Bridging ML Models with Medical Insights for Learning, Inference, and Model Explanation in Radiology

Explore a comprehensive conference talk that bridges machine learning models with medical insights for learning, inference, and model explanation in radiology applications. Delve into cutting-edge research on graph-based self-supervised representation learning for medical images, progressive exaggeration techniques for model explanation, and the challenges of avoiding shortcut solutions in contrastive learning. Examine the use of causal analysis for conceptual deep learning explanation in medical imaging and discover how unpaired data can empower association tests in bioinformatics. Gain valuable insights from Kayhan Batmanghelich's presentation at the Computational Genomics Summer Institute (CGSI) 2022, which synthesizes findings from multiple related papers to provide a holistic view of the intersection between machine learning and medical applications.

Kayhan Batmanghelich | Bridging ML Models with Medical Insights for Learning, ...| CGSI 2022