用合成数据平衡类别，对病理细胞分类效果有限。
Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition
- 对比真实数据与合成数据训练模型，评估增广效果。
- 两种模型平均AUROC均达95%，但合成数据未带来稳定提升。
- 领域预训练模型更鲁棒，ImageNet模型峰值更高，适合临床应用。
MIDOG 2025挑战赛在前期有丝分裂检测基础上新增了非典型有丝分裂分类任务，旨在区分组织病理图像中的正常与非典型有丝分裂，该问题具有显著类别不平衡（9408个正常 vs. 1741个非典型）和跨域特性。我们研究了两种互补骨干网络：(i) ImageNet预训练的ConvNeXt-Small，(ii) Lunit基于自监督学习在病理领域训练的ViT。为缓解强类别偏倚，我们通过合成额外非典型样本以逼近类别平衡，并比较仅使用真实数据与真实+合成数据训练的模型表现。五折交叉验证显示，两种骨干网络均达到优异性能（平均AUROC约95%），其中ConvNeXt略高，而Lunit表现出更强的折叠间稳定性。然而，合成数据平衡并未带来一致改进。在主办方预先公布的隐藏测试集（设计为分布外调试子集）上，ConvNeXt取得最高AUROC（95.4%），Lunit在平衡准确率上仍具竞争力。结果表明，ImageNet与领域预训练骨干均可用于非典型有丝分裂分类，前者可达更高峰值，后者更具鲁棒性；而简单的合成数据平衡策略效益有限。完整隐藏测试集结果将在挑战结束后公布。
原文摘要 · Abstract (English)
The MIDOG 2025 challenge extends prior work on mitotic figure detection by introducing a new Track 2 on atypical mitosis classification. This task aims to distinguish normal from atypical mitotic figures in histopathology images, a clinically relevant but highly imbalanced and cross-domain problem. We investigated two complementary backbones: (i) ConvNeXt-Small, pretrained on ImageNet, and (ii) a histopathology-specific ViT from Lunit trained via self-supervision. To address the strong prevalence imbalance (9408 normal vs. 1741 atypical), we synthesized additional atypical examples to approximate class balance and compared models trained with real-only vs. real+synthetic data. Using five-fold cross-validation, both backbones reached strong performance (mean AUROC approximately 95 percent), with ConvNeXt achieving slightly higher peaks while Lunit exhibited greater fold-to-fold stability. Synthetic balancing, however, did not lead to consistent improvements. On the organizers' preliminary hidden test set, explicitly designed as an out-of-distribution debug subset, ConvNeXt attained the highest AUROC (95.4 percent), whereas Lunit remained competitive on balanced accuracy. These findings suggest that both ImageNet and domain-pretrained backbones are viable for atypical mitosis classification, with domain-pretraining conferring robustness and ImageNet pretraining reaching higher peaks, while naive synthetic balancing has limited benefit. Full hidden test set results will be reported upon challenge completion.
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。