Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning
Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning
复制标题
DOI：
10.1038/s41591-018-0177-5
复制
发表时间：
2018-10-01
期刊：
影响因子：
82.9
通讯作者：
Tsirigos, Aristotelis
中科院分区：
文献类型：
--
作者：
Coudray, Nicolas;Ocampo, Paolo Santiago;Tsirigos, Aristotelis
组织病理学切片的目视检查是病理学家评估肺部肿瘤的阶段、类型和亚型的主要方法之一。腺癌 (LUAD) 和鳞状细胞癌 (LUSC) 是肺癌最常见的亚型，它们的区别需要经验丰富的病理学家进行目视检查。在这项研究中，我们对从癌症基因组图谱获得的全幻灯片图像训练了深度卷积神经网络 (inception v3)，以准确、自动地将它们分类为 LUAD、LUSC 或正常肺组织。我们的方法的性能与病理学家的方法相当，平均曲线下面积 (AUC) 为 0.97。我们的模型在冷冻组织、福尔马林固定石蜡包埋组织和活检的独立数据集上进行了验证。此外，我们训练网络来预测 LUAD 中 10 个最常见的突变基因。我们发现其中的 6 个——STK11、EGFR、FAT1、SETBP1、KRAS 和 TP53——可以从病理图像中预测，在保留群体中测量的 AUC 为 0.733 至 0.856。这些发现表明深度学习模型可以帮助病理学家检测癌症亚型或基因突变。我们的方法可以应用于任何癌症类型，代码可在 https://github.com/ncoudray/DeepPATH 获取。
Visual inspection of histopathology slides is one of the main methods used by pathologists to assess the stage, type and subtype of lung tumors. Adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) are the most prevalent subtypes of lung cancer, and their distinction requires visual inspection by an experienced pathologist. In this study, we trained a deep convolutional neural network (inception v3) on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue. The performance of our method is comparable to that of pathologists, with an average area under the curve (AUC) of 0.97. Our model was validated on independent datasets of frozen tissues, formalin-fixed paraffin-embedded tissues and biopsies. Furthermore, we trained the network to predict the ten most commonly mutated genes in LUAD. We found that six of them-STK11, EGFR, FAT1, SETBP1, KRAS and TP53-can be predicted from pathology images, with AUCs from 0.733 to 0.856 as measured on a held-out population. These findings suggest that deep-learning models can assist pathologists in the detection of cancer subtype or gene mutations. Our approach can be applied to any cancer type, and the code is available at https://github.com/ncoudray/DeepPATH.