Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge
Not on the map. Why?
Abstract (arXiv)
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 for the MIDOG2025 Track 2 challenge: (1) LoRA + UNI2, (2) VPT + UNI2 + Vahadane Normalizer, and (3) VPT + UNI2 + GRL + Stain TTA. We observed that the integration of Visual Prompt Tuning (VPT) with stain normalization techniques contributed to improved generalization. The best robustness was achieved by further incorporating test-time augmentation (TTA) with Vahadane and Macenko stain normalization. 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 suggest that prompt-based adaptation combined with stain-normalization TTA offers a promising strategy for atypical mitosis classification under diverse imaging conditions.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 7 of its 12 references that are in the map. First posted on arXiv 1 Sep 2025.
Builds on
7 of 12 references.
References · 7
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,909
- 2022Visual Prompt Tuningcited by 1,677
- 2017Adversarial Discriminative Domain Adaptationcited by 1,310
- 2022Mitosis domain generalization in histopathology images -- The MIDOG challengecited by 66
- 2018Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challengecited by 61
- 2025Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)cited by 17
- 2025Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluationcited by 7
Built on by
Not cited yet.