Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer
ObjectiveThe purpose of this research was to develop a radiomics model that combines several clinical features for preoperative prediction of the pathological grade of bladder cancer (BCa) using non-enhanced computed tomography (NE-CT) scanning images.Materials and methodsThe computed tomography (CT...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1166245/full |
| _version_ | 1797831685092409344 |
|---|---|
| author | Zhikang Deng Zhikang Deng Wentao Dong Situ Xiong Di Jin Di Jin Hongzhang Zhou Ling Zhang Ling Zhang LiHan Xie LiHan Xie Yaohong Deng Rong Xu Bing Fan |
| author_facet | Zhikang Deng Zhikang Deng Wentao Dong Situ Xiong Di Jin Di Jin Hongzhang Zhou Ling Zhang Ling Zhang LiHan Xie LiHan Xie Yaohong Deng Rong Xu Bing Fan |
| author_sort | Zhikang Deng |
| collection | DOAJ |
| description | ObjectiveThe purpose of this research was to develop a radiomics model that combines several clinical features for preoperative prediction of the pathological grade of bladder cancer (BCa) using non-enhanced computed tomography (NE-CT) scanning images.Materials and methodsThe computed tomography (CT), clinical, and pathological data of 105 BCa patients attending our hospital between January 2017 and August 2022 were retrospectively evaluated. The study cohort comprised 44 low-grade BCa and 61 high-grade BCa patients. The subjects were randomly divided into training (n = 73) and validation (n = 32) cohorts at a ratio of 7:3. Radiomic features were extracted from NE-CT images. A total of 15 representative features were screened using the least absolute shrinkage and selection operator (LASSO) algorithm. Based on these characteristics, six models for predicting BCa pathological grade, including support vector machine (SVM), k-nearest neighbor (KNN), gradient boosting decision tree (GBDT), logical regression (LR), random forest (RF), and extreme gradient boosting (XGBOOST) were constructed. The model combining radiomics score and clinical factors was further constructed. The predictive performance of the models was evaluated based on the area under the receiver operating characteristic (ROC) curve, DeLong test, and decision curve analysis (DCA).ResultsThe selected clinical factors for the model included age and tumor size. LASSO regression analysis identified 15 features most linked to BCa grade, which were included in the machine learning model. The SVM analysis revealed that the highest AUC of the model was 0.842. A nomogram combining the radiomics signature and selected clinical variables showed accurate prediction of the pathological grade of BCa preoperatively. The AUC of the training cohort was 0.919, whereas that of the validation cohort was 0.854. The clinical value of the combined radiomics nomogram was validated using calibration curve and DCA.ConclusionMachine learning models combining CT semantic features and the selected clinical variables can accurately predict the pathological grade of BCa, offering a non-invasive and accurate approach for predicting the pathological grade of BCa preoperatively. |
| first_indexed | 2024-04-09T13:56:49Z |
| format | Article |
| id | doaj.art-7030fddd692d49eba6731c17a3c816f2 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-09T13:56:49Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-7030fddd692d49eba6731c17a3c816f22023-05-08T04:31:57ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-05-011310.3389/fonc.2023.11662451166245Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancerZhikang Deng0Zhikang Deng1Wentao Dong2Situ Xiong3Di Jin4Di Jin5Hongzhang Zhou6Ling Zhang7Ling Zhang8LiHan Xie9LiHan Xie10Yaohong Deng11Rong Xu12Bing Fan13Medical College of Nanchang University, Nanchang University, Nanchang, ChinaDepartment of Nuclear Medicine, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Urology, The First Affiliated Hospital of Nanchang University, Nanchang, ChinaMedical College of Nanchang University, Nanchang University, Nanchang, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Nuclear Medicine, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaMedical College of Nanchang University, Nanchang University, Nanchang, ChinaDepartment of Nuclear Medicine, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaMedical College of Nanchang University, Nanchang University, Nanchang, ChinaDepartment of Nuclear Medicine, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Research & Development, Yizhun Medical AI Co. Ltd., Beijing, ChinaDepartment of Nuclear Medicine, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaObjectiveThe purpose of this research was to develop a radiomics model that combines several clinical features for preoperative prediction of the pathological grade of bladder cancer (BCa) using non-enhanced computed tomography (NE-CT) scanning images.Materials and methodsThe computed tomography (CT), clinical, and pathological data of 105 BCa patients attending our hospital between January 2017 and August 2022 were retrospectively evaluated. The study cohort comprised 44 low-grade BCa and 61 high-grade BCa patients. The subjects were randomly divided into training (n = 73) and validation (n = 32) cohorts at a ratio of 7:3. Radiomic features were extracted from NE-CT images. A total of 15 representative features were screened using the least absolute shrinkage and selection operator (LASSO) algorithm. Based on these characteristics, six models for predicting BCa pathological grade, including support vector machine (SVM), k-nearest neighbor (KNN), gradient boosting decision tree (GBDT), logical regression (LR), random forest (RF), and extreme gradient boosting (XGBOOST) were constructed. The model combining radiomics score and clinical factors was further constructed. The predictive performance of the models was evaluated based on the area under the receiver operating characteristic (ROC) curve, DeLong test, and decision curve analysis (DCA).ResultsThe selected clinical factors for the model included age and tumor size. LASSO regression analysis identified 15 features most linked to BCa grade, which were included in the machine learning model. The SVM analysis revealed that the highest AUC of the model was 0.842. A nomogram combining the radiomics signature and selected clinical variables showed accurate prediction of the pathological grade of BCa preoperatively. The AUC of the training cohort was 0.919, whereas that of the validation cohort was 0.854. The clinical value of the combined radiomics nomogram was validated using calibration curve and DCA.ConclusionMachine learning models combining CT semantic features and the selected clinical variables can accurately predict the pathological grade of BCa, offering a non-invasive and accurate approach for predicting the pathological grade of BCa preoperatively.https://www.frontiersin.org/articles/10.3389/fonc.2023.1166245/fullbladder cancerpathological gradecombined radiomics nomogramtextural featuresnon-enhanced computed tomography |
| spellingShingle | Zhikang Deng Zhikang Deng Wentao Dong Situ Xiong Di Jin Di Jin Hongzhang Zhou Ling Zhang Ling Zhang LiHan Xie LiHan Xie Yaohong Deng Rong Xu Bing Fan Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer Frontiers in Oncology bladder cancer pathological grade combined radiomics nomogram textural features non-enhanced computed tomography |
| title | Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| title_full | Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| title_fullStr | Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| title_full_unstemmed | Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| title_short | Machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| title_sort | machine learning models combining computed tomography semantic features and selected clinical variables for accurate prediction of the pathological grade of bladder cancer |
| topic | bladder cancer pathological grade combined radiomics nomogram textural features non-enhanced computed tomography |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1166245/full |
| work_keys_str_mv | AT zhikangdeng machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT zhikangdeng machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT wentaodong machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT situxiong machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT dijin machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT dijin machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT hongzhangzhou machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT lingzhang machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT lingzhang machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT lihanxie machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT lihanxie machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT yaohongdeng machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT rongxu machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer AT bingfan machinelearningmodelscombiningcomputedtomographysemanticfeaturesandselectedclinicalvariablesforaccuratepredictionofthepathologicalgradeofbladdercancer |