Date: Thursday, April 10, 2025
Location: Stevenson Center 5326
Time: 11:45 am for lunch; noon start

Title: Advancing Precision across the Surgical Care Continuum

Abstract: In the continuum of surgical care, advances in diagnostic and therapeutic precision drive the modern approach to cancer treatment. Treatment quality in surgical oncology fundamentally depends on the exactness of diagnostic assessment, the personalization of therapeutic management, and the completeness of treatment delivery. Yet, despite clinical decision-making relying heavily on longitudinal integration of multimodal data, computer-assisted methods for interpreting changes in disease state are substantially challenged by the ability to achieve robust longitudinal congruity of data throughout treatment course. This talk will highlight recent work that enables (i) multi-modal radiology-pathology deformable image fusion to establish dense ground truth supervision signal as a novel reference standard for training diagnostic models, (ii) longitudinal image registration to establish reliable imaging markers for characterizing therapeutic response, and (iii) registration uncertainty to establish robust intraoperative capabilities for comprehensively targeting preoperatively mapped disease. In aggregate, this research aims to transform the ability to accurately characterize and map the longitudinal context of disease state through all phases of treatment course to advance the precision of image-guided assessment and intervention.

Bio: Jon S. Heiselman, Ph.D. is a Research Assistant Professor of Biomedical Engineering and Director of the Master of Engineering in Surgery and Intervention Program at Vanderbilt University. He was previously a Research Associate in the Department of Surgery at Memorial Sloan Kettering Cancer Center. He is an alumnus of Vanderbilt University (Ph.D. in Biomedical Engineering, 2020) and the University of Michigan Ann Arbor (B.S.E. in Biomedical Engineering, 2015). His research focuses on advancing computer-assisted monitoring, delivery, and assessment of cancer therapies through computational methods in image registration, biomechanical modeling, machine learning, and uncertainty quantification to facilitate clinical interventions and optimize procedural medicine.