A comprehensive evaluation of histopathology foundation models for ovarian cancer subtype classification.
No Thumbnail Available
All Authors
Breen, J.
Allen, K.
Zucker, K.
Godson, L.
Orsi, NM.
Ravikumar, N.
LTHT Author
Allen, Katie
Zucker, Kieran
Godson, Lucy
Orsi, Nicolas
Zucker, Kieran
Godson, Lucy
Orsi, Nicolas
LTHT Department
Pathology
Histopathology
Oncology
Leeds Cancer Centre
Research & Innovation
Histopathology
Oncology
Leeds Cancer Centre
Research & Innovation
Non Medic
Digital Pathology Scientist
Publication Date
2025
Item Type
Journal Article
Language
Subject
Subject Headings
Abstract
Histopathology foundation models show great promise across many tasks, but analyses have been limited by arbitrary hyperparameters. We report the most rigorous single-task validation study to date, specifically in the context of ovarian carcinoma morphological subtyping. Attention-based multiple instance learning classifiers were compared using three ImageNet-pretrained encoders and fourteen foundation models, each trained with 1864 whole slide images and validated through hold-out testing and two external validations (the Transcanadian Study and OCEAN Challenge). The best-performing classifier used the H-optimus-0 foundation model, with balanced accuracies of 89%, 97%, and 74%, though UNI achieved similar results at a quarter of the computational cost. Hyperparameter tuning the classifiers improved performance by a median 1.9% balanced accuracy, with many improvements being statistically significant. Foundation models improve classification performance and may allow for clinical utility, with models providing a second opinion in challenging cases and potentially improving the accuracy and efficiency of diagnoses.
Journal
Npj Precision Oncology