Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification
This work addresses the challenge of accurate atypical mitosis classification for improved patient prognostication in pathology, though it appears incremental as it builds on existing foundation models and methods.
The paper tackled the problem of classifying atypical mitoses in histopathology images, which correlates with tumor aggressiveness, by ensembling multiple Pathology Foundation Models with ConvNeXt V2 and achieving competitive balanced accuracy on a preliminary dataset.
Mitotic figures are classified into typical and atypical variants, with atypical counts correlating strongly with tumor aggressiveness. Accurate differentiation is therefore essential for patient prognostication and resource allocation, yet remains challenging even for expert pathologists. Here, we leveraged Pathology Foundation Models (PFMs) pre-trained on large histopathology datasets and applied parameter-efficient fine-tuning via low-rank adaptation. In addition, we incorporated ConvNeXt V2, a state-of-the-art convolutional neural network architecture, to complement PFMs. During training, we employed a fisheye transform to emphasize mitoses and Fourier Domain Adaptation using ImageNet target images. Finally, we ensembled multiple PFMs to integrate complementary morphological insights, achieving competitive balanced accuracy on the Preliminary Evaluation Phase dataset.