Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics
ObjectiveThis study aimed to identify CT‐based radiomic alterations associated with radiation pneumonitis (RP) and to evaluate the feasibility of machine learning classifiers for personalized RP diagnosis in breast cancer patients using these radiomic signatures.MethodsA total of 146 planning CT sca...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1609421/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849222068622589952 |
|---|---|
| author | Xiaobo Wen Xiaobo Wen Xiaobo Wen Yutao Zhao Wen Dong Congbo Yang Jinzhi Li Li Sun Yutao Xiu Chang’e Gao Ming Zhang |
| author_facet | Xiaobo Wen Xiaobo Wen Xiaobo Wen Yutao Zhao Wen Dong Congbo Yang Jinzhi Li Li Sun Yutao Xiu Chang’e Gao Ming Zhang |
| author_sort | Xiaobo Wen |
| collection | DOAJ |
| description | ObjectiveThis study aimed to identify CT‐based radiomic alterations associated with radiation pneumonitis (RP) and to evaluate the feasibility of machine learning classifiers for personalized RP diagnosis in breast cancer patients using these radiomic signatures.MethodsA total of 146 planning CT scans (pre- and post-radiotherapy) from 73 breast cancer patients with confirmed RP were retrospectively analyzed. The entire lung was delineated as the region of interest (ROI), and 1,834 radiomic features were extracted using PyRadiomics. Feature selection was performed sequentially using the Mann–Whitney U-test (p < 0.05), Spearman’s rank correlation (|ρ| < 0.9), and least absolute shrinkage and selection operator (LASSO). Eight classifiers [logistic regression (LR), support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF), Extra Tree (ET), XGBoost, LightGBM, and multilayer perceptron (MLP)] were trained and evaluated using accuracy, area under the receiver operating characteristic curve (AUC) with 95% confidence intervals, sensitivity, and specificity.ResultsIn the independent test cohort, LR achieved the highest performance [accuracy 0.897, AUC 0.929 (95% CI, 0.838–1.000), sensitivity 0.786, and specificity 1.000]. LightGBM and MLP also exhibited robust discrimination with AUC values of 0.855 (95% CI, 0.719–0.990) and 0.848 (95% CI, 0.705–0.991), respectively. Five texture-oriented and four first-order features were retained, underscoring the importance of texture-focused extractors [wavelet and local binary pattern (LBP)].ConclusionCT-derived radiomic signatures combined with machine learning classifiers enable the accurate detection of RP in breast cancer patients. Texture-oriented feature selection enhances model discrimination, providing potential for the personalized diagnosis of RP in breast cancer patients and adaptive treatment planning. |
| format | Article |
| id | doaj-art-7e91b381eab541a1878b90caec209746 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-7e91b381eab541a1878b90caec2097462025-08-26T08:19:34ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.16094211609421Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomicsXiaobo Wen0Xiaobo Wen1Xiaobo Wen2Yutao Zhao3Wen Dong4Congbo Yang5Jinzhi Li6Li Sun7Yutao Xiu8Chang’e Gao9Ming Zhang10School of Pharmacy, Qingdao University, Qingdao, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaCancer Institute of The Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaCancer Institute of The Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao, ChinaCancer Institute of The Affiliated Hospital of Qingdao University and Qingdao Cancer Institute, Qingdao, ChinaDepartment of Medical Oncology, The First Affiliated Hospital of Kunming Medical University, Kunming, ChinaDepartment of Radiotherapy, Yunnan Cancer Hospital, the Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, ChinaObjectiveThis study aimed to identify CT‐based radiomic alterations associated with radiation pneumonitis (RP) and to evaluate the feasibility of machine learning classifiers for personalized RP diagnosis in breast cancer patients using these radiomic signatures.MethodsA total of 146 planning CT scans (pre- and post-radiotherapy) from 73 breast cancer patients with confirmed RP were retrospectively analyzed. The entire lung was delineated as the region of interest (ROI), and 1,834 radiomic features were extracted using PyRadiomics. Feature selection was performed sequentially using the Mann–Whitney U-test (p < 0.05), Spearman’s rank correlation (|ρ| < 0.9), and least absolute shrinkage and selection operator (LASSO). Eight classifiers [logistic regression (LR), support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF), Extra Tree (ET), XGBoost, LightGBM, and multilayer perceptron (MLP)] were trained and evaluated using accuracy, area under the receiver operating characteristic curve (AUC) with 95% confidence intervals, sensitivity, and specificity.ResultsIn the independent test cohort, LR achieved the highest performance [accuracy 0.897, AUC 0.929 (95% CI, 0.838–1.000), sensitivity 0.786, and specificity 1.000]. LightGBM and MLP also exhibited robust discrimination with AUC values of 0.855 (95% CI, 0.719–0.990) and 0.848 (95% CI, 0.705–0.991), respectively. Five texture-oriented and four first-order features were retained, underscoring the importance of texture-focused extractors [wavelet and local binary pattern (LBP)].ConclusionCT-derived radiomic signatures combined with machine learning classifiers enable the accurate detection of RP in breast cancer patients. Texture-oriented feature selection enhances model discrimination, providing potential for the personalized diagnosis of RP in breast cancer patients and adaptive treatment planning.https://www.frontiersin.org/articles/10.3389/fonc.2025.1609421/fullbreast cancerradiomicsradiation pneumonitismachine learningartificial intelligence |
| spellingShingle | Xiaobo Wen Xiaobo Wen Xiaobo Wen Yutao Zhao Wen Dong Congbo Yang Jinzhi Li Li Sun Yutao Xiu Chang’e Gao Ming Zhang Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics Frontiers in Oncology breast cancer radiomics radiation pneumonitis machine learning artificial intelligence |
| title | Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| title_full | Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| title_fullStr | Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| title_full_unstemmed | Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| title_short | Personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| title_sort | personalized diagnosis of radiation pneumonitis in breast cancer patients based on radiomics |
| topic | breast cancer radiomics radiation pneumonitis machine learning artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1609421/full |
| work_keys_str_mv | AT xiaobowen personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT xiaobowen personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT xiaobowen personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT yutaozhao personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT wendong personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT congboyang personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT jinzhili personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT lisun personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT yutaoxiu personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT changegao personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics AT mingzhang personalizeddiagnosisofradiationpneumonitisinbreastcancerpatientsbasedonradiomics |