Dataset Information

Noninvasive Diagnosis of Nonalcoholic Fatty Liver Disease and Quantification of Liver Fat with Radiofrequency Ultrasound Data Using One-dimensional Convolutional Neural Networks.

ABSTRACT: Background Radiofrequency ultrasound data from the liver contain rich information about liver microstructure and composition. Deep learning might exploit such information to assess nonalcoholic fatty liver disease (NAFLD). Purpose To develop and evaluate deep learning algorithms that use radiofrequency data for NAFLD assessment, with MRI-derived proton density fat fraction (PDFF) as the reference. Materials and Methods A HIPAA-compliant secondary analysis of a single-center prospective study was performed for adult participants with NAFLD and control participants without liver disease. Participants in the parent study were recruited between February 2012 and March 2014 and underwent same-day US and MRI of the liver. Participants were randomly divided into an equal number of training and test groups. The training group was used to develop two algorithms via cross-validation: a classifier to diagnose NAFLD (MRI PDFF ≥ 5%) and a fat fraction estimator to predict MRI PDFF. Both algorithms used one-dimensional convolutional neural networks. The test group was used to evaluate the classifier for sensitivity, specificity, positive predictive value, negative predictive value, and accuracy and to evaluate the estimator for correlation, bias, limits of agreements, and linearity between predicted fat fraction and MRI PDFF. Results A total of 204 participants were analyzed, 140 had NAFLD (mean age, 52 years ± 14 [standard deviation]; 82 women) and 64 were control participants (mean age, 46 years ± 21; 42 women). In the test group, the classifier provided 96% (95% confidence interval [CI]: 90%, 99%) (98 of 102) accuracy for NAFLD diagnosis (sensitivity, 97% [95% CI: 90%, 100%], 68 of 70; specificity, 94% [95% CI: 79%, 99%], 30 of 32; positive predictive value, 97% [95% CI: 90%, 99%], 68 of 70; negative predictive value, 94% [95% CI: 79%, 98%], 30 of 32). The estimator-predicted fat fraction correlated with MRI PDFF (Pearson r = 0.85). The mean bias was 0.8% (P = .08), and 95% limits of agreement were -7.6% to 9.1%. The predicted fat fraction was linear with an MRI PDFF of 18% or less (r = 0.89, slope = 1.1, intercept = 1.3) and nonlinear with an MRI PDFF greater than 18%. Conclusion Deep learning algorithms using radiofrequency ultrasound data are accurate for diagnosis of nonalcoholic fatty liver disease and hepatic fat fraction quantification when other causes of steatosis are excluded. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Lockhart and Smith in this issue.

SUBMITTER: Han A

PROVIDER: S-EPMC7193902 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND & AIMS:Liver biopsy analysis is the standard method used to diagnose nonalcoholic fatty liver disease (NAFLD). Advanced magnetic resonance imaging is a noninvasive procedure that can accurately diagnose and quantify steatosis, but is expensive. Conventional ultrasound is more accessible but identifies steatosis with low levels of sensitivity, specificity, and quantitative accuracy, and results vary among technicians. A new quantitative ultrasound (QUS) technique can identify steatosis in animal models. We assessed the accuracy of QUS in the diagnosis and quantification of hepatic steatosis, comparing findings with those from magnetic resonance imaging proton density fat fraction (MRI-PDFF) analysis as a reference. METHODS:We performed a prospective, cross-sectional analysis of a cohort of adults (N = 204) with NAFLD (MRI-PDFF, ?5%) and without NAFLD (controls). Subjects underwent MRI-PDFF and QUS analyses of the liver on the same day at the University of California, San Diego, from February 2012 through March 2014. QUS parameters and backscatter coefficient (BSC) values were calculated. Patients were assigned randomly to training (n = 102; mean age, 51 ± 17 y; mean body mass index, 31 ± 7 kg/m(2)) and validation (n = 102; mean age, 49 ± 17 y; body mass index, 30 ± 6 kg/m(2)) groups; 69% of patients in each group had NAFLD. RESULTS:BSC (range, 0.00005-0.25 1/cm-sr) correlated with MRI-PDFF (Spearman ? = 0.80; P < .0001). In the training group, the BSC analysis identified patients with NAFLD with an area under the curve value of 0.98 (95% confidence interval, 0.95-1.00; P < .0001). The optimal BSC cut-off value identified patients with NAFLD in the training and validation groups with 93% and 87% sensitivity, 97% and 91% specificity, 86% and 76% negative predictive values, and 99% and 95% positive predictive values, respectively. CONCLUSIONS:QUS measurements of BSC can accurately diagnose and quantify hepatic steatosis, based on a cross-sectional analysis that used MRI-PDFF as the reference. With further validation, QUS could be an inexpensive, widely available method to screen the general or at-risk population for NAFLD.

Project description:ObjectiveTo investigate the diagnostic performance of quantitative ultrasound (US) parameters for the assessment of hepatic steatosis in patients with nonalcoholic fatty liver disease (NAFLD) using magnetic resonance imaging proton density fat fraction (MRI-PDFF) as the reference standard.Materials and methodsIn this single-center prospective study, 120 patients with clinically suspected NAFLD were enrolled between March 2019 and January 2020. The participants underwent US examination for radiofrequency (RF) data acquisition and chemical shift-encoded liver MRI for PDFF measurement. Using the RF data analysis, the attenuation coefficient (AC) based on tissue attenuation imaging (TAI) (AC-TAI) and scatter-distribution coefficient (SC) based on tissue scatter-distribution imaging (TSI) (SC-TSI) were measured. The correlations between the quantitative US parameters (AC and SC) and MRI-PDFF were evaluated using Pearson correlation coefficients. The diagnostic performance of AC-TAI and SC-TSI for detecting hepatic fat contents of ≥ 5% (MRI-PDFF ≥ 5%) and ≥ 10% (MRI-PDFF ≥ 10%) were assessed using receiver operating characteristic (ROC) analysis. The significant clinical or imaging factors associated with AC and SC were analyzed using linear regression analysis.ResultsThe participants were classified based on MRI-PDFF: < 5% (n = 38), 5-10% (n = 23), and ≥ 10% (n = 59). AC-TAI and SC-TSI were significantly correlated with MRI-PDFF (r = 0.659 and 0.727, p < 0.001 for both). For detecting hepatic fat contents of ≥ 5% and ≥ 10%, the areas under the ROC curves of AC-TAI were 0.861 (95% confidence interval [CI]: 0.786-0.918) and 0.835 (95% CI: 0.757-0.897), and those of SC-TSI were 0.964 (95% CI: 0.913-0.989) and 0.935 (95% CI: 0.875-0.972), respectively. Multivariable linear regression analysis showed that MRI-PDFF was an independent determinant of AC-TAI and SC-TSI.ConclusionAC-TAI and SC-TSI derived from quantitative US RF data analysis yielded a good correlation with MRI-PDFF and provided good performance for detecting hepatic steatosis and assessing its severity in NAFLD.

Dataset Information

Noninvasive Diagnosis of Nonalcoholic Fatty Liver Disease and Quantification of Liver Fat with Radiofrequency Ultrasound Data Using One-dimensional Convolutional Neural Networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets