基于深度学习的间皮瘤分类可提高对患者预后的预测，这一成果由美国Owkin 公司Thomas Clozel团队取得。2019年10月7日，《自然—医学》在线发表了这一成果。
研究人员开发了一种基于深度卷积神经网络的新方法，称为MesoNet，可以从完整切片数字化图像准确预测间皮瘤患者的整体生存，而无需任何病理学家提供的局部注释区域。研究人员通过法国MESOBANK的内部验证队列和癌症基因组图谱（TCGA）的独立队列对MesoNet进行了验证。研究人员还证明了该模型在预测患者生存率方面比使用当前病理学方法更为准确。此外，与经典的黑盒深度学习方法不同，MesoNet可以识别有助于患者预后的区域。令人惊讶地，研究人员发现这些区域主要位于基质中，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出预测患者生存的新特征，并有可能导致新生物标志物的发现。
据悉，恶性间皮瘤（MM）是一种主要根据组织学标准诊断的侵袭性癌症。2015年世界卫生组织分类将间皮瘤肿瘤分为三种组织学类型：上皮样、双相样和肉瘤样MM。MM是一种高度复杂的异质性疾病，使其诊断和组织学分型变得困难，导致患者护理以及治疗方案的决策欠佳。
附：英文原文
Title: Deep learning-based classification of mesothelioma improves prediction of patient outcome
Author: Pierre Courtiol, Charles Maussion, Matahi Moarii, Elodie Pronier, Samuel Pilcer, Meriem Sefta, Pierre Manceron, Sylvain Toldo, Mikhail Zaslavskiy, Nolwenn Le Stang, Nicolas Girard, Olivier Elemento, Andrew G. Nicholson, Jean-Yves Blay, Franoise Galateau-Sall, Gilles Wainrib, Thomas Clozel
Issue&Volume: 2019-10-07
Abstract: Malignant mesothelioma (MM) is an aggressive cancer primarily diagnosed on the basis of histological criteria1. 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 modalities2. Here we have developed a new approachbased on deep convolutional neural networkscalled 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. Deep convolutional neural networks predict survival of mesothelioma patients and identify histological features associated with outcome that transcend current histological classifications.
DOI: 10.1038/s41591-019-0583-3
Source:https://www.nature.com/articles/s41591-019-0583-3
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：87.241
官方网址：https://www.nature.com/nm/
投稿链接：https://mts-nmed.nature.com/cgi-bin/main.plex
本期文章：《自然—医学》：Online/在线发表
