| Abstract: | Background: Histological fibrosis stage is the most important prognostic factor in chronic liver disease. MR elastography (MRE) is the most accurate noninvasive method for detecting and staging liver fibrosis. Although accurate, manual ROI-based MRE analysis is complex, time consuming, requires specialized readers, and prone to methodologic variability and suboptimal inter-reader agreement. Objectives: To develop an automated convolutional neural network (CNN)-based method for liver MRE analysis, evaluate its agreement with manual ROI-based analysis, and assess its discriminative performance for dichotomized fibrosis stages using histology as reference standard. Methods: In this retrospective cross-sectional study, 675 participants who underwent MRE using different MRI systems and field strengths at 28 imaging sites from five multicenter international clinical trials of nonalcoholic steatohepatitis were included for algorithm development and internal testing of agreement between automated CNN- and manual ROI-based analyses. Eighty-one patients (52 women, 29 men; mean age, 54 years) who underwent MRE using a single 3-Tesla system and liver biopsy for clinical purposes at a single institution were included for external testing of agreement and assessment of fibrosis stage discriminative performance. Agreement was evaluated using intra-class correlation coefficients (ICC). 95% CIs were computed using bootstrapping. Discriminative performance of each method for dichotomized histologic fibrosis stage was evaluated by AUC and compared using bootstrapping. Results: Mean CNN- and manual ROI-based stiffness measurements ranged from 3.21 to 3.34 kPa in trial participants and from 3.30 to 3.45 kPa in clinical patients. ICC for CNN- and manual ROI-based measurements was 0.98 (95% CI, 0.978-0.98) in trial participants and 0.99 (95% CI: 0.98-0.99) in clinical patients. AUC for classification of dichotomized fibrosis stage ranged from 0.89-0.93 for CNN- and 0.87-0.93 for manual ROI-based analyses (p=.23-.75). Conclusion: Stiffness measurements using the automated CNN-based method agreed strongly with manual ROIbased analysis across MRI systems and field strengths, with excellent discriminative performance for histology-determined dichotomized fibrosis stages in external testing. Clinical Impact: Given the high incidence of chronic liver disease worldwide, it is important that noninvasive tools to assess fibrosis are applied reliably across different settings. CNN-based analysis is feasible and may reduce reliance on expert image analysts. |
