Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer
Abstract Radiation pneumonia (RP) is the most common side effect of chest radiotherapy, and can affect patients’ quality of life. This study aimed to establish a combined model of radiomics, dosiomics, deep learning (DL) based on simulated location CT and dosimetry images combining with clinical par...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-02045-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849309809523818496 |
|---|---|
| author | Xun Wang Aiping Zhang Huipeng Yang Guqing Zhang Junli Ma Shucheng Ye Shuang Ge |
| author_facet | Xun Wang Aiping Zhang Huipeng Yang Guqing Zhang Junli Ma Shucheng Ye Shuang Ge |
| author_sort | Xun Wang |
| collection | DOAJ |
| description | Abstract Radiation pneumonia (RP) is the most common side effect of chest radiotherapy, and can affect patients’ quality of life. This study aimed to establish a combined model of radiomics, dosiomics, deep learning (DL) based on simulated location CT and dosimetry images combining with clinical parameters to improve the predictive ability of ≥ 2 grade RP (RP2) in patients with non-small cell lung cancer (NSCLC). This study retrospectively collected 245 patients with NSCLC who received radiotherapy from three hospitals. 162 patients from Hospital I were randomly divided into training cohort and internal validation cohort according to 7:3. 83 patients from two other hospitals served as an external validation cohort. Multivariate analysis was used to screen independent clinical predictors and establish clinical model (CM). The radiomic and dosiomics (RD) features and DL features were extracted from simulated location CT and dosimetry images based on the region of interest (ROI) of total lung-PTV (TL-PTV). The features screened by the t-test and least absolute shrinkage and selection operator (LASSO) were used to construct the RD and DL model, and RD-score and DL-score were calculated. RD-score, DL-score and independent clinical features were combined to establish deep learning radiomics and dosiomics nomogram (DLRDN). The model performance was evaluated by area under the curve (AUC). Three clinical factors, including V20, V30, and mean lung dose (MLD), were used to establish the CM. 7 RD features including 4 radiomics features and 3 dosiomics features were selected to establish RD model. 10 DL features were selected to establish DL model. Among the different models, DLRDN showed the best predictions, with the AUCs of 0.891 (0.826–0.957), 0.825 (0.693–0.957), and 0.801 (0.698–0.904) in the training cohort, internal validation cohort and external validation cohort, respectively. DCA showed that DLRDN had a higher overall net benefit than other models. The calibration curve showed that the predicted value of DLRDN was in good agreement with the actual value. Overall, radiomics, dosiomics, and DL features based on simulated location CT and dosimetry images have the potential to help predict RP2. The combination of multi-dimensional data produced the optimal predictive model, which could provide guidance for clinicians. |
| format | Article |
| id | doaj-art-b6a38b3aeac04bfabcd250e3d7e76d0b |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b6a38b3aeac04bfabcd250e3d7e76d0b2025-08-20T03:53:57ZengNature PortfolioScientific Reports2045-23222025-05-0115111010.1038/s41598-025-02045-4Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancerXun Wang0Aiping Zhang1Huipeng Yang2Guqing Zhang3Junli Ma4Shucheng Ye5Shuang Ge6Department of Medical Imaging, Affiliated Hospital of Jining Medical UniversityDepartment of Radiation Oncology, Tumor Hospital of JiningDepartment of Radiation Oncology, Jining First People’s HospitalDepartment of Medical Imaging, Affiliated Hospital of Jining Medical UniversityDepartment of Radiation Oncology, Affiliated Hospital of Jining Medical UniversityDepartment of Radiation Oncology, Affiliated Hospital of Jining Medical UniversityDepartment of Radiation Oncology, Affiliated Hospital of Jining Medical UniversityAbstract Radiation pneumonia (RP) is the most common side effect of chest radiotherapy, and can affect patients’ quality of life. This study aimed to establish a combined model of radiomics, dosiomics, deep learning (DL) based on simulated location CT and dosimetry images combining with clinical parameters to improve the predictive ability of ≥ 2 grade RP (RP2) in patients with non-small cell lung cancer (NSCLC). This study retrospectively collected 245 patients with NSCLC who received radiotherapy from three hospitals. 162 patients from Hospital I were randomly divided into training cohort and internal validation cohort according to 7:3. 83 patients from two other hospitals served as an external validation cohort. Multivariate analysis was used to screen independent clinical predictors and establish clinical model (CM). The radiomic and dosiomics (RD) features and DL features were extracted from simulated location CT and dosimetry images based on the region of interest (ROI) of total lung-PTV (TL-PTV). The features screened by the t-test and least absolute shrinkage and selection operator (LASSO) were used to construct the RD and DL model, and RD-score and DL-score were calculated. RD-score, DL-score and independent clinical features were combined to establish deep learning radiomics and dosiomics nomogram (DLRDN). The model performance was evaluated by area under the curve (AUC). Three clinical factors, including V20, V30, and mean lung dose (MLD), were used to establish the CM. 7 RD features including 4 radiomics features and 3 dosiomics features were selected to establish RD model. 10 DL features were selected to establish DL model. Among the different models, DLRDN showed the best predictions, with the AUCs of 0.891 (0.826–0.957), 0.825 (0.693–0.957), and 0.801 (0.698–0.904) in the training cohort, internal validation cohort and external validation cohort, respectively. DCA showed that DLRDN had a higher overall net benefit than other models. The calibration curve showed that the predicted value of DLRDN was in good agreement with the actual value. Overall, radiomics, dosiomics, and DL features based on simulated location CT and dosimetry images have the potential to help predict RP2. The combination of multi-dimensional data produced the optimal predictive model, which could provide guidance for clinicians.https://doi.org/10.1038/s41598-025-02045-4Radiation pneumoniaRadiomicDosiomicDeep learningNon-small cell lung cancer |
| spellingShingle | Xun Wang Aiping Zhang Huipeng Yang Guqing Zhang Junli Ma Shucheng Ye Shuang Ge Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer Scientific Reports Radiation pneumonia Radiomic Dosiomic Deep learning Non-small cell lung cancer |
| title | Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer |
| title_full | Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer |
| title_fullStr | Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer |
| title_full_unstemmed | Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer |
| title_short | Multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non-small cell lung cancer |
| title_sort | multicenter development of a deep learning radiomics and dosiomics nomogram to predict radiation pneumonia risk in non small cell lung cancer |
| topic | Radiation pneumonia Radiomic Dosiomic Deep learning Non-small cell lung cancer |
| url | https://doi.org/10.1038/s41598-025-02045-4 |
| work_keys_str_mv | AT xunwang multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT aipingzhang multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT huipengyang multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT guqingzhang multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT junlima multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT shuchengye multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer AT shuangge multicenterdevelopmentofadeeplearningradiomicsanddosiomicsnomogramtopredictradiationpneumoniariskinnonsmallcelllungcancer |