Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer
This work addresses the need for better evaluation methods for foundation models in medical imaging, specifically for kidney cancer, but it appears incremental as it applies existing techniques to a new domain.
The researchers tackled the problem of evaluating foundation models for translational capabilities in kidney cancer by developing a pathological concept learning approach, which demonstrated effectiveness in survival analysis with explainability and fairness in identifying patient risk levels.
To evaluate the translational capabilities of foundation models, we develop a pathological concept learning approach focused on kidney cancer. By leveraging TNM staging guidelines and pathology reports, we build comprehensive pathological concepts for kidney cancer. Then, we extract deep features from whole slide images using foundation models, construct pathological graphs to capture spatial correlations, and trained graph neural networks to identify these concepts. Finally, we demonstrate the effectiveness of this approach in kidney cancer survival analysis, highlighting its explainability and fairness in identifying low- and high-risk patients. The source code has been released by https://github.com/shangqigao/RadioPath.