introduced for analysis of chemical bonds) is

a measure of a bond (in this context nuclei connections in a graph)

In this work, we have leverage HI to measure structural similarities of

graphs across the populations that are indicative of recurrence in breast

cancer tissue images Illustration of Hosoya Index calculation

Figure 1. Original BCa TMA representing

tumor with (a) recurrent tumor (d) non-

recurrent tumor. (b) and (e) represent the

corresponding cell graphs and resulting

hosoya signature in (c) and (f) respectively.

Ali et al, USCAP 2015

SOFTWARE

AutoHistoStitcherTM:

Preliminary Algorithm

Accepted for

Presentation at USCAP

2015, Boston MA

ProstaCAD Ver. 2

Updated

GUI Redesigned

Based Image Processing Redesigned

New Features Added

A Generic Image Analysis Framework

HistoView

HistoView is a

graphical user

interface for

pathology image

analysis and

visualization.

Separates the image

into different

channels,

corresponding to the

actual colors of the

stain used.

Binarizes the channel

image by thresholding

and visualizes

thresholded result.

Supports whole-slide

images.

INTERESTED IN JOINING CCIPD?

We are always looking for enthusiastic and

motivated graduate, undergraduate students, post-

doctoral and research scientists.

If you think you would be a good fit for CCIPD, send

over your complete CV and 3 representative

publications to “anantm” @ “case.edu”

Follow us on Twitter: @CCIPD_Case

Center for Computational Imaging and Personalized ......Prateek Prasanna, Runner Up, Young Scientist...

Documents

Transcript of Center for Computational Imaging and Personalized ......Prateek Prasanna, Runner Up, Young Scientist...