is a Professor in the Department of Electrical and Computer Engineering, at McGill University (Montréal, Québec, Canada) and the Director of the "Probabilistic Vision Group" and "Medical Imaging Lab" in Centre for Intelligent Machines.
Tal Arbel's research focuses on developing novel probabilistic and machine learning techniques in computer vision and applying them to problems in medical imaging, particularly in neurology and neurosurgery. She has extensive expertise in developing probabilistic graphical models for brain tumor/lesion detection and segmentation, which were successfully applied to the MICCAI BraTS Challenge
public datasets (2012-2016) and to large-scale, multi-scanner, multi-center clinical trial datasets of patients with Multiple Sclerosis (MS). Additional graphical models were developed for accurate detection and segmentation of lesions in contrast-enhanced images, as well as in longitudinal MRI, both important markers of new disease activity and for assessing treatment effects in clinical trials. Tools developed in her lab are currently being used in the software analysis pipeline of her industrial partner for the analysis of almost all new MS treatments throughout the world. She is also working on computational neuroanatomy, with the objectives of generating automatic discoveries of healthy brain morphometry, including the variability of the cortex, as well as permitting the automatic identification of biomarkers of disease progression in MS and cancer. Multi-modal image registration tools that have been developed in her lab have been integrated into the operating theatres of the Montreal Neurological Hospital, where they are being used to assist in image-guidance for tumor resections.
Dr. Arbel has co-organized a number of major international conferences in two fields, including serving as co-organizer and satellite events chair for MICCAI 2017
, area chair/program committee member for CVPR and MICCAI, and General Chair for a major joint national conference (AI/GI/CRV/IS). She currently serves on the editorial board of the Journal of Computer Vision and Image Understanding (CVIU).
She will give a talk on segmentation of lesions and tumors in the context of images of patients with various neurodegenerative diseases, including MS and brain cancer.
is an Associate Professor in the Department of Radiology, Division of Neuroradiology, Perelman School of Medicine at the University of Pennsylvania, and a board-certified Neuro-Radiologist at the Hospital of the University of Pennsylvania (HUP), with 14 years of experience working with gliomas and a dual medical-engineering background.
He is actively pursuing neuroimaging research, applying image processing techniques to solve clinical questions, particularly in Multiple Sclerosis (MS), neurodegenerative disorders, cerebrovascular disease, and primary brain neoplasms. His research involves looking for image-based biomarkers to quantify disease and predict progression. He has developed a Computer-Aided Detection software to detect new lesions on brain MRI in patients with MS that has been fully integrated into the current clinical workflow, and is being used multiple times daily by all neuroradiologists in the department of Neuro-Radiology at the HUP.
He will give a talk of two parts, focusing i) on the revisited ground truth that the BraTS'17 challenge
will use this year, and ii) on the clinical perspective of computational neuro-oncology.
is an Assistant Professor (tenure-track) in the Departments of Cancer Systems Imaging and Diagnostic Radiology, Section of Neuroradiology, at the UT MD Anderson Cancer Center. She is also the co-Director of the Quantitative Imaging Analysis Core. Her research program, the Imaging Genomics, Radiomics, and Therapeutics Lab, focuses on radiomics, radiogenomics (imaging genomics), advanced imaging analytics, multi-parametric imaging and image guided therapy. Dr. Colen's lab is an imaging-based program with research studies that spans the spectrum of clinical, translational and preclinical imaging genomics and radiomics. Her research capitalizes on radiomics and imaging genomics to interrogate all types of cancer as well as non-cancer diseases such as autism, Alzheimer's disease, epilepsy, Parkinson's, etc. Imaging genomics is the linkage of imaging with the genomic composition of the tumor. They have found that distinct radiomic signatures are seen with distinct gene expression profiles in multiple solid cancers. On the other hand, radiomics is the automated high-throughput extraction of multi-dimensional imaging features obtained from medical images. Dr. Colen has demonstrated that radiomic features can provide a more accurate representation of the tumor and tumor heterogeneity, it can depict genomic niches and distinct tumor microenvironmental habitats within solid tumors and other tissue structures. Dr. Colen is very much focused on creating stratification and endpoint biomarkers for use in clinical trials that will better help stratify patients into clinical trials and determine therapy response early on or even before receiving treatment. She has found that radiomics can differentiate between true tumor progression and pseudoprogression (also known as post-treatment changes), a dilemma which can be seen in patients of different types of treatment and in particular immunotherapy. While harnessing the strengths of big data, merging imaging and other -omic data into large centralized databases and analysis, Dr. Colen's team develops software code and scripts that are used for large-scale imaging genomic and radiomic analysis pipelines and adaptive/predictive modeling to determine response to treatment and patient outcomes with high accuracy. They have multiple ongoing studies on multi-parametric imaging such as MR-diffusion, perfusion, and spectroscopy as predictive biomarkers in neuro-oncology treatment and most recent looking at predictive biomarkers to predict GBM genomics. They have experience in 2HG MRS to evaluate gliomas with IDH1 mutation and are working on elucidating the molecular underpinnings of radiomics within different cancers and in drug development. Dr. Colen has found accurate human to mouse matching of imaging, making the case for co-clinical trials using radiomics. She believes in harnessing the power of imaging and genomics that can converge to non-invasively visualize tumor heterogeneity in toto and connect it with the underlying molecular heterogeneity. Image-guided biopsies of tumor areas of 'highest complexity/heterogeneity' will result in identification of driver molecular events of tumor heterogeneity, elucidation of mechanisms of resistance, and response to therapy. Overall, Dr. Colen's research program is dedicated to "helping cure cancer using imaging" with the overarching goal to help find a cure for patients and improve patient outcomes.
She will give a talk focusing on radiomics and radiogenomics of brain tumors.
Jerry L. Prince
received the B.S. degree from the University of Connecticut in 1979 and the S.M., E.E., and Ph.D. degrees in 1982, 1986, and 1988, respectively, from the Massachusetts Institute of Technology, all in electrical engineering and computer science. He worked at the Brigham and Women's Hospital, MIT Lincoln Laboratories, and The Analytic Sciences Corporation (TASC). He joined the faculty at the Johns Hopkins University in 1989, where he is currently William B. Kouwenhoven Professor in the Department of Electrical and Computer Engineering and holds joint appointments in the Departments of Radiology, Biomedical Engineering, Computer Science, and Applied Mathematics and Statistics. Dr. Prince is a Fellow of the IEEE, Fellow of the MICCAI Society, Fellow of the AIMBE, and a member of Sigma Xi. He also holds memberships in Tau Beta Pi, Eta Kappa Nu, and Phi Kappa Phi honor societies. He was an Associate Editor of IEEE Transactions on Image Processing from 1992-1995, an Associate Editor of IEEE Transactions on Medical Imaging from 2000-2004 and is currently a member of the Editorial Board of Medical Image Analysis. Dr. Prince received a 1993 National Science Foundation Residential Faculty Fellows Award, was Maryland's 1997 Outstanding Young Engineer, and was awarded the MICCAI Society Enduring Impact Award in 2012. He is also co-founder of Sonavex, Inc. His current research interests are in image processing and computer vision with primary application to medical imaging; he has published over 300 articles and abstracts on these subjects.