Deep Learning-Based Superresolution Reconstruction for Upper Abdominal Magnetic Resonance Imaging

Objectives The aim of this study was to investigate the impact of a deep learning-based superresolution reconstruction technique for T1-weighted volume-interpolated breath-hold examination (VIBE SR ) on image quality in comparison with standard VIBE images (VIBE SD ). Methods Between May and August 2020, a total of 46 patients with various abdominal pathologies underwent contrast-enhanced upper abdominal VIBE magnetic resonance imaging (MRI) at 1.5 T. After data acquisition, the precontrast and postcontrast T1-weighted VIBE raw data were processed by a deep learning-based prototype algorithm for deblurring and denoising the images as well as for enhancing their sharpness (VIBE SR ). In a randomized and blinded manner, 2 radiologists independently analyzed the image data sets using the unprocessed images VIBE SD as a standard reference. Outcome measures were as follows: overall image quality, anatomic clarity of organ borders, sharpness of vessels, artifacts, noise, and diagnostic confidence. All ratings were performed on an ordinal 4-point Likert scale. If the MRI examination encompassed a hepatic lesion, the maximum diameter of the largest hepatic lesion was quantified, and lesion sharpness and conspicuity were evaluated on an ordinal 4-point Likert scale. In addition, a post hoc regression analysis for lesion evaluation was computed. Finally, interrater/intrarater agreement was analyzed. Results The overall image quality, anatomic clarity of organ borders, and sharpness of vessels in both precontrast and postcontrast images were rated significantly higher in VIBE SR than in VIBE SD ( P < 0.001). Similarly, diagnostic confidence was higher in VIBE SR than in VIBE SD ( P < 0.001). Furthermore, VIBE SR images were rated to have significantly less noise and fewer artifacts in comparison with VIBE SD ( P < 0.001). The interreader agreement was substantial with a Cohen κ of 0.72 for the precontrast analysis and a κ of 0.74 for the postcontrast analysis. A total of 28 hepatic lesions were analyzed. For both readers, lesion sharpness and conspicuity were rated significantly better in VIBE SR than in VIBE SD in both the precontrast and postcontrast data sets ( P < 0.01), which was consistent with the post hoc regression analysis (for every 1-point increase in sharpness/conspicuity, the odds ratio revealed a positive relation with VIBE SR of 13-fold to 17-fold in comparison with VIBE SD ; P < 0.001). In terms of lesion size, there was no significant difference between the precontrast VIBE SD and VIBE SR or between the postcontrast VIBE SD and VIBE SR for both readers. Similarly, there was an excellent interreader agreement regarding lesion size (intraclass correlation coefficient, >0.9). Conclusions The data-driven superresolution reconstruction (VIBE SR ) is clinically feasible for precontrast and postcontrast upper abdominal VIBE MRI, providing improved image quality, diagnostic confidence, and lesion conspicuity compared with standard VIBE SD images.