用医学领域大模型识别异常有丝分裂，提升病理诊断准确率。
Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
- 基于病理大模型H-optimus-0，结合LoRA微调与MixUp增强。
- 通过专家共识生成软标签，实现自适应焦点损失与度量学习。
- 适合病理图像分析、医学大模型应用的研究者参考。
我们针对MIDOG 2025挑战赛第二赛道，提出一种正常有丝分裂（NMFs）与异常有丝分裂（AMFs）的二分类方法。该方法基于近期跨域泛化基准与实测表现优选的病理专用基础模型H-optimus-0，采用低秩适配（LoRA）微调，并结合MixUp数据增强。具体实现包括基于多专家共识的软标签、硬负样本挖掘、自适应焦点损失、度量学习与领域自适应策略。初步评估显示，该方法在复杂分类任务中展现出潜力，也揭示了基础模型应用中的挑战。
原文摘要 · Abstract (English)
We present a solution for the MIDOG 2025 Challenge Track~2, addressing binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs). The approach leverages pathology-specific foundation model H-optimus-0, selected based on recent cross-domain generalization benchmarks and our empirical testing, with Low-Rank Adaptation (LoRA) fine-tuning and MixUp augmentation. Implementation includes soft labels based on multi-expert consensus, hard negative mining, and adaptive focal loss, metric learning and domain adaptation. The method demonstrates both the promise and challenges of applying foundation models to this complex classification task, achieving reasonable performance in the preliminary evaluation phase.
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。