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

Lee, Han Sang; Hong, Helen; Jung, Dae Chul; Park, Seung Hyun; Kim, Jun mo

doi:10.1002/mp.12258

Cited by 51 publications

(32 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bektas et al [29] used different machine learning classifiers, such as SVM, MLP, RF, kNN, and naive Bayes, for predicting Fuhrman nuclear grade of clear cell renal cell carcinomas (ccRCCs), and the best model was created using SVM (AUC = 0.851, accuracy = 0.913). Lee et al [30] combined different feature selection methods and different feature classifiers, which included SVM, RF, kNN and LR, to distinguish benign fat-poor angiomyolipoma from malignant ccRCC. kNN and SVM classifiers with ReliefF feature selection achieved the best accuracy of 72.3 ± 4.6% and 72.1 ± 4.2%, respectively.…”

Section: Discussionmentioning

confidence: 99%

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

Huang

Xia³

2019

Abdom Radiol

View full text Add to dashboard Cite

Purpose To explore the value of CT-enhanced quantitative features combined with machine learning for differential diagnosis of renal chromophobe cell carcinoma (chRCC) and renal oncocytoma (RO). Methods Sixty-one cases of renal tumors (chRCC = 44; RO = 17) that were pathologically confirmed at our hospital between 2008 and 2018 were retrospectively analyzed. All patients had undergone preoperative enhanced CT scans including the corticomedullary (CMP), nephrographic (NP), and excretory phases (EP) of contrast enhancement. Volumes of interest (VOIs), including lesions on the images, were manually delineated using the RadCloud platform. A LASSO regression algorithm was used to screen the image features extracted from all VOIs. Five machine learning classifications were trained to distinguish chRCC from RO by using a fivefold cross-validation strategy. The performance of the classifier was mainly evaluated by areas under the receiver operating characteristic (ROC) curve and accuracy. Results In total, 1029 features were extracted from CMP, NP, and EP. The LASSO regression algorithm was used to screen out the four, four, and six best features, respectively, and eight features were selected when CMP and NP were combined. All five classifiers had good diagnostic performance, with area under the curve (AUC) values greater than 0.850, and support vector machine (SVM) classifier showed a diagnostic accuracy of 0.945 (AUC 0.964 ± 0.054; sensitivity 0.999; specificity 0.800), showing the best performance. Conclusions Accurate preoperative differential diagnosis of chRCC and RO can be facilitated by a combination of CTenhanced quantitative features and machine learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

Huang

Xia³

2019

Abdom Radiol

View full text Add to dashboard Cite

show abstract

“…Our HCF T include seven histogram features (the mean, standard deviation, minimum and maximum intensities, skewness, kurtosis, and entropy), 6 percentages of pixels above certain thresholds, 5 percentile intensities, 14 GLCM, 22 GLRLM, and 10 LBP features. These HCF T have been reported to show meaningful differences between ccRCC and AMLwvf, although AMLwvf is scarcely distinguishable from RCC visually due to its low fat content …”

Section: Methodsmentioning

confidence: 98%

“…These HCF T have been reported to show meaningful differences between ccRCC and AMLwvf, although AMLwvf is scarcely distinguishable from RCC visually due to its low fat content. 22 In the seven-dimensional shape HCF (HCF S ), the features related to the shape of the mass, including the roundness and the curvature, were extracted. The HCF S provides important information about the mass by reflecting certain characteristics of the relationship between the kidney and the mass, such as the degree of invasion of the mass.…”

Section: B Hand-crafted Features Of Texture and Shapementioning

confidence: 99%

“…In these studies of HCFs, several predefined features were selected and assessed based on radiologists’ expert knowledge about the disease. While the HCFs of patient information, enhancement patterns, and shape were mostly analyzed qualitatively for one‐to‐one statistical associations with the disease individually, the texture features were mainly analyzed quantitatively for the classification of different masses . From these assessment and validation processes, the features related to texture inhomogeneities and the mass shapes were suggested as the main characteristics for differentiating SRMs; ccRCC is generally known to have greater inhomogeneity in terms of the texture, and it has a more rounded appearance in terms of the shape as compared to AMLwvf.…”

Section: Introductionmentioning

confidence: 99%

“…While the HCFs of patient information, enhancement patterns, and shape were mostly analyzed qualitatively for oneto-one statistical associations with the disease individually, the texture features were mainly analyzed quantitatively for the classification of different masses. 21,22 From these assessment and validation processes, the features related to texture inhomogeneities and the mass shapes were suggested as the main characteristics for differentiating SRMs; ccRCC is generally known to have greater inhomogeneity in terms of the texture, and it has a more rounded appearance in terms of the shape as compared to AMLwvf. The advantage of HCFs is that they can analyze features that reflect expert knowledge by selecting features suitable for a given problem among various predefined features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

Differentiating Benign from Malignant Renal Tumors Using T2‐ and Diffusion‐Weighted Images: A Comparison of Deep Learning and Radiomics Models Versus Assessment from Radiologists

Zhu

Líu³

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Differentiating benign from malignant renal tumors is important for selection of the most effective treatment. Purpose To develop magnetic resonance imaging (MRI)‐based deep learning (DL) models for differentiation of benign and malignant renal tumors and to compare their discrimination performance with the performance of radiomics models and assessment by radiologists. Study Type Retrospective. Population A total of 217 patients were randomly assigned to a training cohort (N = 173) or a testing cohort (N = 44). Field Strength/Sequence Diffusion‐weighted imaging (DWI) and fast spin‐echo sequence T2‐weighted imaging (T2WI) at 3.0T. Assessment A radiologist manually labeled the region of interest (ROI) on each image. Three DL models using ResNet‐18 architecture and three radiomics models using random forest were developed using T2WI alone, DWI alone, and a combination of the two image sets to discriminate between benign and malignant renal tumors. The diagnostic performance of two radiologists was assessed based on professional experience. We also compared the performance of each model and the radiologists. Statistical Tests The area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the performance of each model and the radiologists. P < 0.05 indicated statistical significance. Results The AUC of the DL models based on T2WI, DWI, and the combination was 0.906, 0.846, and 0.925 in the testing cohorts, respectively. The AUC of the combination DL model was significantly better than that of the models based on individual sequences (0.925 > 0.906, 0.925 > 0.846). The AUC of the radiomics models based on T2WI, DWI, and the combination was 0.824, 0.742, and 0.826 in the testing cohorts, respectively. The AUC of two radiologists was 0.724 and 0.667 in the testing cohorts. Conclusion Thus, the MRI‐based DL model is useful for differentiating benign from malignant renal tumors in clinic, and the DL model based on T2WI + DWI had the best performance. Level of Evidence 3 Technical Efficacy Stage 2

show abstract

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

Cited by 51 publications

References 25 publications

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

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

Differentiating Benign from Malignant Renal Tumors Using T2‐ and Diffusion‐Weighted Images: A Comparison of Deep Learning and Radiomics Models Versus Assessment from Radiologists

Contact Info

Product

Resources

About