Deep learning-based classification of mesothelioma improves prediction of patient outcome
Deep learning-based classification of mesothelioma improves prediction of patient outcome
复制标题
DOI：
10.1038/s41591-019-0583-3
复制
发表时间：
2019-10-01
期刊：
影响因子：
82.9
通讯作者：
Clozel, Thomas
中科院分区：
文献类型：
--
作者：
Courtiol, Pierre;Maussion, Charles;Clozel, Thomas
恶性间皮瘤（MM）是一种侵袭性癌症，主要根据组织学标准进行诊断（1）。2015年世界卫生组织分类将间皮瘤肿瘤细分为三种组织学类型：上皮样，双相和肉瘤样MM MM MM是一种高度复杂和异质性的疾病，使其诊断和组织学分型困难，并导致次优的患者护理和治疗方式的决定（2）。在这里，我们开发了一种新的方法-基于深度卷积神经网络-称为MesoNet，可以从全切片数字化图像中准确预测间皮瘤患者的总体生存率，而无需任何病理学家提供的本地注释区域。我们在法国MESOBANK的内部验证队列和癌症基因组图谱（TCGA）的独立队列上验证了MesoNet。我们还证明了该模型在预测患者生存率方面比使用当前的病理学实践更准确。此外，与经典的黑盒深度学习方法不同，MesoNet识别出有助于患者预后预测的区域。引人注目的是，我们发现这些区域主要位于间质中，并且是与炎症、细胞多样性和空泡化相关的组织学特征。这些发现表明，深度学习模型可以识别预测患者生存的新特征，并可能导致新的生物标志物发现。
Malignant mesothelioma (MM) is an aggressive cancer primarily diagnosed on the basis of histological criteria(1). The 2015 World Health Organization classification subdivides mesothelioma tumors into three histological types: epithelioid, biphasic and sarcomatoid MM. MM is a highly complex and heterogeneous disease, rendering its diagnosis and histological typing difficult and leading to suboptimal patient care and decisions regarding treatment modalities(2). Here we have developed a new approach-based on deep convolutional neural networks-called MesoNet to accurately predict the overall survival of mesothelioma patients from whole-slide digitized images, without any pathologist-provided locally annotated regions. We validated MesoNet on both an internal validation cohort from the French MESOBANK and an independent cohort from The Cancer Genome Atlas (TCGA). We also demonstrated that the model was more accurate in predicting patient survival than using current pathology practices. Furthermore, unlike classical black-box deep learning methods, MesoNet identified regions contributing to patient outcome prediction. Strikingly, we found that these regions are mainly located in the stroma and are histological features associated with inflammation, cellular diversity and vacuolization. These findings suggest that deep learning models can identify new features predictive of patient survival and potentially lead to new biomarker discoveries.