Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge
Biwen Meng, Xi Long, Jingxin Liu
公開日: 2025/9/1
Abstract
Atypical mitotic figures (AMFs) are clinically relevant indicators of abnormal cell division, yet their reliable detection remains challenging due to morphological ambiguity and scanner variability. In this work, we investigated three variants of adapting the pathology foundation model UNI2-h for the MIDOG2025 Track 2 challenge. Starting from a LoRA-based baseline, we found that visual prompt tuning (VPT) substantially improved generalization, and that further integrating test-time augmentation (TTA) with Vahadane and Macenko stain normalization provided the best robustness. Our final submission achieved a balanced accuracy of 0.8837 and an ROC-AUC of 0.9513 on the preliminary leaderboard, ranking within the top 10 teams. These results demonstrate that prompt-based adaptation combined with stain-normalization TTA offers an effective strategy for atypical mitosis classification under diverse imaging conditions.