A Fairness Audit of Medical Imaging Foundation Models on a Multimodal Structured Clinical Benchmark

Milan Mohan, Saketh Lingisetty, Umar Ahmad, Avi Kumar, Shankar Harikrishnan, Sanjana Chamarty, Kevin Zhu

Submission Type: I want my submission to be considered for poster only

Keywords: Medical Imaging Foundation Models, Vision Transformers (ViT) in Healthcare, Representation Learning (Frozen Encoders), Linear Probing, Multimodal Learning, Clinical Prediction Models, Pulmonary Embolism Detection (CTPA), Medical Image Analysis, Health disparities

TL;DR: Foundation models for medical imaging miss critical localized signals, leading to worse PE diagnosis and large age-driven fairness gaps that only high capacity models can effectively mitigate.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 446