MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors
Purpose: We aim to develop an MRI-based radiomics model to improve the accuracy of differentiating non-ccRCC from benign renal tumors preoperatively. Methods: The retrospective study included 195 patients with pathologically confirmed renal tumors (134 non-ccRCCs and 61 benign renal tumors) who unde...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | European Journal of Radiology Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352047724000637 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257485146882048 |
|---|---|
| author | Ruiting Wang Lianting Zhong Pingyi Zhu Xianpan Pan Lei Chen Jianjun Zhou Yuqin Ding |
| author_facet | Ruiting Wang Lianting Zhong Pingyi Zhu Xianpan Pan Lei Chen Jianjun Zhou Yuqin Ding |
| author_sort | Ruiting Wang |
| collection | DOAJ |
| description | Purpose: We aim to develop an MRI-based radiomics model to improve the accuracy of differentiating non-ccRCC from benign renal tumors preoperatively. Methods: The retrospective study included 195 patients with pathologically confirmed renal tumors (134 non-ccRCCs and 61 benign renal tumors) who underwent preoperative renal mass protocol MRI examinations. The patients were divided into a training set (n = 136) and test set (n = 59). Simple t-test and the Least Absolute Shrink and Selection Operator (LASSO) were used to select the most valuable features and the rad-scores of them were calculated. The clinicoradiologic models, single-sequence radiomics models, multi-sequence radiomics models and combined models for differentiation were constructed with 2 classifiers (support vector machine (SVM), logistic regression (LR)) in the training set and used for differentiation in the test set. Ten-fold cross validation was applied to obtain the optimal hyperparameters of the models. The performances of the models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). Delong’s test was performed to compare the performances of models. Results: After univariate and multivariate logistic regression analysis, the independent risk factors to differentiate non-ccRCC from benign renal tumors were selected as follows: age, tumor region, hemorrhage, pseudocapsule and enhancement degree. Among the 14 machine learning classification models constructed, the combined model with LR has the highest efficiency in differentiating non-ccRCC from benign renal tumors. The AUC in the training set is 0.964, and the accuracy is 0.919. The AUC in the test set is 0.936, and the accuracy is 0.864. Conclusion: The MRI-based radiomics machine learning is feasible to differentiate non-ccRCC from benign renal tumors, which could improve the accuracy of clinical diagnosis. |
| format | Article |
| id | doaj-art-757c73b3962d4e7e841089ea4e4b884e |
| institution | OA Journals |
| issn | 2352-0477 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | European Journal of Radiology Open |
| spelling | doaj-art-757c73b3962d4e7e841089ea4e4b884e2025-08-20T01:56:24ZengElsevierEuropean Journal of Radiology Open2352-04772024-12-011310060810.1016/j.ejro.2024.100608MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumorsRuiting Wang0Lianting Zhong1Pingyi Zhu2Xianpan Pan3Lei Chen4Jianjun Zhou5Yuqin Ding6Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Institute of Medical Imaging, Shanghai, ChinaDepartment of Radiology, Zhongshan Hospital (Xiamen), Fudan University, Xiamen, Fujian, ChinaDepartment of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Institute of Medical Imaging, Shanghai, ChinaShanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaShanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Radiology, Zhongshan Hospital (Xiamen), Fudan University, Xiamen, Fujian, China; Xiamen Municipal Clinical Research Center for Medical Imaging, Xiamen, Fujian, China; Fujian Province Key Clinical Specialty for Medical Imaging, Xiamen, Fujian, China; Correspondence to: Department of Radiology, Zhongshan Hospital (Xiamen), Fudan University, 668 Jinhu Road, Huli District, Xiamen 361015, China.Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Institute of Medical Imaging, Shanghai, China; Correspondence to: Department of Radiology, Zhongshan Hospital, Shanghai Institute of Medical Imaging, 180 Fenglin Road, Shanghai 200032, PR ChinaPurpose: We aim to develop an MRI-based radiomics model to improve the accuracy of differentiating non-ccRCC from benign renal tumors preoperatively. Methods: The retrospective study included 195 patients with pathologically confirmed renal tumors (134 non-ccRCCs and 61 benign renal tumors) who underwent preoperative renal mass protocol MRI examinations. The patients were divided into a training set (n = 136) and test set (n = 59). Simple t-test and the Least Absolute Shrink and Selection Operator (LASSO) were used to select the most valuable features and the rad-scores of them were calculated. The clinicoradiologic models, single-sequence radiomics models, multi-sequence radiomics models and combined models for differentiation were constructed with 2 classifiers (support vector machine (SVM), logistic regression (LR)) in the training set and used for differentiation in the test set. Ten-fold cross validation was applied to obtain the optimal hyperparameters of the models. The performances of the models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). Delong’s test was performed to compare the performances of models. Results: After univariate and multivariate logistic regression analysis, the independent risk factors to differentiate non-ccRCC from benign renal tumors were selected as follows: age, tumor region, hemorrhage, pseudocapsule and enhancement degree. Among the 14 machine learning classification models constructed, the combined model with LR has the highest efficiency in differentiating non-ccRCC from benign renal tumors. The AUC in the training set is 0.964, and the accuracy is 0.919. The AUC in the test set is 0.936, and the accuracy is 0.864. Conclusion: The MRI-based radiomics machine learning is feasible to differentiate non-ccRCC from benign renal tumors, which could improve the accuracy of clinical diagnosis.http://www.sciencedirect.com/science/article/pii/S2352047724000637Renal cell carcinomaBenign renal tumorsMachine learningRadiomicsMagnetic resonance imaging |
| spellingShingle | Ruiting Wang Lianting Zhong Pingyi Zhu Xianpan Pan Lei Chen Jianjun Zhou Yuqin Ding MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors European Journal of Radiology Open Renal cell carcinoma Benign renal tumors Machine learning Radiomics Magnetic resonance imaging |
| title | MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors |
| title_full | MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors |
| title_fullStr | MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors |
| title_full_unstemmed | MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors |
| title_short | MRI-based radiomics machine learning model to differentiate non-clear cell renal cell carcinoma from benign renal tumors |
| title_sort | mri based radiomics machine learning model to differentiate non clear cell renal cell carcinoma from benign renal tumors |
| topic | Renal cell carcinoma Benign renal tumors Machine learning Radiomics Magnetic resonance imaging |
| url | http://www.sciencedirect.com/science/article/pii/S2352047724000637 |
| work_keys_str_mv | AT ruitingwang mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT liantingzhong mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT pingyizhu mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT xianpanpan mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT leichen mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT jianjunzhou mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors AT yuqinding mribasedradiomicsmachinelearningmodeltodifferentiatenonclearcellrenalcellcarcinomafrombenignrenaltumors |