MIDRC and Medical Imaging AI

Forum Details

Date: Friday, October 17, 2025 12PM Eastern Time

Speakers: Maryellen L. Giger, PhD from the University of Chicago

Maryellen Giger, PhD from University of Chicago shows how Artificial Intelligence in medical imaging involves research in task-based discovery, predictive modeling, and robust clinical translation.  Quantitative radiomic analyses, an extension of computer-aided detection (CADe) and computer-aided diagnosis (CADx) methods, are yielding novel image-based tumor characteristics, i.e., signatures that may ultimately contribute to the design of patient-specific cancer diagnostics and treatments. Beyond human-engineered features, deep networks are also being investigated in the diagnosis of disease on radiography, ultrasound, MRI, molecular imaging, and others.  The method of extracting characteristic radiomic features of a region can be referred to as “virtual biopsies”.  For such AI, there is a critical need for curated, diverse, and re-usable data to enable development of trustworthy AI.  This presentation will discuss AI and the creation and benefits of MIDRC (midrc.org; data.midrc.org) relative to medical imaging, with specific focus on curated data, representative data, various resources, validation methods and sequestered data, understanding of potential biases, and sustainability.