Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy
ObjectivesTo develop a magnetic resonance imaging (MRI)-based radiomics model for predicting the severity of radiation proctitis (RP) in cervical cancer patients’ post-radiotherapy.MethodsWe retrospectively analyzed clinical data and MRI images from 126 cervical squamous cell carcinoma patients trea...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1523567/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582942124146688 |
|---|---|
| author | Jing Xue Menghan Wu Jing Zhang Jiayang Yang Guannan Lv Baojun Qu Yanping Zhang Xia Yan Xia Yan Jianbo Song Jianbo Song |
| author_facet | Jing Xue Menghan Wu Jing Zhang Jiayang Yang Guannan Lv Baojun Qu Yanping Zhang Xia Yan Xia Yan Jianbo Song Jianbo Song |
| author_sort | Jing Xue |
| collection | DOAJ |
| description | ObjectivesTo develop a magnetic resonance imaging (MRI)-based radiomics model for predicting the severity of radiation proctitis (RP) in cervical cancer patients’ post-radiotherapy.MethodsWe retrospectively analyzed clinical data and MRI images from 126 cervical squamous cell carcinoma patients treated with concurrent chemoradiotherapy. Logistic regression (LR), Pearson correlation coefficient, and least absolute shrinkage and selection operator (LASSO) methods were utilized to select optimal imaging features, leading to a combined prediction model developed using a random forest (RF) algorithm. Model performance was assessed using the area under the curve (AUC), DeLong test, calibration curve, and decision curve analysis (DCA), with Shapley Additive exPlanations (SHAP) values for interpretation.ResultsThe samples were split into training (70%) and validation (30%) sets. The delta-radiomics model, comprising 10 delta features, showed strong predictive performance (AUC: 0.92 for training and 0.90 for validation sets). A comprehensive model combining delta-radiomics with clinical features outperformed this, achieving AUCs of 0.99 and 0.98. DeLong’s test confirmed the comprehensive model’s statistical superiority, and both calibration curves and DCA indicated good calibration and high net benefit. Key features associated with RP included D1cc, T1_wavelet-LLL_glcm_MCC, D2cc, and T2_original_firstorder_90 Percentile.ConclusionsThe MRI-based delta radiomics model shows significant promise in predicting RP severity in cervical cancer patients following radiotherapy, with enhanced predictive performance when combined with clinical features. |
| format | Article |
| id | doaj-art-4ad3496caf0641d3aadeb089d4584495 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-4ad3496caf0641d3aadeb089d45844952025-01-29T05:21:29ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-01-011510.3389/fonc.2025.15235671523567Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapyJing Xue0Menghan Wu1Jing Zhang2Jiayang Yang3Guannan Lv4Baojun Qu5Yanping Zhang6Xia Yan7Xia Yan8Jianbo Song9Jianbo Song10Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan, ChinaThird Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan, ChinaResearch Centre for Nuclear and Radiation Frontier Technology, China Institute for Radiation Protection, Taiyuan, ChinaShanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi Hospital, Taiyuan, ChinaGynecological Tumor Treatment Center, The Second People’s Hospital of Datong, Cancer Hospital, Datong, Shanxi, ChinaGynecological Tumor Treatment Center, The Second People’s Hospital of Datong, Cancer Hospital, Datong, Shanxi, ChinaGynecological Tumor Treatment Center, The Second People’s Hospital of Datong, Cancer Hospital, Datong, Shanxi, ChinaShanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi Hospital, Taiyuan, ChinaShanxi Provincial Key Laboratory for Translational Nuclear Medicine and Precision Protection, Taiyuan, ChinaThird Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan, ChinaShanxi Provincial Key Laboratory for Translational Nuclear Medicine and Precision Protection, Taiyuan, ChinaObjectivesTo develop a magnetic resonance imaging (MRI)-based radiomics model for predicting the severity of radiation proctitis (RP) in cervical cancer patients’ post-radiotherapy.MethodsWe retrospectively analyzed clinical data and MRI images from 126 cervical squamous cell carcinoma patients treated with concurrent chemoradiotherapy. Logistic regression (LR), Pearson correlation coefficient, and least absolute shrinkage and selection operator (LASSO) methods were utilized to select optimal imaging features, leading to a combined prediction model developed using a random forest (RF) algorithm. Model performance was assessed using the area under the curve (AUC), DeLong test, calibration curve, and decision curve analysis (DCA), with Shapley Additive exPlanations (SHAP) values for interpretation.ResultsThe samples were split into training (70%) and validation (30%) sets. The delta-radiomics model, comprising 10 delta features, showed strong predictive performance (AUC: 0.92 for training and 0.90 for validation sets). A comprehensive model combining delta-radiomics with clinical features outperformed this, achieving AUCs of 0.99 and 0.98. DeLong’s test confirmed the comprehensive model’s statistical superiority, and both calibration curves and DCA indicated good calibration and high net benefit. Key features associated with RP included D1cc, T1_wavelet-LLL_glcm_MCC, D2cc, and T2_original_firstorder_90 Percentile.ConclusionsThe MRI-based delta radiomics model shows significant promise in predicting RP severity in cervical cancer patients following radiotherapy, with enhanced predictive performance when combined with clinical features.https://www.frontiersin.org/articles/10.3389/fonc.2025.1523567/fullcervical cancerradiation proctitisprediction modelradiomicsdelta radiomics |
| spellingShingle | Jing Xue Menghan Wu Jing Zhang Jiayang Yang Guannan Lv Baojun Qu Yanping Zhang Xia Yan Xia Yan Jianbo Song Jianbo Song Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy Frontiers in Oncology cervical cancer radiation proctitis prediction model radiomics delta radiomics |
| title | Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| title_full | Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| title_fullStr | Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| title_full_unstemmed | Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| title_short | Delta-radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| title_sort | delta radiomics analysis based on magnetic resonance imaging to identify radiation proctitis in patients with cervical cancer after radiotherapy |
| topic | cervical cancer radiation proctitis prediction model radiomics delta radiomics |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1523567/full |
| work_keys_str_mv | AT jingxue deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT menghanwu deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT jingzhang deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT jiayangyang deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT guannanlv deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT baojunqu deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT yanpingzhang deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT xiayan deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT xiayan deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT jianbosong deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy AT jianbosong deltaradiomicsanalysisbasedonmagneticresonanceimagingtoidentifyradiationproctitisinpatientswithcervicalcancerafterradiotherapy |