用深度集成与规则优化提升肿瘤细胞有丝分裂图像分类准确率
Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement
- 采用多个ConvNeXtBase模型集成学习，提升分类稳定性
- 在MIDOG25测试集上达到84.02%的平衡准确率
- 规则模块可提升特异性，但需优化以避免敏感性下降
有丝分裂图像是肿瘤分级的重要生物标志物。区分异常有丝分裂（AMFs）与正常有丝分裂（NMFs）仍具挑战，因人工标注耗时且主观。本文训练了一个基于ConvNeXtBase的深度集成模型，并引入规则基础修正（RBR）模块。在MIDOG25初步测试集上，集成模型取得84.02%的平衡准确率。虽然RBR提升了特异性，但降低了敏感性和整体性能。结果表明，深度集成在AMF分类中表现良好；而RBR虽能提高特定指标，仍需进一步研究。
原文摘要 · Abstract (English)
Mitotic figures (MFs) are relevant biomarkers in tumor grading. Differentiating atypical MFs (AMFs) from normal MFs (NMFs) remains difficult, as manual annotation is time-consuming and subjective. In this work an ensemble of ConvNeXtBase models was trained with AUCMEDI and extend with a rule-based refinement (RBR) module. On the MIDOG25 preliminary test set, the ensemble achieved a balanced accuracy of 84.02%. While the RBR increased specificity, it reduced sensitivity and overall performance. The results show that deep ensembles perform well for AMF classification. RBR can increase specific metrics but requires further research.
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。