Evaluating Foundation Models with Pathological Concept Learning for Kidney Cancer

preprint OA: gold CC-BY-NC-4.0
📄 Open PDF Full text JSON View at publisher
AI-generated deep summary by claude@2026-07, 2026-07-04 · read from full text

The paper evaluates the translational capabilities of foundation models using a pathological concept learning framework for kidney cancer. Using TNM staging guidelines and pathology reports, the authors build pathological concepts, extract deep features from whole-slide images with foundation models, represent spatial relationships as pathological graphs, and train graph neural networks to identify these concepts; they then apply the learned concepts to kidney cancer survival analysis. The study reports that the approach improves performance while providing explainability and fairness in distinguishing low- and high-risk patients, with a key caveat that the work is validated on available TNM/pathology-report-derived concepts and data sourced from TCGA/TNM-aligned pathology information. Relevance to endometriosis: the paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

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 .
Full text 2,804 characters · extracted from oa-doi-fallback · click to expand
Abstract 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. Competing Interest Statement The authors have declared no competing interest. Funding Statement This work was supported by the Cancer Research UK Cambridge Centre [CTRQQR-2021\textbackslash 100012; and C9685/A25117], The Mark Foundation for Cancer Research [RG95043], NIHR Cambridge Biomedical Research Centre (NIHR203312), and the EPSRC Tier-2 capital grant [EP/P020259/1]. M.C.O. was supported by the Joseph Mitchell Cancer Research Fund, the Academy of Medical Sciences [G117526] and NIHR [NIHR206092]. Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The results shown here are in whole or part based upon data generated by the TCGA Research Network: http://cancergenome.nih.gov/. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data Availability The results shown here are in whole or part based upon data generated by the TCGA Research Network: http://cancergenome.nih.gov/.

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: oa-doi-fallback

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-21T05:10:58.409756+00:00
License: CC-BY-NC-4.0