Saved in:
Bibliographic Details
Main Authors: Gao, Shangqi, Wang, Sihan, Gao, Yibo, Wang, Boming, Zhuang, Xiahai, Warren, Anne, Stewart, Grant, Jones, James, Crispin-Ortuzar, Mireia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.25552
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912616827322368
author Gao, Shangqi
Wang, Sihan
Gao, Yibo
Wang, Boming
Zhuang, Xiahai
Warren, Anne
Stewart, Grant
Jones, James
Crispin-Ortuzar, Mireia
author_facet Gao, Shangqi
Wang, Sihan
Gao, Yibo
Wang, Boming
Zhuang, Xiahai
Warren, Anne
Stewart, Grant
Jones, James
Crispin-Ortuzar, Mireia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25552
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer
Gao, Shangqi
Wang, Sihan
Gao, Yibo
Wang, Boming
Zhuang, Xiahai
Warren, Anne
Stewart, Grant
Jones, James
Crispin-Ortuzar, Mireia
Artificial Intelligence
J.3
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.
title Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer
topic Artificial Intelligence
J.3
url https://arxiv.org/abs/2509.25552