当前位置:科学网首页 > 小柯机器人 >详情
人工智能助力病理诊断
作者:小柯机器人 发布时间:2019/8/13 13:16:10

近日,美国纪念斯隆-凯特琳癌症中心的Thomas J. Fuchs研究组,开发出了利用完整切片图像进行临床级计算病理学的深度学习系统。该研究于2019年8月发表于国际一流学术期刊《自然—医学》上。

据了解,由于需要大量手工注释数据集,病理学决策支持系统的开发及其在临床实践中的应用受到了阻碍。

为了克服这个问题,研究人员提出了一个基于多实例学习的深度学习系统,该系统仅使用诊断报告作为标签进行训练,从而避免了昂贵且耗时的逐像素手动注释。研究人员在来自15187名没有任何形式数据管理患者的44732个完整切片图像的数据集上大规模地评估了该框架。对前列腺癌、基底细胞癌和腋窝淋巴结转移乳腺癌的测试达到所有癌症类型的曲线下面积均高于0.98。其临床应用将使病理学家排除65-75%的切片,同时保持100%的灵敏度。

这项研究表明,该系统能够以前所未有的规模训练准确的分类模型,为临床实践中计算决策支持系统的应用奠定了基础。

附:英文原文

Title: Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

Author: Gabriele Campanella, Matthew G. Hanna, Luke Geneslaw, Allen Miraflor, Vitor Werneck Krauss Silva, Klaus J. Busam, Edi Brogi, Victor E. Reuter, David S. Klimstra, Thomas J. Fuchs

Issue&Volume: Volume 25 Issue 8, August 2019

Abstract: 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 6575% 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.

DOI: 10.1038/s41591-019-0508-1

Source:https://www.nature.com/articles/s41591-019-0508-1

期刊信息

Nature Medicine:《自然—医学》,创刊于1995年。隶属于施普林格·自然出版集团,最新IF:30.641
官方网址:https://www.nature.com/nm/
投稿链接:https://mts-nmed.nature.com/cgi-bin/main.plex