Accelerating Cardiac Diffusion Tensor Imaging With a U-Net Based Model: Toward Single Breath-Hold.

Abstract

In vivo cardiac diffusion tensor imaging (cDTI) characterizes myocardial microstructure. Despite its potential clinical impact, considerable technical challenges exist due to the inherent low signal-to-noise ratio. To reduce scan time toward one breath-hold by reconstructing diffusion tensors for in vivo cDTI with a fitting-free deep learning approach. Retrospective. A total of 197 healthy controls, 547 cardiac patients. A 3 T, diffusion-weighted stimulated echo acquisition mode single-shot echo-planar imaging sequence. A U-Net was trained to reconstruct the diffusion tensor elements of the reference results from reduced datasets that could be acquired in 5, 3 or 1 breath-hold(s) (BH) per slice. Fractional anisotropy (FA), mean diffusivity (MD), helix angle (HA), and sheetlet angle (E2A) were calculated and compared to the same measures when using a conventional linear-least-square (LLS) tensor fit with the same reduced datasets. A conventional LLS tensor fit with all available data (12 ± 2.0 [mean ± sd] breath-holds) was used as the reference baseline. Wilcoxon signed rank/rank sum and Kruskal-Wallis tests. Statistical significance threshold was set at P=0.05. Intersubject measures are quoted as median [interquartile range]. For global mean or median results, both the LLS and U-Net methods with reduced datasets present a bias for some of the results. For both LLS and U-Net, there is a small but significant difference from the reference results except for LLS: MD 5BH (P=0.38) and MD 3BH (P=0.09). When considering direct pixel-wise errors the U-Net model outperformed significantly the LLS tensor fit for reduced datasets that can be acquired in three or just one breath-hold for all parameters. Diffusion tensor prediction with a trained U-Net is a promising approach to minimize the number of breath-holds needed in clinical cDTI studies. 4 TECHNICAL EFFICACY: Stage 1.