Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study
Abstract Aim To assess the predictive performance, risk stratification capabilities, and auxiliary diagnostic utility of radiomics, deep learning, and fusion models in identifying visceral pleural invasion (VPI) in lung adenocarcinoma. Materials and methods A total of 449 patients (female:male, 263:...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | Journal of Cardiothoracic Surgery |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13019-025-03488-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849331768385077248 |
|---|---|
| author | Jiabi Zhao Tingting Wang Bin Wang Bhuva Maheshkumar Satishkumar Lumin Ding Xiwen Sun Caizhong Chen |
| author_facet | Jiabi Zhao Tingting Wang Bin Wang Bhuva Maheshkumar Satishkumar Lumin Ding Xiwen Sun Caizhong Chen |
| author_sort | Jiabi Zhao |
| collection | DOAJ |
| description | Abstract Aim To assess the predictive performance, risk stratification capabilities, and auxiliary diagnostic utility of radiomics, deep learning, and fusion models in identifying visceral pleural invasion (VPI) in lung adenocarcinoma. Materials and methods A total of 449 patients (female:male, 263:186; 59.8 ± 10.5 years) diagnosed with clinical IA stage lung adenocarcinoma (LAC) from two distinct hospitals were enrolled in the study and divided into a training cohort (n = 289) and an external test cohort (n = 160). The fusion models were constructed from the feature level and the decision level respectively. A comprehensive analysis was conducted to assess the prediction ability and prognostic value of radiomics, deep learning, and fusion models. The diagnostic performance of radiologists of varying seniority with and without the assistance of the optimal model was compared. Results The late fusion model demonstrated superior diagnostic performance (AUC = 0.812) compared to clinical (AUC = 0.650), radiomics (AUC = 0.710), deep learning (AUC = 0.770), and the early fusion models (AUC = 0.586) in the external test cohort. The multivariate Cox regression analysis showed that the VPI status predicted by the late fusion model were independently associated with patient disease-free survival (DFS) (p = 0.044). Furthermore, model assistance significantly improved radiologist performance, particularly for junior radiologists; the AUC increased by 0.133 (p < 0.001) reaching levels comparable to the senior radiologist without model assistance (AUC: 0.745 vs. 0.730, p = 0.790). Conclusions The proposed decision-level (late fusion) model significantly reducing the risk of overfitting and demonstrating excellent robustness in multicenter external validation, which can predict VPI status in LAC, aid in prognostic stratification, and assist radiologists in achieving higher diagnostic performance. |
| format | Article |
| id | doaj-art-cac40a4414ac4ddf83ec6c25b2ec3c09 |
| institution | Kabale University |
| issn | 1749-8090 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cardiothoracic Surgery |
| spelling | doaj-art-cac40a4414ac4ddf83ec6c25b2ec3c092025-08-20T03:46:24ZengBMCJournal of Cardiothoracic Surgery1749-80902025-05-0120111110.1186/s13019-025-03488-6Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter studyJiabi Zhao0Tingting Wang1Bin Wang2Bhuva Maheshkumar Satishkumar3Lumin Ding4Xiwen Sun5Caizhong Chen6Department of Radiology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese MedicineDepartment of Radiology, Shanghai Pulmonary Hospital, Tongji University School of MedicineDepartment of Radiology, Shanghai Pudong New Area Mental Health Center, School of Medicine, Tongji UniversityDepartment of Radiology, Shanghai Pulmonary Hospital, Tongji University School of MedicineDepartment of Radiology, Zhongshan Hospital, Fudan UniversityAbstract Aim To assess the predictive performance, risk stratification capabilities, and auxiliary diagnostic utility of radiomics, deep learning, and fusion models in identifying visceral pleural invasion (VPI) in lung adenocarcinoma. Materials and methods A total of 449 patients (female:male, 263:186; 59.8 ± 10.5 years) diagnosed with clinical IA stage lung adenocarcinoma (LAC) from two distinct hospitals were enrolled in the study and divided into a training cohort (n = 289) and an external test cohort (n = 160). The fusion models were constructed from the feature level and the decision level respectively. A comprehensive analysis was conducted to assess the prediction ability and prognostic value of radiomics, deep learning, and fusion models. The diagnostic performance of radiologists of varying seniority with and without the assistance of the optimal model was compared. Results The late fusion model demonstrated superior diagnostic performance (AUC = 0.812) compared to clinical (AUC = 0.650), radiomics (AUC = 0.710), deep learning (AUC = 0.770), and the early fusion models (AUC = 0.586) in the external test cohort. The multivariate Cox regression analysis showed that the VPI status predicted by the late fusion model were independently associated with patient disease-free survival (DFS) (p = 0.044). Furthermore, model assistance significantly improved radiologist performance, particularly for junior radiologists; the AUC increased by 0.133 (p < 0.001) reaching levels comparable to the senior radiologist without model assistance (AUC: 0.745 vs. 0.730, p = 0.790). Conclusions The proposed decision-level (late fusion) model significantly reducing the risk of overfitting and demonstrating excellent robustness in multicenter external validation, which can predict VPI status in LAC, aid in prognostic stratification, and assist radiologists in achieving higher diagnostic performance.https://doi.org/10.1186/s13019-025-03488-6RadiomicsDeep learningAdenocarcinoma of lungCT |
| spellingShingle | Jiabi Zhao Tingting Wang Bin Wang Bhuva Maheshkumar Satishkumar Lumin Ding Xiwen Sun Caizhong Chen Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study Journal of Cardiothoracic Surgery Radiomics Deep learning Adenocarcinoma of lung CT |
| title | Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study |
| title_full | Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study |
| title_fullStr | Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study |
| title_full_unstemmed | Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study |
| title_short | Deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage IA lung adenocarcinoma: a multicenter study |
| title_sort | deep learning radiomics fusion model to predict visceral pleural invasion of clinical stage ia lung adenocarcinoma a multicenter study |
| topic | Radiomics Deep learning Adenocarcinoma of lung CT |
| url | https://doi.org/10.1186/s13019-025-03488-6 |
| work_keys_str_mv | AT jiabizhao deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT tingtingwang deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT binwang deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT bhuvamaheshkumarsatishkumar deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT luminding deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT xiwensun deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy AT caizhongchen deeplearningradiomicsfusionmodeltopredictvisceralpleuralinvasionofclinicalstageialungadenocarcinomaamulticenterstudy |