Uncertainty‐aware physics‐driven deep learning network for free‐breathing liver fat and R₂* quantification using self‐gated stack‐of‐radial <scp>MRI</scp>

Abstract

Purpose To develop a deep learning‐based method for rapid liver proton‐density fat fraction (PDFF) and R 2 * quantification with built‐in uncertainty estimation using self‐gated free‐breathing stack‐of‐radial MRI. Methods This work developed an uncertainty‐aware physics‐driven deep learning network (UP‐Net) to (1) suppress radial streaking artifacts because of undersampling after self‐gating, (2) calculate accurate quantitative maps, and (3) provide pixel‐wise uncertainty maps. UP‐Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat–water and R 2 * signal model. UP‐Net was trained and tested using free‐breathing multi‐echo stack‐of‐radial MRI data from 105 subjects. UP‐Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R 2 * in a testing dataset. Results Compared with images reconstructed using compressed sensing (CS), UP‐Net achieved structural similarity index &gt;0.87 and normalized root mean squared error &lt;0.18. Compared with reference quantitative maps generated using CS and graph‐cut (GC) algorithms, UP‐Net achieved low mean differences (MD) for liver PDFF (−0.36%) and R 2 * (−0.37 s −1 ). Compared with breath‐holding Cartesian MRI results, UP‐Net achieved low MD for liver PDFF (0.53%) and R 2 * (6.75 s −1 ). UP‐Net uncertainty scores predicted absolute liver PDFF and R 2 * errors with low MD of 0.27% and 0.12 s −1 compared to CS + GC results. The computational time for UP‐Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice. Conclusion UP‐Net rapidly calculates accurate liver PDFF and R 2 * maps from self‐gated free‐breathing stack‐of‐radial MRI. The pixel‐wise uncertainty maps from UP‐Net predict quantification errors in the liver.

Topics & Concepts