提升病理图像中异常有丝分裂的跨域识别准确率
Mix, Align, Distil: Reliable Cross-Domain Atypical Mitosis Classification
- 通过风格扰动增强特征多样性，分阶段注入模型
- 利用弱域标签对齐多站点注意力特征，提升泛化能力
- 基于EMA教师模型与温度缩放蒸馏，稳定预测结果
异常有丝分裂（AMFs）是重要的组织病理学标志物，但受扫描仪、染色和采集差异导致的域偏移影响，识别一致性差。本文针对MIDOG 2025任务2提出一种简单训练时策略，以实现域鲁棒的AMF分类。方法包括：(i) 在骨干网络早期和中期引入风格扰动，增加特征多样性；(ii) 利用弱域标签（扫描仪、来源、物种、肿瘤类型）通过辅助对齐损失，对齐各站点注意力优化后的特征；(iii) 通过指数移动平均（EMA）教师模型结合温度缩放KL散度进行蒸馏，稳定预测输出。在主办方提供的初步排行榜上，该方法达到平衡准确率0.8762、敏感度0.8873、特异度0.8651及ROC AUC 0.9499。该方法推理开销极低，仅依赖粗粒度域元数据，性能均衡且强大，为MIDOG 2025挑战赛提供了有力竞争方案。
原文摘要 · Abstract (English)
Atypical mitotic figures (AMFs) are important histopathological markers yet remain challenging to identify consistently, particularly under domain shift stemming from scanner, stain, and acquisition differences. We present a simple training-time recipe for domain-robust AMF classification in MIDOG 2025 Task 2. The approach (i) increases feature diversity via style perturbations inserted at early and mid backbone stages, (ii) aligns attention-refined features across sites using weak domain labels (Scanner, Origin, Species, Tumor) through an auxiliary alignment loss, and (iii) stabilizes predictions by distilling from an exponential moving average (EMA) teacher with temperature-scaled KL divergence. On the organizer-run preliminary leaderboard for atypical mitosis classification, our submission attains balanced accuracy of 0.8762, sensitivity of 0.8873, specificity of 0.8651, and ROC AUC of 0.9499. The method incurs negligible inference-time overhead, relies only on coarse domain metadata, and delivers strong, balanced performance, positioning it as a competitive submission for the MIDOG 2025 challenge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。