M-W You1, N Kim2, H J Choi3. 1. Department of Radiology, Kyung Hee University Hospital, Seoul, South Korea. 2. Department of Convergence Medicine, Biomedical Engineering Research Center, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea. 3. Department of Radiology, Seoul National University College of Medicine, and Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, South Korea. Electronic address: hjcbnbc@naver.com.
Abstract
AIM: To investigate the diagnostic performance and usefulness of texture analysis in differentiating angiomyolipoma (AML) without visible fat from clear cell renal cell carcinoma (ccRCC) on four-phase contrast-enhanced computed tomography (CECT). MATERIALS AND METHODS: Seventeen patients with AML without visible fat and 50 patients with ccRCC of size ≤4.5 cm who had also undergone preoperative four-phase CECT were included in this study. The histogram, grey-level co-occurrence matrix (GLCM), and grey-level run length matrix (GLRLM) were evaluated. Sequential feature selection (SFS) and support vector machine (SVM) classifier with leave-one-out cross validation were used. RESULTS: Using the SFS and SVM classifiers, five texture features were selected; mean (unenhanced), standard deviation (unenhanced and excretory), cluster prominence (nephrographic), and long-run high grey-level emphasis (corticomedullary). Diagnostic performance of the five selected texture features for all CT phases was as follows: 82% sensitivity, 76% specificity, 85% accuracy, and 85 area under the receiver operating characteristic curve (AUC). In the subgroup analysis, the AUCs of each phase were significantly >0.5 (p<0.05). In the pairwise comparison of AUCs between four phases, there were no significant differences between the four phases except the unenhanced and corticomedullary phases (p=0.015), i.e., the unenhanced phase showed slightly higher AUC than the corticomedullary phase. CONCLUSIONS: Texture analysis of small renal masses (≤4.5 cm) on four-phase CECT can accurately differentiate AML without visible fat from ccRCC and showed good diagnostic performance for both the unenhanced and enhanced phases.
AIM: To investigate the diagnostic performance and usefulness of texture analysis in differentiating angiomyolipoma (AML) without visible fat from clear cell renal cell carcinoma (ccRCC) on four-phase contrast-enhanced computed tomography (CECT). MATERIALS AND METHODS: Seventeen patients with AML without visible fat and 50 patients with ccRCC of size ≤4.5 cm who had also undergone preoperative four-phase CECT were included in this study. The histogram, grey-level co-occurrence matrix (GLCM), and grey-level run length matrix (GLRLM) were evaluated. Sequential feature selection (SFS) and support vector machine (SVM) classifier with leave-one-out cross validation were used. RESULTS: Using the SFS and SVM classifiers, five texture features were selected; mean (unenhanced), standard deviation (unenhanced and excretory), cluster prominence (nephrographic), and long-run high grey-level emphasis (corticomedullary). Diagnostic performance of the five selected texture features for all CT phases was as follows: 82% sensitivity, 76% specificity, 85% accuracy, and 85 area under the receiver operating characteristic curve (AUC). In the subgroup analysis, the AUCs of each phase were significantly >0.5 (p<0.05). In the pairwise comparison of AUCs between four phases, there were no significant differences between the four phases except the unenhanced and corticomedullary phases (p=0.015), i.e., the unenhanced phase showed slightly higher AUC than the corticomedullary phase. CONCLUSIONS: Texture analysis of small renal masses (≤4.5 cm) on four-phase CECT can accurately differentiate AML without visible fat from ccRCC and showed good diagnostic performance for both the unenhanced and enhanced phases.