Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy
Background and purpose:This study sought to develop an advanced composite model to enhance the prognostic accuracy for cervical cancer patients undergoing concurrent chemoradiotherapy (CCRT). The model integrated imaging features from [18F]FDG PET/CT scans with inflammatory markers using a novel uns...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1486654/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850193767196262400 |
|---|---|
| author | Jinyu Shi Lian Wang Min Zhou Shushan Ge Shushan Ge Bin Zhang Jiangqin Han Jihui Li Shengming Deng Shengming Deng |
| author_facet | Jinyu Shi Lian Wang Min Zhou Shushan Ge Shushan Ge Bin Zhang Jiangqin Han Jihui Li Shengming Deng Shengming Deng |
| author_sort | Jinyu Shi |
| collection | DOAJ |
| description | Background and purpose:This study sought to develop an advanced composite model to enhance the prognostic accuracy for cervical cancer patients undergoing concurrent chemoradiotherapy (CCRT). The model integrated imaging features from [18F]FDG PET/CT scans with inflammatory markers using a novel unsupervised two-way clustering approach.MethodsIn this retrospective study, 154 patients diagnosed with primary cervical cancer and treated with CCRT were evaluated using [18F]FDG PET/CT scans. A total of 1,702 radiomic features were extracted from the imaging data. These features underwent rigorous selection based on reproducibility and non-redundancy. The unsupervised two-way clustering method was then employed to simultaneously stratify patients and reduce the dimensionality of features, resulting in the generation of meta-features that were subsequently used to predict overall survival.ResultsKaplan-Meier survival analysis demonstrated that the two-way clustering method successfully stratified patients into distinct risk groups with significant survival differences (P<0.001), outperforming traditional K-means clustering. Predictive models constructed using meta-features derived from two-way clustering showed superior performance compared to those using principal component analysis (PCA), particularly when more than four features were included. The highest C-index values for the COX, COX_Lasso, and RSF models were observed with nine meta-features, yielding results of 0.691 ± 0.026, 0.634 ± 0.018, and 0.684 ± 0.020, respectively. In contrast, models based solely on clinical variables exhibited lower predictive performance, with C-index values of 0.645 ± 0.041, 0.567 ± 0.016, and 0.561 ± 0.033. The combination of clinical data, inflammatory markers, and radiomic features achieved the highest predictive accuracy, with a mean AUC of 0.88 ± 0.07.ConclusionIntegrating radiomic data with inflammatory markers using unsupervised two-way clustering offered a robust approach for predicting survival outcomes in cervical cancer patients. This methodology presented a promising avenue for personalized patient management, potentially leading to more informed treatment decisions and improved outcomes. |
| format | Article |
| id | doaj-art-8e34600dccaf4d5d9f3ab236e6b103fb |
| institution | OA Journals |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-8e34600dccaf4d5d9f3ab236e6b103fb2025-08-20T02:14:10ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-05-011510.3389/fonc.2025.14866541486654Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapyJinyu Shi0Lian Wang1Min Zhou2Shushan Ge3Shushan Ge4Bin Zhang5Jiangqin Han6Jihui Li7Shengming Deng8Shengming Deng9Department of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Oncology, Xuyi People’s Hospital, Huaian, ChinaDepartment of Nuclear Medicine, Yancheng No.1 People’s Hospital, Affiliated Hospital of Medical School, Nanjing University, Yancheng, ChinaDepartment of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Nuclear Medicine, National Health Commission (NHC) Key Laboratory of Nuclear Technology Medical Transformation, Mianyang Central Hospital, Mianyang, Sichuan, ChinaDepartment of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Nuclear Medicine, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Nuclear Medicine, National Health Commission (NHC) Key Laboratory of Nuclear Technology Medical Transformation, Mianyang Central Hospital, Mianyang, Sichuan, ChinaBackground and purpose:This study sought to develop an advanced composite model to enhance the prognostic accuracy for cervical cancer patients undergoing concurrent chemoradiotherapy (CCRT). The model integrated imaging features from [18F]FDG PET/CT scans with inflammatory markers using a novel unsupervised two-way clustering approach.MethodsIn this retrospective study, 154 patients diagnosed with primary cervical cancer and treated with CCRT were evaluated using [18F]FDG PET/CT scans. A total of 1,702 radiomic features were extracted from the imaging data. These features underwent rigorous selection based on reproducibility and non-redundancy. The unsupervised two-way clustering method was then employed to simultaneously stratify patients and reduce the dimensionality of features, resulting in the generation of meta-features that were subsequently used to predict overall survival.ResultsKaplan-Meier survival analysis demonstrated that the two-way clustering method successfully stratified patients into distinct risk groups with significant survival differences (P<0.001), outperforming traditional K-means clustering. Predictive models constructed using meta-features derived from two-way clustering showed superior performance compared to those using principal component analysis (PCA), particularly when more than four features were included. The highest C-index values for the COX, COX_Lasso, and RSF models were observed with nine meta-features, yielding results of 0.691 ± 0.026, 0.634 ± 0.018, and 0.684 ± 0.020, respectively. In contrast, models based solely on clinical variables exhibited lower predictive performance, with C-index values of 0.645 ± 0.041, 0.567 ± 0.016, and 0.561 ± 0.033. The combination of clinical data, inflammatory markers, and radiomic features achieved the highest predictive accuracy, with a mean AUC of 0.88 ± 0.07.ConclusionIntegrating radiomic data with inflammatory markers using unsupervised two-way clustering offered a robust approach for predicting survival outcomes in cervical cancer patients. This methodology presented a promising avenue for personalized patient management, potentially leading to more informed treatment decisions and improved outcomes.https://www.frontiersin.org/articles/10.3389/fonc.2025.1486654/fullPET/CTcervical cancerunsupervised machine learningconcurrent chemoradiotherapy (CCRT)prognostic prediction |
| spellingShingle | Jinyu Shi Lian Wang Min Zhou Shushan Ge Shushan Ge Bin Zhang Jiangqin Han Jihui Li Shengming Deng Shengming Deng Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy Frontiers in Oncology PET/CT cervical cancer unsupervised machine learning concurrent chemoradiotherapy (CCRT) prognostic prediction |
| title | Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| title_full | Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| title_fullStr | Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| title_full_unstemmed | Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| title_short | Harnessing unsupervised machine learning with [18F]FDG PET/CT to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| title_sort | harnessing unsupervised machine learning with 18f fdg pet ct to develop a composite model for predicting overall survival in cervical cancer patients undergoing concurrent chemoradiotherapy |
| topic | PET/CT cervical cancer unsupervised machine learning concurrent chemoradiotherapy (CCRT) prognostic prediction |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1486654/full |
| work_keys_str_mv | AT jinyushi harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT lianwang harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT minzhou harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT shushange harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT shushange harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT binzhang harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT jiangqinhan harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT jihuili harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT shengmingdeng harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy AT shengmingdeng harnessingunsupervisedmachinelearningwith18ffdgpetcttodevelopacompositemodelforpredictingoverallsurvivalincervicalcancerpatientsundergoingconcurrentchemoradiotherapy |