MitoDetect++可精准检测并区分正常与异常有丝分裂，适合跨域病理分析。
MitoDetect++: A Domain-Robust Pipeline for Mitosis Detection and Atypical Subtyping
- 采用U-Net+EfficientNetV2-L主干网络，融合注意力机制进行检测
- 在验证域上实现0.892的平衡准确率，跨域泛化能力强
- 适用于临床病理诊断，尤其适合多中心数据场景
自动化检测和分类有丝分裂，尤其是区分异常与正常类型，是计算病理学中的关键挑战。本文提出MitoDetect++，一个面向MIDOG 2025挑战的统一深度学习流程，同时解决有丝分裂检测与异常亚型分类任务。检测部分（Track 1）采用基于U-Net的编码器-解码器结构，以EfficientNetV2-L为骨干网络，结合注意力模块，并使用组合分割损失进行训练。分类部分（Track 2）利用Virchow2视觉变换器，通过低秩适应（LoRA）高效微调，降低资源消耗。为提升泛化能力、缓解域偏移，引入强数据增强、焦点损失及分组感知的五折交叉验证。推理阶段采用测试时增强（TTA）进一步提升鲁棒性。该方法在多个验证域上达到0.892的平衡准确率，凸显其临床适用性与多任务可扩展性。
原文摘要 · Abstract (English)
Automated detection and classification of mitotic figures especially distinguishing atypical from normal remain critical challenges in computational pathology. We present MitoDetect++, a unified deep learning pipeline designed for the MIDOG 2025 challenge, addressing both mitosis detection and atypical mitosis classification. For detection (Track 1), we employ a U-Net-based encoder-decoder architecture with EfficientNetV2-L as the backbone, enhanced with attention modules, and trained via combined segmentation losses. For classification (Track 2), we leverage the Virchow2 vision transformer, fine-tuned efficiently using Low-Rank Adaptation (LoRA) to minimize resource consumption. To improve generalization and mitigate domain shifts, we integrate strong augmentations, focal loss, and group-aware stratified 5-fold cross-validation. At inference, we deploy test-time augmentation (TTA) to boost robustness. Our method achieves a balanced accuracy of 0.892 across validation domains, highlighting its clinical applicability and scalability across tasks.
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。