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.
@article{arxiv.2509.25552,
title = {Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer},
author = {Shangqi Gao and Sihan Wang and Yibo Gao and Boming Wang and Xiahai Zhuang and Anne Warren and Grant Stewart and James Jones and Mireia Crispin-Ortuzar},
journal= {arXiv preprint arXiv:2509.25552},
year = {2025}
}