使用深度学习分类并预测NSCLC组织病理学图像

SCI

   3 October 2018

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

• Coudray Nicolas,Ocampo Paolo Santiago,Sakellaropoulos Theodore et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning.[J] .Nat. Med., 2018.

• Nicolas Coudray, Paolo Santiago Ocampo. *e-mail: [e-mail];[e-mail]
  

Visual inspection of histopathology slides is one of the main methods used by pathologists to assess the stage, type and subtype of lung tumors.

组织病理学载玻片的目视检查是病理学家用于评估肺肿瘤的阶段，类型和亚型的主要方法之一。

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.

腺癌（LUAD）和鳞状细胞癌（LUSC）是最常见的肺癌亚型，它们的需要经验丰富的病理学家进行目视检查来区分。

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.

在这项研究中，我们在从癌症基因组图谱获得的全幻灯片图像上训练了一个深度卷积神经网络（初始v3），以准确和自动地将它们分类为LUAD，LUSC或正常肺组织。

The performance of our method is comparable to that of pathologists, with an average area under the curve (AUC) of 0.97.

我们的方法的表现与病理学家的表现相当，曲线下的平均面积（AUC）为0.97。

Our model was validated on independent datasets of frozen tissues, formalin-fixed paraffin-embedded tissues and biopsies.

我们的模型在冷冻组织，福尔马林固定的石蜡包埋组织和活组织检查的独立数据集上得到验证。

Furthermore, we trained the network to predict the ten most commonly mutated genes in LUAD.

此外，我们训练网络预测LUAD中十个最常见的突变基因。

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.

我们发现其中6个-STK11，EGFR，FAT1，SETBP1，KRAS和TP53-可以从病理图像中预测，在保持的人群中测量的AUC为0.733-0.856。

These findings suggest that deep-learning models can assist pathologists in the detection of cancer subtype or gene mutations.

这些研究结果表明，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。

Our approach can be applied to any cancer type, and the code is available at https://github.com/ncoudray/DeepPATH

我们的方法可以应用于任何癌症类型，代码可以通过以下网址获得：

https://github.com/ncoudray/DeepPATH

喜欢SCI天天读的理由

陪您一起学习SCI医学论文

每天5分钟，让自己的英语牛逼起来

特殊福利让您惊喜连连