通过生成伪子袋与课程对比学习，提升病理切片不平衡多分类性能。
Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Image
- 基于特征分布生成伪子袋，挖掘切片冗余信息。
- 在三组数据上平均提升4.39分F1值，优于现有方法。
- 适合病理图像分析、小样本多分类任务的研究者。
病理计算显著提升了病理科医生的工作效率与诊断决策能力。尽管辅助诊断系统在全切片图像（WSI）分析中已展现重要价值，但样本不平衡下的多分类问题仍是难题。为此，我们提出通过生成与原始WSI特征分布相似的子袋来学习细粒度信息。同时，采用伪子袋生成算法，充分利用WSI中的丰富冗余信息，实现不平衡多分类任务的高效训练。此外，引入基于亲和性的样本选择与课程对比学习策略，增强模型表征学习的稳定性。不同于以往方法，本框架从学习袋级表示转向理解并利用多实例袋的特征分布。在三个数据集上的实验表明，该方法在肿瘤分类与淋巴结转移检测任务中均取得显著提升，平均F1得分比次优方法高出4.39点，验证了其优越性。
原文摘要 · Abstract (English)
Pathology computing has dramatically improved pathologists' workflow and diagnostic decision-making processes. Although computer-aided diagnostic systems have shown considerable value in whole slide image (WSI) analysis, the problem of multi-classification under sample imbalance remains an intractable challenge. To address this, we propose learning fine-grained information by generating sub-bags with feature distributions similar to the original WSIs. Additionally, we utilize a pseudo-bag generation algorithm to further leverage the abundant and redundant information in WSIs, allowing efficient training in unbalanced-sample multi-classification tasks. Furthermore, we introduce an affinity-based sample selection and curriculum contrastive learning strategy to enhance the stability of model representation learning. Unlike previous approaches, our framework transitions from learning bag-level representations to understanding and exploiting the feature distribution of multi-instance bags. Our method demonstrates significant performance improvements on three datasets, including tumor classification and lymph node metastasis. On average, it achieves a 4.39-point improvement in F1 score compared to the second-best method across the three tasks, underscoring its superior performance.
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。