用染色感知增强和混合损失提升病理图像中异常有丝分裂的鲁棒识别
Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization
- 基于DenseNet121，结合染色感知增强与几何/亮度变换
- 在多域测试中达85.0%准确率、0.927 AUROC，敏感性89.2%
- 适合真实病理场景下异常有丝分裂的自动检测任务
异常有丝分裂是组织病理学中肿瘤侵袭性的关键生物标志物，但因类别严重不平衡及成像域间差异，可靠识别仍具挑战。本文提出一种面向MIDOG 2025（Track 2）的DenseNet-121框架，集成染色感知增强（Macenko）、几何与强度变换，以及通过加权采样实现的不平衡自适应学习，采用类别加权二元交叉熵与焦点损失的混合目标函数。模型以AdamW端到端训练，并在多个独立域上评估，展现出对扫描仪和染色变化的强泛化能力，在官方测试集上达到85.0%平衡准确率、0.927 AUROC、89.2%敏感性和80.9%特异性。结果表明，DenseNet-121结合染色感知增强与不平衡自适应目标，可构建适用于真实计算病理工作流的鲁棒、域泛化分类框架。
原文摘要 · Abstract (English)
Atypical mitotic figures are important biomarkers of tumor aggressiveness in histopathology, yet reliable recognition remains challenging due to severe class imbalance and variability across imaging domains. We present a DenseNet-121-based framework tailored for atypical mitosis classification in the MIDOG 2025 (Track 2) setting. Our method integrates stain-aware augmentation (Macenko), geometric and intensity transformations, and imbalance-aware learning via weighted sampling with a hybrid objective combining class-weighted binary cross-entropy and focal loss. Trained end-to-end with AdamW and evaluated across multiple independent domains, the model demonstrates strong generalization under scanner and staining shifts, achieving balanced accuracy 85.0%, AUROC 0.927, sensitivity 89.2%, and specificity 80.9% on the official test set. These results indicate that combining DenseNet-121 with stain-aware augmentation and imbalance-adaptive objectives yields a robust, domain-generalizable framework for atypical mitosis classification suitable for real-world computational pathology workflows.
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。