Can Quantitative CT Texture Analysis be Used to Differentiate Fat-poor Renal Angiomyolipoma from Renal Cell Carcinoma on Unenhanced CT Images?
Can Quantitative CT Texture Analysis be Used to Differentiate Fat-poor Renal Angiomyolipoma from Renal Cell Carcinoma on Unenhanced CT Images?
复制标题
DOI：
10.1148/radiol.2015142215
复制
发表时间：
2015-09-01
期刊：
影响因子：
19.7
通讯作者：
Thornhill, Rebecca E.
中科院分区：
文献类型：
--
作者：
Hodgdon, Taryn;McInnes, Matthew D. F.;Thornhill, Rebecca E.
目的：为了确定纹理分析的准确性，以区分脂肪贫乏的血管平滑肌脂肪瘤（fp-AML）从肾细胞癌（RCC）的非增强计算机断层扫描（CT）images.Materials and Methods：在这个机构审查委员会批准的回顾性病例对照研究中，AML和RCC患者从病理数据库中确定：16例fp-AML患者（未增强CT时无可见脂肪）和84例RCC患者。轴向非增强CT图像由两名独立分析员手动绘制轮廓。对每个病变进行纹理分析，并评估再现性。纹理特征相关的灰度直方图，灰度共生，游程矩阵统计进行了评估。最具鉴别力的特征被用来生成支持向量机（SVM）分类器。纹理特征的诊断准确性进行了评估，并进行了10倍交叉验证。每例患者的非增强CT图像由两名盲法放射科医生独立审查，他们在五点量表上主观地对病变异质性进行分级。采用DeLong方法评价主观异质性评分和纹理特征之间的受试者工作特征曲线下面积（AUC）的差异。结果：RCC的病变均匀性较低，病变熵较高（P > .01）。一个模型结合了几个纹理特征，导致AUC为0.89 +/- 0.04。纹理特征的平均SVM准确度范围为83%至91%（经过10倍交叉验证）。最佳主观异质性评级为2或更高被确定为两名阅片者的RCC预测因子，阅片者之间的AUC无显著差异（P = 0.06）。三个基于纹理的分类器中的每一个都比放射科医生对模型的主观异质性评级更准确，该模型包含前三个纹理特征的子集（纹理特征和主观视觉异质性之间的AUC差异，0.25; 95%置信区间：0.02，0.47; P = 0.03）。CT纹理分析可用于在平扫CT图像上准确区分fp-AML和RCC。(C)RSNA，2015年
Purpose: To determine the accuracy of texture analysis to differentiate fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma (RCC) on unenhanced computed tomography (CT) images.Materials and Methods: In this institutional review board-approved retrospective case-control study, patients with AML and RCC were identified from the pathology database: there were 16 patients with fp-AML (no visible fat at unenhanced CT) and 84 patients with RCC. Axial unenhanced CT images were contoured manually by two independent analysts. Texture analysis was performed for each lesion, and reproducibility was assessed. Texture features related to the gray-level histogram, gray-level co-occurrence, and run-length matrix statistics were evaluated. The most discriminative features were used to generate support vector machine (SVM) classifiers. Diagnostic accuracy of textural features was assessed and 10-fold cross validation was performed. Unenhanced CT images for each patient were independently reviewed by two blinded radiologists who subjectively graded lesion heterogeneity on a five-point scale. Differences in area under the receiver operating characteristic curve (AUC) between subjective heterogeneity ratings and textural features were evaluated by using the DeLong method.Results: There was lower lesion homogeneity and higher lesion entropy in RCCs (P > .01). A model incorporating several texture features resulted in an AUC of 0.89 +/- 0.04. The average SVM accuracy of textural features ranged from 83% to 91% (after 10-fold cross validation). An optimal subjective heterogeneity rating of 2 or higher was identified as a predictor of RCC for both readers, with no significant difference in AUC between readers (P = .06). Each of the three textural-based classifiers was more accurate than either radiologists' subjective heterogeneity ratings for the models incorporating a subset of the top three textural features (difference in AUC between textural features and subjective visual heterogeneity, 0.25; 95% confidence interval: 0.02, 0.47; P = .03).Conclusion: CT texture analysis can be used to accurately differentiate fp-AML from RCC on unenhanced CT images. (C) RSNA, 2015