Improving Consistency and Reducing Human Bias for Physicians' Target Contouring using AI Auto-Segmentation
This podcast discussed the topic of "Improving consistency and reducing human bias for physicians’ target contouring using AI auto-segmentation." Experts joining the discussion include Steve Jiang, PhD, Professor and Vice Chair in Department of Radiation Oncology at University of Texas Southwestern and Director of Medical Artificial Intelligence and Automation Lab, Nathan Yu, MD, Assistant Professor in Department of Radiation Oncology, Mayo Clinic Arizona, and Yi Rong, PhD, Professor and Lead photon physicist in Department of Radiation Oncology at Mayo Clinic Arizona. This podcast focused on the utility of AI in automatic segmentation of medical imaging and the challenges related to physician variability in clinical practice. We discussed various strategies for addressing these challenges, including developing physician-style aware AI models and balancing standardization with personalization in AI tool development and deployment. The emphasis is on the feasibility and clinical utility of using AI to improve the accuracy and efficiency of medical image segmentation while respecting the art and personalization inherent in clinical medicine.