Magnetic Resonance Elastography of the Liver: A Single-Institution Review of Cases Performed in a 5-Year Interval.

OBJECTIVE: This study aimed to assess the diagnostic accuracy of magnetic resonance elastography (MRE) in detecting hepatic fibrosis and determining clinically relevant stiffness cutoff values per stage of fibrosis. METHODS: This retrospective study assessed 1488 hepatic MRE evaluations performed at a single institution for 5 years. Mean liver stiffness measurements were collected from 282 patients who had an MRE study within 1 year of histopathologic analysis. Areas under receiver operating characteristic curves were calculated for each stage of fibrosis with nonparametric ordinal measures of accuracy, and Youden Index was determined. RESULTS: Mean liver stiffness measurement values were as follows: F0, 2.5± 0.55 kPa; F1, 3.1± 0.80 kPa; F2, 3.4±0.95 kPa; F3, 4.7±1.44 kPa; and F4, 7.9± 2.64 kPa. Nonparametric ordinal measures of accuracy per fibrosis stage were as follows: F0: 0.934, P < 0.001; F0-F1: 0.917, P < 0.001; F0-F2: 0.944, P < 0.001; and F0-F3: 0.941, P < 0.001. Youden Index values for fibrosis stages F2, F3, and F4 were 3.9, 4.0, and 4.5 kPa, respectively. CONCLUSIONS: Magnetic resonance elastography is an accurate diagnostic tool in assessing liver fibrosis.

Deep Learning Prediction of Voxel-Level Liver Stiffness in Patients with Nonalcoholic Fatty Liver Disease.

PURPOSE: To reconstruct virtual MR elastography (MRE) images based on traditional MRI inputs with a machine learning algorithm. MATERIALS AND METHODS: In this single-institution, retrospective study, 149 patients (mean age, 58 years ± 12 [standard deviation]; 71 men) with nonalcoholic fatty liver disease who underwent MRI and MRE between January 2016 and January 2019 were evaluated. Nine conventional MRI sequences and clinical data were used to train a convolutional neural network to reconstruct MRE images at the per-voxel level. The architecture was further modified to accept multichannel three-dimensional inputs and to allow inclusion of clinical and demographic information. Liver stiffness and fibrosis category (F0 [no fibrosis] to F4 [significant fibrosis]) of reconstructed images were assessed by using voxel- and patient-level agreement by correlation, sensitivity, and specificity calculations; in addition, classification by receiver operator characteristic analyses was performed, and Dice score was used to evaluate hepatic stiffness locality. RESULTS: The model for predicting liver stiffness incorporated four image sequences (precontrast T1-weighted liver acquisition with volume acquisition [LAVA] water and LAVA fat, 120-second-delay T1-weighted LAVA water, and single-shot fast spin-echo T2 weighted) and clinical data. The model had a patient-level and voxel-level correlation of 0.50 ± 0.05 and 0.34 ± 0.03, respectively. By using a stiffness threshold of 3.54 kPa to make a binary classification into no fibrosis or mild fibrosis (F0-F1) versus clinically significant fibrosis (F2-F4), the model had sensitivity of 80% ± 4, specificity of 75% ± 5, accuracy of 78% ± 3, area under the receiver operating characteristic curve of 84 ± 0.04, and a Dice score of 0.74. CONCLUSION: The generation of virtual elastography images is feasible by using conventional MRI and clinical data with a machine learning algorithm.Keywords: MR Imaging, Abdomen/GI, Liver, Cirrhosis, Computer Applications/Virtual Imaging, Experimental Investigations, Feature Detection, Classification, Reconstruction Algorithms, Supervised Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2021.