Cross-Domain Validation of a Resection-Trained Self-Supervised Model on Multicentre Mesothelioma Biopsies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seyedshahi, Farzaneh, Damiola, Francesca, Lantuejoul, Sylvie, Yuan, Ke, Quesne, John Le
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911296398557184
author Seyedshahi, Farzaneh
Damiola, Francesca
Lantuejoul, Sylvie
Yuan, Ke
Quesne, John Le
author_facet Seyedshahi, Farzaneh
Damiola, Francesca
Lantuejoul, Sylvie
Yuan, Ke
Quesne, John Le
contents Accurate subtype classification and outcome prediction in mesothelioma are essential for guiding therapy and patient care. Most computational pathology models are trained on large tissue images from resection specimens, limiting their use in real-world settings where small biopsies are common. We show that a self-supervised encoder trained on resection tissue can be applied to biopsy material, capturing meaningful morphological patterns. Using these patterns, the model can predict patient survival and classify tumor subtypes. This approach demonstrates the potential of AI-driven tools to support diagnosis and treatment planning in mesothelioma.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01681
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Domain Validation of a Resection-Trained Self-Supervised Model on Multicentre Mesothelioma Biopsies
Seyedshahi, Farzaneh
Damiola, Francesca
Lantuejoul, Sylvie
Yuan, Ke
Quesne, John Le
Computer Vision and Pattern Recognition
Accurate subtype classification and outcome prediction in mesothelioma are essential for guiding therapy and patient care. Most computational pathology models are trained on large tissue images from resection specimens, limiting their use in real-world settings where small biopsies are common. We show that a self-supervised encoder trained on resection tissue can be applied to biopsy material, capturing meaningful morphological patterns. Using these patterns, the model can predict patient survival and classify tumor subtypes. This approach demonstrates the potential of AI-driven tools to support diagnosis and treatment planning in mesothelioma.
title Cross-Domain Validation of a Resection-Trained Self-Supervised Model on Multicentre Mesothelioma Biopsies
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.01681