响马读paper

一个要求成员每月至少读一篇文献并打卡的学术交流社群

2020, Nature Communications. DOI: 10.1038/s41467-020-17678-4 PMID: 32747659 PMCID: PMC7400514
A deep learning model to predict RNA-Seq expression of tumours from whole slide images
Benoît Schmauch, Alberto Romagnoni, Elodie Pronier, Charlie Saillard, Pascale Maillé, Julien Calderaro, Aurélie Kamoun, Meriem Sefta, Sylvain Toldo, Mikhail Zaslavskiy, Thomas Clozel, Matahi Moarii, Pierre Courtiol, Gilles Wainrib
Abstract:
Deep learning methods for digital pathology analysis are an effective way to address multiple clinical questions, from diagnosis to prediction of treatment outcomes. These methods have also been used to predict gene mutations from pathology images, but no comprehensive evaluation of their potential for extracting molecular features from histology slides has yet been performed. We show that HE2RNA, a model based on the integration of multiple data modes, can be trained to systematically predict RNA-Seq profiles from whole-slide images alone, without expert annotation. Through its interpretable design, HE2RNA provides virtual spatialization of gene expression, as validated by CD3- and CD20-staining on an independent dataset. The transcriptomic representation learned by HE2RNA can also be transferred on other datasets, even of small size, to increase prediction performance for specific molecular phenotypes. We illustrate the use of this approach in clinical diagnosis purposes such as the identification of tumors with microsatellite instability.
2022-04-30 21:26:00
#paper https://doi.org/10.1038/s41467-020-17678-4 A deep learning model to predict RNA-Seq expression of tumours from whole slide images. Nature Comm (2020) 深度学习模型(CNN)在医学影像中有广泛的应用,最近也有研究指出可以通过病理图片来预测DNA突变和突变数,但是还没有研究关注过是否可以通过病理图片来预测基因表达,这篇文章填补了这部分空白。文章提出了一种基于多任务弱监督的深度学习模型 HE2RNA, 使用TCGA不同癌症类型数据(WSI + RNA-seq)进行训练,发现能准确预测基因的数量主要取决于训练数据集的大小,对这些被准确预测的基因进行富集分析,发现他们集中在免疫和T细胞调控,细胞周期,和癌症hallmark的通路上。最后文章还展现HE2RNA可以用于基因表达的空间可视化(预测基因在slide上表达)和提高MSI预测效果
TOP