A radiomic approach to differential diagnosis of renal cell carcinoma in patients with hydronephrosis and renal calculi.
10.12122/j.issn.1673-4254.2019.05.08
- Author:
Hang ZHANG
1
;
Qing LI
2
;
Shulong LI
1
;
Jianhua MA
1
;
Jing HUANG
1
Author Information
1. School of Biomedical Engineering, Southern Medical University//Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China.
2. Clinical Laboratory, Shenzhen Hospital of Southern Medical University, Shenzhen 518000, China.
- Publication Type:Journal Article
- Keywords:
computed tomography, feature selection;
radiomics;
renal cell carcinoma;
renal hydronephrosis with calculi;
support vector machine
- MeSH:
Carcinoma, Renal Cell;
diagnosis;
Diagnosis, Differential;
Humans;
Hydronephrosis;
diagnosis;
Kidney Calculi;
Kidney Neoplasms;
diagnosis;
Retrospective Studies
- From:
Journal of Southern Medical University
2019;39(5):547-553
- CountryChina
- Language:Chinese
-
Abstract:
To explore the application of radiomic analysis in differential diagnosis of renal cell carcinoma in patients with hydronephrosis and renal calculi using supervised machine learning methods.The abdominal CT scan data were retrospectively analyzed for 66 patients with pathologically confirmed hydronephrosis and renal calculi, among whom 35 patients had renal cell carcinoma. In each case 18 non-texture features and 344 texture features were extracted from the region of interest (ROI). Infinite feature selection (InfFS)-based forward feature selection method coupled with support vector machine (SVM) classifier was used to select the optimal feature subset. SVM was trained and performed the prediction using the selected feature subset to classify whether hydronephrosis with renal calculi was associated with renal cell carcinoma.A total of 12 texture features were selected as the optimal features. The area under curve (AUC), accuracy, sensitivity, specificity, false positive rate and false negative rate of the SVM- InfFS model for predicting accompanying renal tumors in patients with hydronephrosis and calculi were 0.907, 81.0%, 70.0%, 90.9%, 9.1%, and 30.0%, respectively. The diagnostic accuracy, sensitivity, specificity, false positive and false negative rates by the clinicians provided with these classification results were 90.5%, 80.0%, 100%, 0.00%, and 20.0%, respectively.The computer-aided classification model based on supervised machine learning can effectively extract the diagnostic information and improve the diagnostic rate of renal cell carcinoma associated with hydronephrosis and renal calculi.
