Department of Radiology, Kyung Hee University Hospital, Seoul, South Korea.
Department of Convergence Medicine, Biomedical Engineering Research Center, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea.
Clin Radiol. 2019 Jul;74(7):547-554. doi: 10.1016/j.crad.2019.02.018. Epub 2019 Apr 20.
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).
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.
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.
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.
探讨纹理分析在四期增强 CT 成像中鉴别无脂肪可见的血管平滑肌脂肪瘤（AML）与小肾细胞癌（ccRCC）的诊断性能和实用性。
本研究纳入了 17 例无脂肪可见的 AML 患者和 50 例大小≤4.5cm 的 ccRCC 患者，所有患者均接受了术前四期 CT 增强检查。评估了直方图、灰度共生矩阵（GLCM）和灰度游程长度矩阵（GLRLM）。采用顺序特征选择（SFS）和支持向量机（SVM）分类器进行留一法交叉验证。
使用 SFS 和 SVM 分类器，共选择了 5 个纹理特征，包括平扫（unenhanced）、平扫（unenhanced）及排泄期标准差、肾实质期聚类突出度（nephrographic）和皮质期长灰度级强调（long-run high grey-level emphasis）。这 5 个纹理特征在所有 CT 期的诊断性能为：82%的敏感性、76%的特异性、85%的准确性和 85%的受试者工作特征曲线下面积（area under the receiver operating characteristic curve，AUC）。在亚组分析中，各期的 AUC 均显著>0.5（p<0.05）。在四期之间的 AUC 两两比较中，除平扫期和皮质期外（p=0.015），其余各期之间无显著差异，即平扫期的 AUC 略高于皮质期。
四期增强 CT 成像中小肾肿块（≤4.5cm）的纹理分析可准确鉴别无脂肪可见的 AML 与 ccRCC，对平扫期和增强期均具有良好的诊断性能。
