Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning.
Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning.
复制标题
基于深度学习的乳腺癌全切片图像的基因突变和生物学通路预测。
DOI：
10.1038/s41698-021-00225-9
复制
发表时间：
2021-09-23
影响因子：
7.9
通讯作者：
Metaxas DN
中科院分区：
文献类型：
--
作者：
Qu H;Zhou M;Yan Z;Wang H;Rustgi VK;Zhang S;Gevaert O;Metaxas DN
乳腺癌是全世界妇女中最常见的癌症，由一组异质性亚型疾病组成。全切片图像（WSIs）可以捕获细胞水平的异质性，并且被病理学家常规用于癌症诊断。然而，与靶向治疗相关的关键驱动基因突变是通过基因组分析（如高通量分子谱分析）鉴定的。在这项研究中，我们开发了一个深度学习模型来预测直接来自WSI的基因突变和生物途径活动。我们的研究为突变及其相关途径之间的WSI视觉相互作用提供了独特的见解，使头对头的比较能够加强我们的主要发现。使用来自Genomic Data Commons Database的组织病理学图像，我们的模型可以预测六个重要基因的点突变（AUC 0.68-0.85）和另外六个基因的拷贝数改变（AUC 0.69-0.79）。此外，训练的模型可以预测十个典型途径中的三个的活性（AUC 0.65-0.79）。接下来，我们可视化了WSI中肿瘤瓦片的权重图，以通过自注意机制理解深度学习模型的决策过程。我们进一步验证了与转移性乳腺癌相关的肝癌和肺癌模型。我们的研究结果为乳腺癌患者的病理图像特征，分子结果和靶向治疗之间的关联提供了见解。
Breast carcinoma is the most common cancer among women worldwide that consists of a heterogeneous group of subtype diseases. The whole-slide images (WSIs) can capture the cell-level heterogeneity, and are routinely used for cancer diagnosis by pathologists. However, key driver genetic mutations related to targeted therapies are identified by genomic analysis like high-throughput molecular profiling. In this study, we develop a deep-learning model to predict the genetic mutations and biological pathway activities directly from WSIs. Our study offers unique insights into WSI visual interactions between mutation and its related pathway, enabling a head-to-head comparison to reinforce our major findings. Using the histopathology images from the Genomic Data Commons Database, our model can predict the point mutations of six important genes (AUC 0.68–0.85) and copy number alteration of another six genes (AUC 0.69–0.79). Additionally, the trained models can predict the activities of three out of ten canonical pathways (AUC 0.65–0.79). Next, we visualized the weight maps of tumor tiles in WSI to understand the decision-making process of deep-learning models via a self-attention mechanism. We further validated our models on liver and lung cancers that are related to metastatic breast cancer. Our results provide insights into the association between pathological image features, molecular outcomes, and targeted therapies for breast cancer patients.
登录
查看更多内容
影响因子：
--
作者：
Mogi A;Kuwano H
通讯作者：
Kuwano H
影响因子：
22.7
作者：
Kather JN;Heij LR;Grabsch HI;Loeffler C;Echle A;Muti HS;Krause J;Niehues JM;Sommer KA;Bankhead P;Kooreman LF;Schulte JJ;Cipriani NA;Buelow RD;Boor P;Ortiz-Brüchle NN;Hanby AM;Speirs V;Kochanny S;Patnaik A;Srisuwananukorn A;Brenner H;Hoffmeister M;van den Brandt PA;Jäger D;Trautwein C;Pearson AT;Luedde T
通讯作者：
Luedde T
影响因子：
6.8
作者：
Feng Y;Spezia M;Huang S;Yuan C;Zeng Z;Zhang L;Ji X;Liu W;Huang B;Luo W;Liu B;Lei Y;Du S;Vuppalapati A;Luu HH;Haydon RC;He TC;Ren G
通讯作者：
Ren G
影响因子：
--
作者：
Anand D;Kurian NC;Dhage S;Kumar N;Rane S;Gann PH;Sethi A
通讯作者：
Sethi A
DOI：
10.1097/jto.0b013e31826aed28
发表时间：
2012-12
期刊：
Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer
影响因子：
--
作者：
Heist RS;Mino-Kenudson M;Sequist LV;Tammireddy S;Morrissey L;Christiani DC;Engelman JA;Iafrate AJ
通讯作者：
Iafrate AJ