Deep Learning-Enhanced Single Breath-Hold Abdominal MRI at 0.55 T-Technical Feasibility and Image Quality Assessment.
Authors
Affiliations (3)
Affiliations (3)
- Department of Radiology, University Hospital Basel, Basel, Switzerland (A.C.S., H.C.B., M.M.O., A.K., D.T.B., J.V.).
- Research & Clinical Translation, Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany (M.D.N., M.F.).
- Department of Radiology, University Hospital Basel, Basel, Switzerland (A.C.S., H.C.B., M.M.O., A.K., D.T.B., J.V.). Electronic address: [email protected].
Abstract
Inherently lower signal-to-noise ratios hamper the broad clinical use of low-field abdominal MRI. This study aimed to investigate the technical feasibility and image quality of deep learning (DL)-enhanced T2 HASTE and T1 VIBE-Dixon abdominal MRI at 0.55 T. From July 2024 to September 2024, healthy volunteers underwent conventional and DL-enhanced 0.55 T abdominal MRI, including conventional T2 HASTE, fat-suppressed T2 HASTE (HASTE FS), and T1 VIBE-Dixon acquisitions, and DL-enhanced single- (HASTE DL<sub>SBH</sub>) and multi-breath-hold HASTE (HASTE DL<sub>MBH</sub>), fat-suppressed single- (HASTE FS DL<sub>SBH</sub>) and multi-breath-hold HASTE (HASTE FS DL<sub>MBH</sub>), and T1 VIBE-Dixon (VIBE-Dixon<sub>DL</sub>) acquisitions. Three abdominal radiologists evaluated the scans for quality parameters and artifacts (Likert scale 1-5), and incidental findings. Interreader agreement and comparative analyses were conducted. 33 healthy volunteers (mean age: 30±4years) were evaluated. Image quality was better for single breath-hold DL-enhanced MRI (all P<0.001) with good or better interreader agreement (κ≥0.61), including T2 HASTE (HASTE DL<sub>SBH</sub>: 4 [IQR: 4-4] vs. HASTE: 3 [3-3]), T2 HASTE FS (4 [4-4] vs. 3 [3-3]), and T1 VIBE-Dixon (4 [4-5] vs. 4 [3-4]). Similarly, image noise and spatial resolution were better for DL-MRI scans (P<0.001). No quality differences were found between single- and multi-breath-hold HASTE DL or HASTE FS DL (both: 4 [4-4]; P>0.572). The number and size of incidental lesions were identical between techniques (16 lesions; mean diameter 8±5 mm; P=1.000). DL-based image reconstruction enables single breath-hold T2 HASTE and T1 VIBE-Dixon abdominal imaging at 0.55 T with better image quality than conventional MRI.