Deep feature classification of angiomyolipoma without visible fat and renal cell carcinoma in abdominal contrast-enhanced CT images with texture image patches and hand-crafted feature concatenation.

To develop an automatic deep feature classification (DFC) method for distinguishing benign angiomyolipoma without visible fat (AMLwvf) from malignant clear cell renal cell carcinoma (ccRCC) from abdominal contrast-enhanced computer tomography (CE CT) images. A dataset including 80 abdominal CT images of 39 AMLwvf and 41 ccRCC patients was used. We proposed a DFC method for differentiating the small renal masses (SRM) into AMLwvf and ccRCC using the combination of hand-crafted and deep features, and machine learning classifiers. First, 71-dimensional hand-crafted features (HCF) of texture and shape were extracted from the SRM contours. Second, 1000-4000-dimensional deep features (DF) were extracted from the ImageNet pretrained deep learning model with the SRM image patches. In DF extraction, we proposed the texture image patches (TIP) to emphasize the texture information inside the mass in DFs and reduce the mass size variability. Finally, the two features were concatenated and the random forest (RF) classifier was trained on these concatenated features to classify the types of SRMs. The proposed method was tested on our dataset using leave-one-out cross-validation and evaluated using accuracy, sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV), and area under receiver operating characteristics curve (AUC). In experiments, the combinations of four deep learning models, AlexNet, VGGNet, GoogleNet, and ResNet, and four input image patches, including original, masked, mass-size, and texture image patches, were compared and analyzed. In qualitative evaluation, we observed the change in feature distributions between the proposed and comparative methods using tSNE method. In quantitative evaluation, we evaluated and compared the classification results, and observed that (a) the proposed HCF + DF outperformed HCF-only and DF-only, (b) AlexNet showed generally the best performances among the CNN models, and (c) the proposed TIPs not only achieved the competitive performances among the input patches, but also steady performance regardless of CNN models. As a result, the proposed method achieved the accuracy of 76.6 ± 1.4% for the proposed HCF + DF with AlexNet and TIPs, which improved the accuracy by 6.6%p and 8.3%p compared to HCF-only and DF-only, respectively. The proposed shape features and TIPs improved the HCFs and DFs, respectively, and the feature concatenation further enhanced the quality of features for differentiating AMLwvf from ccRCC in abdominal CE CT images.

Lee H ，Hong H ，Kim J ，Jung DC ... -  《-》

Differentiation of fat-poor angiomyolipoma from clear cell renal cell carcinoma in contrast-enhanced MDCT images using quantitative feature classification.

To develop a computer-aided classification system to differentiate benign fat-poor angiomyolipoma (fp-AML) from malignant clear cell renal cell carcinoma (ccRCC) using quantitative feature classification on histogram and texture patterns from contrast-enhanced multidetector computer tomography (CE MDCT) images. A dataset including 50 CE MDCT images of 25 fp-AML and 25 ccRCC patients was used. From these images, the tumors were manually segmented by an expert radiologist to define the regions of interest (ROI). A feature classification system was proposed for separating two types of renal masses, using histogram and texture features and machine learning classifiers. First, 64 quantitative image features, including histogram features based on basic histogram characteristics, percentages of pixels above the thresholds, percentile intensities, and texture features based on gray-level co-occurrence matrices (GLCM), gray-level run-length matrices (GLRLM), and local binary patterns (LBP), were extracted from each ROI. A number of feature selection methods including stepwise feature selection (SFS), ReliefF selection, and principal component analysis (PCA) transformation, were applied to select the group of useful features. Finally, the feature classifiers including logistic regression, k nearest neighbors (kNN), support vector machine (SVM), and random forest (RF), were trained on the selected features to differentiate benign fp-AML from malignant ccRCC. Each combination of feature selection and classification methods was tested using a fivefold cross-validation method and evaluated using accuracy, sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV), and area under receiver operating characteristic curve (AUC). In feature selection, the features commonly selected by different feature selection methods were assessed. From three selection methods, three histogram features including maximum intensity, percentages of pixels above the thresholds 210 and 230, and one texture feature of GLCM sum entropy, were jointly selected as key features to distinguish two types of renal masses. In feature classification, kNN and SVM classifiers with ReliefF feature selection demonstrated the best performance among other choices of feature selection and classification methods, where ReliefF+kNN and ReliefF+SVM achieved the accuracy of 72.3 ± 4.6% and 72.1 ± 4.2%, respectively. We propose a computer-aided classification system for distinguishing fp-AML from ccRCC using machine learning classifiers with quantitative texture features. Our contribution is to investigate the proper combination between the quantitative features and classification systems on the CE MDCT images. In experiments, it can be demonstrated that (a) the features based on histogram characteristics on bright intensity region and texture patterns on inhomogeneity inside masses were selected as key features to classify fp-AML and ccRCC, and (b) the proper combination of feature selection and classification methods achieved high performance in differentiating benign from malignant masses. The proposed classification system can be used to assess the useful features associated with the malignancy for renal masses in CE MDCT images.

Lee HS ，Hong H ，Jung DC ，Park S ，Kim J ... -  《-》

Radiomics of small renal masses on multiphasic CT: accuracy of machine learning-based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat.

Yang R ，Wu J ，Sun L ，Lai S ，Xu Y ，Liu X ，Ma Y ，Zhen X ... -  《-》

Machine learning-based quantitative texture analysis of CT images of small renal masses: Differentiation of angiomyolipoma without visible fat from renal cell carcinoma.

Feng Z ，Rong P ，Cao P ，Zhou Q ，Zhu W ，Yan Z ，Liu Q ，Wang W ... -  《-》

The value of quantitative CT texture analysis in differentiation of angiomyolipoma without visible fat from clear cell renal cell carcinoma on four-phase contrast-enhanced CT images.

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.

You MW ，Kim N ，Choi HJ 《-》