Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering
Abstract Deep learning models are increasingly being used to interpret whole‐slide images (WSIs) in digital pathology and to predict genetic mutations. Currently, it is commonly assumed that tumor regions have most of the predictive power. However, it is reasonable to assume that other tissues from...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | The Journal of Pathology: Clinical Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cjp2.302 |
| _version_ | 1811178385126195200 |
|---|---|
| author | Zihan Chen Xingyu Li Miaomiao Yang Hong Zhang Xu Steven Xu |
| author_facet | Zihan Chen Xingyu Li Miaomiao Yang Hong Zhang Xu Steven Xu |
| author_sort | Zihan Chen |
| collection | DOAJ |
| description | Abstract Deep learning models are increasingly being used to interpret whole‐slide images (WSIs) in digital pathology and to predict genetic mutations. Currently, it is commonly assumed that tumor regions have most of the predictive power. However, it is reasonable to assume that other tissues from the tumor microenvironment may also provide important predictive information. In this paper, we propose an unsupervised clustering‐based multiple‐instance deep learning model for the prediction of genetic mutations using WSIs of three cancer types obtained from The Cancer Genome Atlas. Our proposed model facilitates the identification of spatial regions related to specific gene mutations and exclusion of patches that lack predictive information through the use of unsupervised clustering. This results in a more accurate prediction of gene mutations when compared with models using all image patches on WSIs and two recently published algorithms for all three different cancer types evaluated in this study. In addition, our study validates the hypothesis that the prediction of gene mutations solely based on tumor regions on WSI slides may not always provide the best performance. Other tissue types in the tumor microenvironment could provide a better prediction ability than tumor tissues alone. These results highlight the heterogeneity in the tumor microenvironment and the importance of identification of predictive image patches in digital pathology prediction tasks. |
| first_indexed | 2024-04-11T06:17:15Z |
| format | Article |
| id | doaj.art-41e9159432ab4ee2afb49f3a95e5d01d |
| institution | Directory Open Access Journal |
| issn | 2056-4538 |
| language | English |
| last_indexed | 2024-04-11T06:17:15Z |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Pathology: Clinical Research |
| spelling | doaj.art-41e9159432ab4ee2afb49f3a95e5d01d2022-12-22T04:41:01ZengWileyThe Journal of Pathology: Clinical Research2056-45382023-01-019131710.1002/cjp2.302Optimization of deep learning models for the prediction of gene mutations using unsupervised clusteringZihan Chen0Xingyu Li1Miaomiao Yang2Hong Zhang3Xu Steven Xu4School of Data Science University of Science and Technology of China Hefei PR ChinaDepartment of Statistics and Finance, School of Management University of Science and Technology of China Hefei PR ChinaClinical Pathology Center The Fourth Affiliated Hospital of Anhui Medical University Hefei PR ChinaDepartment of Statistics and Finance, School of Management University of Science and Technology of China Hefei PR ChinaClinical Pharmacology and Quantitative Science Genmab Inc. Princeton NJ USAAbstract Deep learning models are increasingly being used to interpret whole‐slide images (WSIs) in digital pathology and to predict genetic mutations. Currently, it is commonly assumed that tumor regions have most of the predictive power. However, it is reasonable to assume that other tissues from the tumor microenvironment may also provide important predictive information. In this paper, we propose an unsupervised clustering‐based multiple‐instance deep learning model for the prediction of genetic mutations using WSIs of three cancer types obtained from The Cancer Genome Atlas. Our proposed model facilitates the identification of spatial regions related to specific gene mutations and exclusion of patches that lack predictive information through the use of unsupervised clustering. This results in a more accurate prediction of gene mutations when compared with models using all image patches on WSIs and two recently published algorithms for all three different cancer types evaluated in this study. In addition, our study validates the hypothesis that the prediction of gene mutations solely based on tumor regions on WSI slides may not always provide the best performance. Other tissue types in the tumor microenvironment could provide a better prediction ability than tumor tissues alone. These results highlight the heterogeneity in the tumor microenvironment and the importance of identification of predictive image patches in digital pathology prediction tasks.https://doi.org/10.1002/cjp2.302deep learningwhole‐slide imagesH&E imagegene mutationunsupervised clustering |
| spellingShingle | Zihan Chen Xingyu Li Miaomiao Yang Hong Zhang Xu Steven Xu Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering The Journal of Pathology: Clinical Research deep learning whole‐slide images H&E image gene mutation unsupervised clustering |
| title | Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| title_full | Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| title_fullStr | Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| title_full_unstemmed | Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| title_short | Optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| title_sort | optimization of deep learning models for the prediction of gene mutations using unsupervised clustering |
| topic | deep learning whole‐slide images H&E image gene mutation unsupervised clustering |
| url | https://doi.org/10.1002/cjp2.302 |
| work_keys_str_mv | AT zihanchen optimizationofdeeplearningmodelsforthepredictionofgenemutationsusingunsupervisedclustering AT xingyuli optimizationofdeeplearningmodelsforthepredictionofgenemutationsusingunsupervisedclustering AT miaomiaoyang optimizationofdeeplearningmodelsforthepredictionofgenemutationsusingunsupervisedclustering AT hongzhang optimizationofdeeplearningmodelsforthepredictionofgenemutationsusingunsupervisedclustering AT xustevenxu optimizationofdeeplearningmodelsforthepredictionofgenemutationsusingunsupervisedclustering |