Foundation models pretrained on large-scale pathology datasets have shown promising results across various diagnostic tasks. Here, we present a systematic evaluation of transfer learning strategies for brain tumor classification using these models. We analyzed 254 cases comprising five major tumor types: glioblastoma, astrocytoma, oligodendroglioma, primary central nervous system lymphoma, and metastatic tumors. Comparing state-of-the-art foundation models with conventional approaches, we found that foundation models demonstrated robust classification performance with as few as 10 patches per case, despite the traditional assumption that extensive per-case image sampling is necessary. Furthermore, our evaluation revealed that simple transfer learning strategies like linear probing were sufficient, while fine-tuning often degraded model performance. These findings suggest a paradigm shift from "training encoders on extensive pathological data" to "querying pre-trained encoders with labeled datasets", providing practical implications for implementing AI-assisted diagnosis in clinical pathology.
View on arXiv@article{enda2025_2501.11014,
title={ Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification },
author={ Ken Enda and Yoshitaka Oda and Zen-ichi Tanei and Kenichi Satoh and Hiroaki Motegi and Terasaka Shunsuke and Shigeru Yamaguchi and Takahiro Ogawa and Wang Lei and Masumi Tsuda and Shinya Tanaka },
journal={arXiv preprint arXiv:2501.11014},
year={ 2025 }
}