Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
复制标题
DOI：
10.1038/s41591-019-0508-1
复制
发表时间：
2019-08-01
期刊：
影响因子：
82.9
通讯作者：
Fuchs, Thomas J.
中科院分区：
文献类型：
--
作者：
Campanella, Gabriele;Hanna, Matthew G.;Fuchs, Thomas J.
病理学决策支持系统的开发及其在临床实践中的部署受到了大量手动注释数据集的阻碍。为了克服这个问题，我们提出了一个基于多实例学习的深度学习系统，该系统仅使用报告的诊断作为训练标签，从而避免了昂贵且耗时的像素级手动注释。我们在来自15，187名患者的44，732张完整切片图像的数据集上大规模评估了该框架，而没有任何形式的数据管理。对前列腺癌、基底细胞癌和乳腺癌腋窝淋巴结转移的测试结果显示，所有癌症类型的曲线下面积均高于0.98。它的临床应用将允许病理学家排除65-75%的载玻片，同时保持100%的灵敏度。我们的研究结果表明，该系统能够以前所未有的规模训练准确的分类模型，为在临床实践中部署计算决策支持系统奠定了基础。
The development of decision support systems for pathology and their deployment in clinical practice have been hindered by the need for large manually annotated datasets. To overcome this problem, we present a multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations. We evaluated this framework at scale on a dataset of 44,732 whole slide images from 15,187 patients without any form of data curation. Tests on prostate cancer, basal cell carcinoma and breast cancer metastases to axillary lymph nodes resulted in areas under the curve above 0.98 for all cancer types. Its clinical application would allow pathologists to exclude 65-75% of slides while retaining 100% sensitivity. Our results show that this system has the ability to train accurate classification models at unprecedented scale, laying the foundation for the deployment of computational decision support systems in clinical practice.