CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study
Abstract Background To construct and assess a computed tomography (CT)-based deep learning radiomics nomogram (DLRN) for predicting the pathological grade of bladder cancer (BCa) preoperatively. Methods We retrospectively enrolled 688 patients with BCa (469 in the training cohort, 219 in the externa...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | Cancer Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40644-023-00609-z |
| _version_ | 1827633295584657408 |
|---|---|
| author | Hongzheng Song Shifeng Yang Boyang Yu Na Li Yonghua Huang Rui Sun Bo Wang Pei Nie Feng Hou Chencui Huang Meng Zhang Hexiang Wang |
| author_facet | Hongzheng Song Shifeng Yang Boyang Yu Na Li Yonghua Huang Rui Sun Bo Wang Pei Nie Feng Hou Chencui Huang Meng Zhang Hexiang Wang |
| author_sort | Hongzheng Song |
| collection | DOAJ |
| description | Abstract Background To construct and assess a computed tomography (CT)-based deep learning radiomics nomogram (DLRN) for predicting the pathological grade of bladder cancer (BCa) preoperatively. Methods We retrospectively enrolled 688 patients with BCa (469 in the training cohort, 219 in the external test cohort) who underwent surgical resection. We extracted handcrafted radiomics (HCR) features and deep learning (DL) features from three-phase CT images (including corticomedullary-phase [C-phase], nephrographic-phase [N-phase] and excretory-phase [E-phase]). We constructed predictive models using 11 machine learning classifiers, and we developed a DLRN by combining the radiomic signature with clinical factors. We assessed performance and clinical utility of the models with reference to the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). Results The support vector machine (SVM) classifier model based on HCR and DL combined features was the best radiomic signature, with AUC values of 0.953 and 0.943 in the training cohort and the external test cohort, respectively. The AUC values of the clinical model in the training cohort and the external test cohort were 0.752 and 0.745, respectively. DLRN performed well on both data cohorts (training cohort: AUC = 0.961; external test cohort: AUC = 0.947), and outperformed the clinical model and the optimal radiomic signature. Conclusion The proposed CT-based DLRN showed good diagnostic capability in distinguishing between high and low grade BCa. |
| first_indexed | 2024-03-09T14:57:32Z |
| format | Article |
| id | doaj.art-d722b09811ae425292eb2e674b512980 |
| institution | Directory Open Access Journal |
| issn | 1470-7330 |
| language | English |
| last_indexed | 2024-03-09T14:57:32Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Imaging |
| spelling | doaj.art-d722b09811ae425292eb2e674b5129802023-11-26T14:06:16ZengBMCCancer Imaging1470-73302023-09-0123111210.1186/s40644-023-00609-zCT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter studyHongzheng Song0Shifeng Yang1Boyang Yu2Na Li3Yonghua Huang4Rui Sun5Bo Wang6Pei Nie7Feng Hou8Chencui Huang9Meng Zhang10Hexiang Wang11Department of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical UniversityQingdao No.58 High School of Shandong ProvinceDepartment of Radiology, The People’s Hospital of Zhangqiu AreaDepartment of Radiology, The Puyang Oilfield General HospitalDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Pathology, The Affiliated Hospital of Qingdao UniversityDepartment of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co., LtdDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityAbstract Background To construct and assess a computed tomography (CT)-based deep learning radiomics nomogram (DLRN) for predicting the pathological grade of bladder cancer (BCa) preoperatively. Methods We retrospectively enrolled 688 patients with BCa (469 in the training cohort, 219 in the external test cohort) who underwent surgical resection. We extracted handcrafted radiomics (HCR) features and deep learning (DL) features from three-phase CT images (including corticomedullary-phase [C-phase], nephrographic-phase [N-phase] and excretory-phase [E-phase]). We constructed predictive models using 11 machine learning classifiers, and we developed a DLRN by combining the radiomic signature with clinical factors. We assessed performance and clinical utility of the models with reference to the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). Results The support vector machine (SVM) classifier model based on HCR and DL combined features was the best radiomic signature, with AUC values of 0.953 and 0.943 in the training cohort and the external test cohort, respectively. The AUC values of the clinical model in the training cohort and the external test cohort were 0.752 and 0.745, respectively. DLRN performed well on both data cohorts (training cohort: AUC = 0.961; external test cohort: AUC = 0.947), and outperformed the clinical model and the optimal radiomic signature. Conclusion The proposed CT-based DLRN showed good diagnostic capability in distinguishing between high and low grade BCa.https://doi.org/10.1186/s40644-023-00609-zUrinary bladder neoplasmsComputed tomographyDeep learningRadiomicsNomogram |
| spellingShingle | Hongzheng Song Shifeng Yang Boyang Yu Na Li Yonghua Huang Rui Sun Bo Wang Pei Nie Feng Hou Chencui Huang Meng Zhang Hexiang Wang CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study Cancer Imaging Urinary bladder neoplasms Computed tomography Deep learning Radiomics Nomogram |
| title | CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study |
| title_full | CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study |
| title_fullStr | CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study |
| title_full_unstemmed | CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study |
| title_short | CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study |
| title_sort | ct based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer a multicenter study |
| topic | Urinary bladder neoplasms Computed tomography Deep learning Radiomics Nomogram |
| url | https://doi.org/10.1186/s40644-023-00609-z |
| work_keys_str_mv | AT hongzhengsong ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT shifengyang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT boyangyu ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT nali ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT yonghuahuang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT ruisun ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT bowang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT peinie ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT fenghou ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT chencuihuang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT mengzhang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy AT hexiangwang ctbaseddeeplearningradiomicsnomogramforthepredictionofpathologicalgradeinbladdercanceramulticenterstudy |