30种领域泛化算法在病理图像上实测，发现自监督和染色增强最有效。
Benchmarking Domain Generalization Algorithms in Computational Pathology
- 用7560次交叉验证系统评估30种领域泛化方法
- 自监督学习与染色增强在三类任务中持续领先
- 新发布泛癌肿瘤检测数据集HISTOPANTUM供后续研究
深度学习在计算病理学（CPath）任务中展现出巨大潜力，但其在未见数据上的表现常因域偏移而下降。解决此问题需依赖领域泛化（DG）算法，然而目前尚缺乏对CPath场景下DG算法的系统性评估。本研究通过7560次交叉验证，系统评测了30种DG算法在3个难度不同的CPath任务上的表现。实验采用统一且稳健的平台，融合模态特定技术与近期进展如预训练基础模型。大规模交叉验证揭示了不同DG策略的相对性能。结果表明，自监督学习与染色增强始终优于其他方法，凸显预训练模型与数据增强的潜力。此外，本文引入新的泛癌肿瘤检测数据集HISTOPANTUM，为未来研究提供基准。该工作为研究者选择合适的DG方法提供了重要参考。
原文摘要 · Abstract (English)
Deep learning models have shown immense promise in computational pathology (CPath) tasks, but their performance often suffers when applied to unseen data due to domain shifts. Addressing this requires domain generalization (DG) algorithms. However, a systematic evaluation of DG algorithms in the CPath context is lacking. This study aims to benchmark the effectiveness of 30 DG algorithms on 3 CPath tasks of varying difficulty through 7,560 cross-validation runs. We evaluate these algorithms using a unified and robust platform, incorporating modality-specific techniques and recent advances like pretrained foundation models. Our extensive cross-validation experiments provide insights into the relative performance of various DG strategies. We observe that self-supervised learning and stain augmentation consistently outperform other methods, highlighting the potential of pretrained models and data augmentation. Furthermore, we introduce a new pan-cancer tumor detection dataset (HISTOPANTUM) as a benchmark for future research. This study offers valuable guidance to researchers in selecting appropriate DG approaches for CPath tasks.
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。