Exploring the Acceleration Limits of Deep Learning Variational Network-based Two-dimensional Brain MRI
Alireza Radmanesh1, Matthew J Muckley1, Tullie Murrell1
1Department of Radiology, NYU School of Medicine-NYU Langone Health, New York, NY (A.R., E.L., D.K.S., Y.W.L.); Meta AI, Facebook, 770 Broadway, 2nd Floor, New York, NY 10003 (M.J.M.); Stealth, New York, NY (T.M.); Department of Artificial Intelligence Research, Meta AI, Facebook, Menlo Park, Calif (A.S.); and Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany (F.K.).
Purpose:
To explore the limits of deep learning-based brain MRI reconstruction and identify useful acceleration ranges for general-purpose imaging and potential screening.
Materials And Methods:
In this retrospective study conducted from 2019 through 2021, a model was trained for reconstruction on 5847 brain MR images. Performance was evaluated across a wide range of accelerations (up to 100-fold along a single phase-encoded direction for two-dimensional [2D] sections) on the fastMRI test set collected at New York University, consisting of 558 image volumes. In a sample of 69 volumes, reconstructions were classified by radiologists for identification of two clinical thresholds: (a) general-purpose diagnostic imaging and (b) potential use in a screening protocol. A Monte Carlo procedure was developed to estimate reconstruction error with only undersampled data. The model was evaluated on both in-domain and out-of-domain data. The 95% CIs were calculated using the percentile bootstrap method.
Results:
Radiologists rated 100% of 69 volumes as having sufficient image quality for general-purpose imaging at up to 4× acceleration and 65 of 69 volumes (94%) as having sufficient image quality for screening at up to 14× acceleration. The Monte Carlo procedure estimated ground truth peak signal-to-noise ratio and mean squared error with coefficients of determination greater than 0.5 at 2× to 20× acceleration levels. Out-of-distribution experiments demonstrated the model's ability to produce images substantially distinct from the training set, even at 100× acceleration.
Conclusion:
For 2D brain images using deep learning-based reconstruction, maximum acceleration for potential screening was three to four times higher than that for diagnostic general-purpose imaging.Keywords: MRI Reconstruction, High Acceleration, Deep Learning, Screening, Out of Distribution Supplemental material is available for this article. © RSNA, 2022.
