Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study
BackgroundLung cancer is the leading cause of cancer-related mortality, and accurate prediction of patient survival can aid treatment planning and potentially improve outcomes. In this study, we proposed an automated system capable of lung segmentation and survival prediction using graph convolution...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.868186/full |
| _version_ | 1818048270986903552 |
|---|---|
| author | Jie Lian Yonghao Long Fan Huang Kei Shing Ng Faith M. Y. Lee David C. L. Lam Benjamin X. L. Fang Qi Dou Varut Vardhanabhuti |
| author_facet | Jie Lian Yonghao Long Fan Huang Kei Shing Ng Faith M. Y. Lee David C. L. Lam Benjamin X. L. Fang Qi Dou Varut Vardhanabhuti |
| author_sort | Jie Lian |
| collection | DOAJ |
| description | BackgroundLung cancer is the leading cause of cancer-related mortality, and accurate prediction of patient survival can aid treatment planning and potentially improve outcomes. In this study, we proposed an automated system capable of lung segmentation and survival prediction using graph convolution neural network (GCN) with CT data in non-small cell lung cancer (NSCLC) patients.MethodsIn this retrospective study, we segmented 10 parts of the lung CT images and built individual lung graphs as inputs to train a GCN model to predict 5-year overall survival. A Cox proportional-hazard model, a set of machine learning (ML) models, a convolutional neural network based on tumor (Tumor-CNN), and the current TNM staging system were used as comparison.FindingsA total of 1,705 patients (main cohort) and 125 patients (external validation cohort) with lung cancer (stages I and II) were included. The GCN model was significantly predictive of 5-year overall survival with an AUC of 0.732 (p < 0.0001). The model stratified patients into low- and high-risk groups, which were associated with overall survival (HR = 5.41; 95% CI:, 2.32–10.14; p < 0.0001). On external validation dataset, our GCN model achieved the AUC score of 0.678 (95% CI: 0.564–0.792; p < 0.0001).InterpretationThe proposed GCN model outperformed all ML, Tumor-CNN, and TNM staging models. This study demonstrated the value of utilizing medical imaging graph structure data, resulting in a robust and effective model for the prediction of survival in early-stage lung cancer. |
| first_indexed | 2024-12-10T10:19:02Z |
| format | Article |
| id | doaj.art-38b9778e57dd41a1af3c350e520f1fe3 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-10T10:19:02Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-38b9778e57dd41a1af3c350e520f1fe32022-12-22T01:52:55ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-07-011210.3389/fonc.2022.868186868186Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter StudyJie Lian0Yonghao Long1Fan Huang2Kei Shing Ng3Faith M. Y. Lee4David C. L. Lam5Benjamin X. L. Fang6Qi Dou7Varut Vardhanabhuti8Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaDepartment of Computer Science, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaFaculty of Medicine, University College London, London, United KingdomDepartment of Medicine, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaDepartment of Radiology, Queen Mary Hospital, Hong Kong, Hong Kong SAR, ChinaDepartment of Computer Science, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaDepartment of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, Hong Kong SAR, ChinaBackgroundLung cancer is the leading cause of cancer-related mortality, and accurate prediction of patient survival can aid treatment planning and potentially improve outcomes. In this study, we proposed an automated system capable of lung segmentation and survival prediction using graph convolution neural network (GCN) with CT data in non-small cell lung cancer (NSCLC) patients.MethodsIn this retrospective study, we segmented 10 parts of the lung CT images and built individual lung graphs as inputs to train a GCN model to predict 5-year overall survival. A Cox proportional-hazard model, a set of machine learning (ML) models, a convolutional neural network based on tumor (Tumor-CNN), and the current TNM staging system were used as comparison.FindingsA total of 1,705 patients (main cohort) and 125 patients (external validation cohort) with lung cancer (stages I and II) were included. The GCN model was significantly predictive of 5-year overall survival with an AUC of 0.732 (p < 0.0001). The model stratified patients into low- and high-risk groups, which were associated with overall survival (HR = 5.41; 95% CI:, 2.32–10.14; p < 0.0001). On external validation dataset, our GCN model achieved the AUC score of 0.678 (95% CI: 0.564–0.792; p < 0.0001).InterpretationThe proposed GCN model outperformed all ML, Tumor-CNN, and TNM staging models. This study demonstrated the value of utilizing medical imaging graph structure data, resulting in a robust and effective model for the prediction of survival in early-stage lung cancer.https://www.frontiersin.org/articles/10.3389/fonc.2022.868186/fulllung cancergraph convolutional networkscox proportional-hazardssurvival predictionlung graph model |
| spellingShingle | Jie Lian Yonghao Long Fan Huang Kei Shing Ng Faith M. Y. Lee David C. L. Lam Benjamin X. L. Fang Qi Dou Varut Vardhanabhuti Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study Frontiers in Oncology lung cancer graph convolutional networks cox proportional-hazards survival prediction lung graph model |
| title | Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study |
| title_full | Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study |
| title_fullStr | Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study |
| title_full_unstemmed | Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study |
| title_short | Imaging-Based Deep Graph Neural Networks for Survival Analysis in Early Stage Lung Cancer Using CT: A Multicenter Study |
| title_sort | imaging based deep graph neural networks for survival analysis in early stage lung cancer using ct a multicenter study |
| topic | lung cancer graph convolutional networks cox proportional-hazards survival prediction lung graph model |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.868186/full |
| work_keys_str_mv | AT jielian imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT yonghaolong imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT fanhuang imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT keishingng imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT faithmylee imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT davidcllam imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT benjaminxlfang imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT qidou imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy AT varutvardhanabhuti imagingbaseddeepgraphneuralnetworksforsurvivalanalysisinearlystagelungcancerusingctamulticenterstudy |