Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning
Abstract 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 mutat...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2021-09-01
|
Series: | npj Precision Oncology |
Online Access: | https://doi.org/10.1038/s41698-021-00225-9 |
_version_ | 1797641186470526976 |
---|---|
author | Hui Qu Mu Zhou Zhennan Yan He Wang Vinod K. Rustgi Shaoting Zhang Olivier Gevaert Dimitris N. Metaxas |
author_facet | Hui Qu Mu Zhou Zhennan Yan He Wang Vinod K. Rustgi Shaoting Zhang Olivier Gevaert Dimitris N. Metaxas |
author_sort | Hui Qu |
collection | DOAJ |
description | Abstract 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. |
first_indexed | 2024-03-11T13:41:58Z |
format | Article |
id | doaj.art-08b773bbbe0c42f8a2e65a6cbf18368a |
institution | Directory Open Access Journal |
issn | 2397-768X |
language | English |
last_indexed | 2024-03-11T13:41:58Z |
publishDate | 2021-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Precision Oncology |
spelling | doaj.art-08b773bbbe0c42f8a2e65a6cbf18368a2023-11-02T11:23:31ZengNature Portfolionpj Precision Oncology2397-768X2021-09-015111110.1038/s41698-021-00225-9Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learningHui Qu0Mu Zhou1Zhennan Yan2He Wang3Vinod K. Rustgi4Shaoting Zhang5Olivier Gevaert6Dimitris N. Metaxas7Department of Computer Science, Rutgers UniversitySensebrain ResearchSensebrain ResearchSchool of Medicine, Yale UniversityDepartment of Medicine, Rutgers Robert Wood Johnson Medical SchoolSenseTime Research and Shanghai AI LaboratoryStanford Center for Biomedical Informatics Research (BMIR), Department of Medicine, Stanford UniversityDepartment of Computer Science, Rutgers UniversityAbstract 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.https://doi.org/10.1038/s41698-021-00225-9 |
spellingShingle | Hui Qu Mu Zhou Zhennan Yan He Wang Vinod K. Rustgi Shaoting Zhang Olivier Gevaert Dimitris N. Metaxas Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning npj Precision Oncology |
title | Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
title_full | Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
title_fullStr | Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
title_full_unstemmed | Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
title_short | Genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
title_sort | genetic mutation and biological pathway prediction based on whole slide images in breast carcinoma using deep learning |
url | https://doi.org/10.1038/s41698-021-00225-9 |
work_keys_str_mv | AT huiqu geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT muzhou geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT zhennanyan geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT hewang geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT vinodkrustgi geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT shaotingzhang geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT oliviergevaert geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning AT dimitrisnmetaxas geneticmutationandbiologicalpathwaypredictionbasedonwholeslideimagesinbreastcarcinomausingdeeplearning |