结合组织病理学专属增强的ConvNeXt用于有丝分裂象分类
ConvNeXt with Histopathology-Specific Augmentations for Mitotic Figure Classification
AI总结：
针对MIDOG 2025挑战赛中有丝分裂象分类的域偏移、类别不平衡等挑战，提出结合组织病理学专属增强的轻量ConvNeXt方案，多数据集训练结合平衡采样与分组5折验证，初步平衡准确率达0.8961，验证了广域覆盖加针对性增强的有效性。
摘要：
准确的有丝分裂象分类在计算病理学中至关重要，因为有丝分裂活性可为癌症分级和患者预后提供依据。由于形态差异细微且类内变异性高，将提示肿瘤侵袭性更强的非典型有丝分裂象（AMFs）与正常有丝分裂象（NMFs）区分开来仍具挑战性。器官、组织类型和扫描仪的差异带来的域偏移，以及标注有限和严重的类别不平衡，进一步增加了该任务的难度。为应对MIDOG 2025挑战赛赛道2的这些挑战，我们提出了一种基于轻量级ConvNeXt架构的解决方案，使用所有可用数据集（AMi-Br、AtNorM-Br、AtNorM-MD和OMG-Octo）进行训练以最大化域覆盖范围。我们通过组织病理学专属的增强流程（包括弹性变换和染色专属变换）以及平衡采样来缓解类别不平衡，从而提升模型鲁棒性。分组5折交叉验证策略确保了评估的可靠性。在初步排行榜上，我们的模型取得了0.8961的平衡准确率，位居参赛作品前列。这些结果表明，广泛的域暴露结合针对性的增强策略，是构建准确且泛化性强的有丝分裂象分类器的关键。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
