用特定增强方法提升卷积模型对癌细胞分裂图像的分类准确率
ConvNeXt with Histopathology-Specific Augmentations for Mitotic Figure Classification
- 基于轻量级ConvNeXt架构，融合多数据集提升泛化能力
- 在挑战赛中达到0.8961的平衡准确率，优于多数参赛模型
- 适合病理图像分析、医学影像诊断方向的研究者参考
准确分类有丝分裂图像对计算病理学至关重要，因其能反映癌症分级和患者预后。区分具有更高肿瘤侵袭性的异常有丝分裂图像（AMFs）与正常有丝分裂图像（NMFs）仍具挑战，因形态差异细微且类内变异大。任务还受器官、组织类型、扫描仪等域偏移影响，标注数据有限且类别严重不平衡。为应对MIDOG 2025挑战赛第2赛道的问题，我们提出基于轻量级ConvNeXt架构的解决方案，训练时使用全部可用数据集（AMi-Br、AtNorM-Br、AtNorM-MD、OMG-Octo）以扩大领域覆盖。通过包含弹性变换和染色特异性增强的病理专用增强流程提升鲁棒性，并采用平衡采样缓解类别不平衡。采用分组5折交叉验证策略确保评估可靠性。在初步排行榜上，模型取得0.8961的平衡准确率，位居前列。结果表明，广泛领域覆盖结合针对性增强策略是构建高精度、强泛化有丝分裂图像分类器的关键。
原文摘要 · Abstract (English)
Accurate mitotic figure classification is crucial in computational pathology, as mitotic activity informs cancer grading and patient prognosis. Distinguishing atypical mitotic figures (AMFs), which indicate higher tumor aggressiveness, from normal mitotic figures (NMFs) remains challenging due to subtle morphological differences and high intra-class variability. This task is further complicated by domain shifts, including variations in organ, tissue type, and scanner, as well as limited annotations and severe class imbalance. To address these challenges in Track 2 of the MIDOG 2025 Challenge, we propose a solution based on the lightweight ConvNeXt architecture, trained on all available datasets (AMi-Br, AtNorM-Br, AtNorM-MD, and OMG-Octo) to maximize domain coverage. Robustness is enhanced through a histopathology-specific augmentation pipeline, including elastic and stain-specific transformations, and balanced sampling to mitigate class imbalance. A grouped 5-fold cross-validation strategy ensures reliable evaluation. On the preliminary leaderboard, our model achieved a balanced accuracy of 0.8961, ranking among the top entries. These results highlight that broad domain exposure combined with targeted augmentation strategies is key to building accurate and generalizable mitotic figure classifiers.
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。