Deep Learning-Enhanced T1-Weighted Imaging for Breast MRI at 1.5T.

: Assessment of a novel deep-learning (DL)-based T1w volumetric interpolated breath-hold (VIBE) sequence in breast MRI in comparison with standard VIBE (VIBE) for image quality evaluation. : Prospective study of 52 breast cancer patients examined at 1.5T breast MRI with T1w VIBE and T1 VIBE sequence. T1w VIBE was integrated as an additional early non-contrast and a delayed post-contrast scan. Two radiologists independently scored T1w VIBE sequences both pre- and post-contrast and their calculated subtractions (SUBs) for image quality, sharpness, (motion)-artifacts, perceived signal-to-noise and diagnostic confidence with a Likert-scale from 1: Non-diagnostic to 5: Excellent. Lesion diameter was evaluated on the SUB for T1w VIBE/. All lesions were visually evaluated in T1w VIBE/ pre- and post-contrast and their subtractions. Statistics included correlation analyses and paired t-tests. : Significantly higher Likert scale values were detected in the pre-contrast T1w VIBE compared to the T1w VIBE for image quality (each < 0.001), image sharpness ( < 0.001), SNR ( < 0.001), and diagnostic confidence ( < 0.010). Significantly higher values for image quality ( < 0.001 in each case), image sharpness ( < 0.001), SNR ( < 0.001), and artifacts ( < 0.001) were detected in the post-contrast T1w VIBE and in the SUB. SUB provided superior diagnostic certainty compared to SUB in one reader ( = 0.083 or = 0.004). : Deep learning-enhanced T1w VIBE at 1.5T breast MRI offers superior image quality compared to T1w VIBE.