Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP
Abstract Objective To investigate the predictive value of machine learning-based PET/CT radiomics and clinical risk factors in predicting interim efficacy in patients with follicular lymphoma (FL). Methods This study retrospectively analyzed data from 97 patients with FL diagnosed via histopathologi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12885-025-13507-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585649606098944 |
|---|---|
| author | Zeying Wen Xiaohe Gao Qingxia Wu Jianwei Yang Jian Sun Keliu Wu Hongfei Zhao Ruihua Wang Yanmei Li |
| author_facet | Zeying Wen Xiaohe Gao Qingxia Wu Jianwei Yang Jian Sun Keliu Wu Hongfei Zhao Ruihua Wang Yanmei Li |
| author_sort | Zeying Wen |
| collection | DOAJ |
| description | Abstract Objective To investigate the predictive value of machine learning-based PET/CT radiomics and clinical risk factors in predicting interim efficacy in patients with follicular lymphoma (FL). Methods This study retrospectively analyzed data from 97 patients with FL diagnosed via histopathological examination between July 2012 and November 2023. Lesion segmentation was performed using LIFEx software, and radiomics features were extracted through the uAI Research Portal (uRP) platform, including first-order features, shape features, and texture features. Fourteen filters were applied to the raw images to extract higher-order features from the derived images. Univariate analysis was employed to identify clinical risk factors, and correlation coefficients, MRMR, and LASSO algorithms were used for dimensionality reduction and selection of radiomics features. Finally, a logistic regression machine learning model was developed to predict the interim efficacy of FL using a five-fold cross-validation strategy. Model performance was assessed using the area under the receiver operating characteristic (ROC) curve, accuracy, and the Delong test to compare AUC differences. Result Among the 97 patients, 42 (43.30%) achieved complete response (CR) for interim efficacy, while 55 (56.70%) had non-complete response (non-CR). A total of 2264 radiomics features were extracted from the images. Seven clinical risk factors and ten radiomics features associated with interim efficacy were selected to construct the clinical, radiomics, and radiomics-clinical combined models. Among the three logistic regression machine learning models developed, the radiomics-clinical combined model demonstrated the best performance, achieving a mean AUC of 0.849 (95% CI, 0.676–1.000) and an accuracy of 0.795, outperforming the other two models. Conclusion Our preliminary results demonstrate that a radiomics-clinical combined model, based on baseline [18F]FDG PET/CT radiomics features and clinical risk factors, may contribute to predicting interim efficacy in FL patients. |
| format | Article |
| id | doaj-art-8e4b16ea446c48bcb9ae45e160678182 |
| institution | Kabale University |
| issn | 1471-2407 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj-art-8e4b16ea446c48bcb9ae45e1606781822025-01-26T12:38:10ZengBMCBMC Cancer1471-24072025-01-0125111310.1186/s12885-025-13507-3Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOPZeying Wen0Xiaohe Gao1Qingxia Wu2Jianwei Yang3Jian Sun4Keliu Wu5Hongfei Zhao6Ruihua Wang7Yanmei Li8Department of Radiology, The First Affiliated Hospital of Henan University of Chinese MedicineThe First Clinical Medical College, Henan University of Chinese MedicineBeijing United Imaging Research Institute of Intelligent ImagingPET/CT center, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalThe First Clinical Medical College, Henan University of Chinese MedicineDepartment of Nuclear Medicine, The First Affiliated Hospital of Zhengzhou UniversityThe First Clinical Medical College, Henan University of Chinese MedicineDepartment of Nuclear Medicine, The First Affiliated Hospital of Zhengzhou UniversityPET/CT center, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer HospitalAbstract Objective To investigate the predictive value of machine learning-based PET/CT radiomics and clinical risk factors in predicting interim efficacy in patients with follicular lymphoma (FL). Methods This study retrospectively analyzed data from 97 patients with FL diagnosed via histopathological examination between July 2012 and November 2023. Lesion segmentation was performed using LIFEx software, and radiomics features were extracted through the uAI Research Portal (uRP) platform, including first-order features, shape features, and texture features. Fourteen filters were applied to the raw images to extract higher-order features from the derived images. Univariate analysis was employed to identify clinical risk factors, and correlation coefficients, MRMR, and LASSO algorithms were used for dimensionality reduction and selection of radiomics features. Finally, a logistic regression machine learning model was developed to predict the interim efficacy of FL using a five-fold cross-validation strategy. Model performance was assessed using the area under the receiver operating characteristic (ROC) curve, accuracy, and the Delong test to compare AUC differences. Result Among the 97 patients, 42 (43.30%) achieved complete response (CR) for interim efficacy, while 55 (56.70%) had non-complete response (non-CR). A total of 2264 radiomics features were extracted from the images. Seven clinical risk factors and ten radiomics features associated with interim efficacy were selected to construct the clinical, radiomics, and radiomics-clinical combined models. Among the three logistic regression machine learning models developed, the radiomics-clinical combined model demonstrated the best performance, achieving a mean AUC of 0.849 (95% CI, 0.676–1.000) and an accuracy of 0.795, outperforming the other two models. Conclusion Our preliminary results demonstrate that a radiomics-clinical combined model, based on baseline [18F]FDG PET/CT radiomics features and clinical risk factors, may contribute to predicting interim efficacy in FL patients.https://doi.org/10.1186/s12885-025-13507-3Follicular lymphomaRadiomicsInterim efficacy |
| spellingShingle | Zeying Wen Xiaohe Gao Qingxia Wu Jianwei Yang Jian Sun Keliu Wu Hongfei Zhao Ruihua Wang Yanmei Li Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP BMC Cancer Follicular lymphoma Radiomics Interim efficacy |
| title | Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP |
| title_full | Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP |
| title_fullStr | Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP |
| title_full_unstemmed | Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP |
| title_short | Baseline [18F]FDG PET/CT radiomics for predicting interim efficacy in follicular lymphoma treated with first-line R-CHOP |
| title_sort | baseline 18f fdg pet ct radiomics for predicting interim efficacy in follicular lymphoma treated with first line r chop |
| topic | Follicular lymphoma Radiomics Interim efficacy |
| url | https://doi.org/10.1186/s12885-025-13507-3 |
| work_keys_str_mv | AT zeyingwen baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT xiaohegao baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT qingxiawu baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT jianweiyang baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT jiansun baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT keliuwu baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT hongfeizhao baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT ruihuawang baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop AT yanmeili baseline18ffdgpetctradiomicsforpredictinginterimefficacyinfollicularlymphomatreatedwithfirstlinerchop |