Leveraging a vendor-neutral deep learning reconstruction algorithm to reduce scan time and enhance image quality in T2-weighted liver MRI

Retrospective study of 86 patients showing that accelerated single-breath-hold T2-weighted liver MRI reconstructed with SwiftMR achieved significantly higher sharpness and signal-to-noise ratio than the routine two-breath-hold protocol (p < 0.001), with higher lesion conspicuity in patients with focal liver lesions — enabling a single breath-hold in place of two while shortening acquisition time.

Jeong B, Kim S. Sci Rep. 2026 (in press). DOI: 10.1038/s41598-026-60802-5.