Artificial intelligence based image quality enhancement in liver MRI: a quantitative and qualitative evaluation

<jats:title>Abstract</jats:title><jats:sec> <jats:title>Purpose</jats:title> <jats:p>To compare liver MRI with AIR Recon Deep Learning™(ARDL) algorithm applied and turned-off (NON-DL) with conventional high-resolution acquisition (NAÏVE) sequences, in terms of quantitative and qualitative image analysis and scanning time.</jats:p> </jats:sec><jats:sec> <jats:title>Material and methods</jats:title> <jats:p>This prospective study included fifty consecutive volunteers (31 female, mean age 55.5 ± 20 years) from September to November 2021. 1.5 T MRI was performed and included three sets of images: axial single-shot fast spin-echo (SSFSE) T2 images, diffusion-weighted images(DWI) and apparent diffusion coefficient(ADC) maps acquired with both ARDL and NAÏVE protocol; the NON-DL images, were also assessed. Two radiologists in consensus drew fixed regions of interest in liver parenchyma to calculate signal-to-noise-ratio (SNR) and contrast to-noise-ratio (CNR). Subjective image quality was assessed by two other radiologists independently with a five-point Likert scale. Acquisition time was recorded.</jats:p> </jats:sec><jats:sec> <jats:title>Results</jats:title> <jats:p>SSFSE T2 objective analysis showed higher SNR and CNR for ARDL vs NAÏVE, ARDL vs NON-DL(all <jats:italic>P</jats:italic> < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAÏVE and, ARDL vs NON-DL (all <jats:italic>P</jats:italic> > 0.2517).CNR was higher for ARDL vs NON-DL(<jats:italic>P</jats:italic> = 0.0170), whereas no differences were found between ARDL and NAÏVE(<jats:italic>P</jats:italic> = 1). No differences were observed for all three comparisons, in terms of SNR and CNR, for ADC maps (all <jats:italic>P</jats:italic> > 0.32).</jats:p> <jats:p>Qualitative analysis for all sequences showed better overall image quality for ARDL with lower truncation artifacts, higher sharpness and contrast (all <jats:italic>P</jats:italic> < 0.0070) with excellent inter-rater agreement (<jats:italic>k</jats:italic> ≥ 0.8143). Acquisition time was lower in ARDL sequences compared to NAÏVE (SSFSE T2 = 19.08 ± 2.5 s vs. 24.1 ± 2 s and DWI = 207.3 ± 54 s vs. 513.6 ± 98.6 s, all <jats:italic>P</jats:italic> < 0.0001).</jats:p> </jats:sec><jats:sec> <jats:title>Conclusion</jats:title> <jats:p>ARDL applied on upper abdomen showed overall better image quality and reduced scanning time compared with NAÏVE protocol.</jats:p> </jats:sec>