A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images
Summary: The chromosome instability (CIN) is one of the hallmarks of cancer and is closely related to tumor metastasis. However, the sheer size and resolution of histopathology whole-slide images (WSIs) already challenges the capabilities of computational pathology. In this study, we propose a corre...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004223009513 |
| _version_ | 1797818660015833088 |
|---|---|
| author | Liangliang Liu Ying Wang Jing Chang Pei Zhang Shufeng Xiong Hebing Liu |
| author_facet | Liangliang Liu Ying Wang Jing Chang Pei Zhang Shufeng Xiong Hebing Liu |
| author_sort | Liangliang Liu |
| collection | DOAJ |
| description | Summary: The chromosome instability (CIN) is one of the hallmarks of cancer and is closely related to tumor metastasis. However, the sheer size and resolution of histopathology whole-slide images (WSIs) already challenges the capabilities of computational pathology. In this study, we propose a correlation graph attention network (MLP-GAT) that can construct graphs for classifying multi-type CINs from the WSIs of breast cancer. We construct a WSIs dataset of breast cancer from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA). Extensive experiments show that MLP-GAT far outperforms accepted state-of-the-art methods and demonstrate the advantages of the constructed graph networks for analyzing WSI data. The visualization shows the difference among the tiles in a WSI. Furthermore, the generalization performance of the proposed method was verified on the stomach cancer. This study provides guidance for studying the relationship between CIN and cancer from the perspective of image phenotype. |
| first_indexed | 2024-03-13T09:11:12Z |
| format | Article |
| id | doaj.art-ac29ad90a39a4ac1bccb45245c11d107 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-13T09:11:12Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-ac29ad90a39a4ac1bccb45245c11d1072023-05-27T04:26:23ZengElsevieriScience2589-00422023-06-01266106874A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide imagesLiangliang Liu0Ying Wang1Jing Chang2Pei Zhang3Shufeng Xiong4Hebing Liu5College of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. China; Corresponding authorCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. China; Corresponding authorSummary: The chromosome instability (CIN) is one of the hallmarks of cancer and is closely related to tumor metastasis. However, the sheer size and resolution of histopathology whole-slide images (WSIs) already challenges the capabilities of computational pathology. In this study, we propose a correlation graph attention network (MLP-GAT) that can construct graphs for classifying multi-type CINs from the WSIs of breast cancer. We construct a WSIs dataset of breast cancer from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA). Extensive experiments show that MLP-GAT far outperforms accepted state-of-the-art methods and demonstrate the advantages of the constructed graph networks for analyzing WSI data. The visualization shows the difference among the tiles in a WSI. Furthermore, the generalization performance of the proposed method was verified on the stomach cancer. This study provides guidance for studying the relationship between CIN and cancer from the perspective of image phenotype.http://www.sciencedirect.com/science/article/pii/S2589004223009513HistologyInterconnection networkMedical imaging |
| spellingShingle | Liangliang Liu Ying Wang Jing Chang Pei Zhang Shufeng Xiong Hebing Liu A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images iScience Histology Interconnection network Medical imaging |
| title | A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images |
| title_full | A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images |
| title_fullStr | A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images |
| title_full_unstemmed | A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images |
| title_short | A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images |
| title_sort | correlation graph attention network for classifying chromosomal instabilities from histopathology whole slide images |
| topic | Histology Interconnection network Medical imaging |
| url | http://www.sciencedirect.com/science/article/pii/S2589004223009513 |
| work_keys_str_mv | AT liangliangliu acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT yingwang acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT jingchang acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT peizhang acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT shufengxiong acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT hebingliu acorrelationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT liangliangliu correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT yingwang correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT jingchang correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT peizhang correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT shufengxiong correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages AT hebingliu correlationgraphattentionnetworkforclassifyingchromosomalinstabilitiesfromhistopathologywholeslideimages |