Title:Learning from Multimodal Data for Improving Radiology Imaging-Based Cancer Detection

Abstract:Radiology imaging-based cancer detection and risk-stratification play an important role in improving personalized patient care, treatment planning, reducing cancer deaths, and reducing overtreatment. Yet, subtle imaging features lead to wide inter-reader variability, missed cancers, and overdiagnosis and overtreatment of indolent disease. Computational methods that leverage the fusion of multimodal machine learning with interdisciplinary domain knowledge have immense potential in helping standardize radiologist interpretations and serving as a diagnostic support tool to clinicians. Research questions involve how to seamlessly integrate and learn from complementary multimodal data (e.g., radiology images, pathology images, clinical variables) in clinically relevant ways, and how to design robust experiments and evaluations to enable translation from the laboratories to the clinic. This talk will highlight how we address these questions as we develop multimodal machine learning systems to assist clinicians in prostate and kidney cancer detection and risk-stratification.

Bio:

Dr. Indrani Bhattacharya is an Assistant Professor in the Department of Biomedical Data Science. She is also affiliated with the Center for Precision Health and Artificial Intelligence (CPHAI) and the Center for Technology and Behavioral Health (CTBH) at Dartmouth. Prior to her current appointment, she was a Research Engineer in the Department of Radiology (Division of Integrative Biomedical Imaging Informatics) at Stanford University School of Medicine.  Dr. Bhattacharya received her Ph.D. and M.S. in Electrical, Computer, and Systems Engineering from Rensselaer Polytechnic Institute (RPI), NY, and her bachelor’s in electrical engineering from Jadavpur University, India. Dr. Bhattacharya’s research focuses on developing translational machine learning and image analysis methods that help clinicians in disease detection, risk-stratification, and treatment planning. She is specifically interested in investigating how to seamlessly integrate and learn from multimodal imaging and non-imaging medical data for developing precision medicine and personalized treatment plans. Her research is highly interdisciplinary, at the intersection of machine learning, medicine, and human behavioral analytics. During her doctoral and postdoctoral research career, she has been the recipient of multiple awards, including the RPI Founder’s Award of Excellence, selection as one of the ‘Rising Stars in EECS, 2020’, and several travel, poster, and perfect pitch awards from the NIH, NSF, DoD, and DoE.