Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification
- 17 February 2026
- journal article
- Published by Wiley in Pathology International
- Vol. 76 (2) , e70098
Abstract
Deploying pathology AI at individual hospitals faces challenges including limited cases and adapting pretrained models to local data. Brain tumor classification, with diverse diagnostic categories but few cases per institution, represents this challenge. Foundation models may offer a solution, but optimal transfer learning strategies remain unclear. We evaluated fine‐tuning (FT) versus linear probing (LP) for brain tumor classification using foundation models (UNI, Prov‐GigaPath) and conventional models including ImageNet‐pretrained Vision Transformer (ViT‐L) and CTransPath. Models were trained on an institutional dataset (254 cases: glioblastoma, astrocytoma, oligodendroglioma, PCNSL, and metastatic tumors) and validated on EBRAINS dataset (698 cases). Conventional models maintained FT ≥ LP on both datasets. However, foundation models showed a reversal: FT only marginally outperformed LP on institutional data, and LP significantly outperformed FT on external data ( p < 0.01), suggesting that fine‐tuning may compromise the generalization capabilities of foundation models. Notably, UNI with LP using only 10 patches per case significantly outperformed fine‐tuned conventional models using 500 patches on external validation ( p < 0.001). These findings suggest that for foundation models, fine‐tuning on limited institutional data may cause overfitting, and preserving pre‐trained representations through linear probing enables more efficient AI implementation with better generalization.Keywords
All Related Versions
Funding Information
- Japan Science and Technology Agency (JPMJBS2426)
This publication has 20 references indexed in Scilit:
- Applications of artificial intelligence in the analysis of histopathology images of gliomas: a reviewnpj Imaging, 2024
- A whole-slide foundation model for digital pathology from real-world dataNature, 2024
- Registered multi-device/staining histology image dataset for domain-agnostic machine learning modelsScientific Data, 2024
- Towards a general-purpose foundation model for computational pathologyNature Medicine, 2024
- Primary brain tumours in adultsThe Lancet, 2023
- Robust and data-efficient generalization of self-supervised machine learning for diagnostic imagingNature Biomedical Engineering, 2023
- Histopathological auxiliary system for brain tumour (HAS-Bt) based on weakly supervised learning using a WHO CNS5-style pipelineJournal of Neuro-Oncology, 2023
- Transformer-based unsupervised contrastive learning for histopathological image classificationMedical Image Analysis, 2022
- Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologyMedical Image Analysis, 2019
- Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade GliomasNew England Journal of Medicine, 2015