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

Abstract

Purpose: 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.

Material and methods: 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.

Results: SSFSE T2 objective analysis showed higher SNR and CNR for ARDL vs NAÏVE, ARDL vs NON-DL(all P < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAÏVE and, ARDL vs NON-DL (all P > 0.2517).CNR was higher for ARDL vs NON-DL(P = 0.0170), whereas no differences were found between ARDL and NAÏVE(P = 1). No differences were observed for all three comparisons, in terms of SNR and CNR, for ADC maps (all P > 0.32). Qualitative analysis for all sequences showed better overall image quality for ARDL with lower truncation artifacts, higher sharpness and contrast (all P < 0.0070) with excellent inter-rater agreement (k ≥ 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 P < 0.0001).

Conclusion: ARDL applied on upper abdomen showed overall better image quality and reduced scanning time compared with NAÏVE protocol.

Keywords: Artificial intelligence; Image quality; Scanning time; Sequences optimization.

Fig. 1

ROIs placement on MRI scan for quantitative analysis. Unenhanced axial SSFSE T2 images of a 52-years-old male with one of the three ROIs placed on the V hepatic segment liver, one ROI on the background and one in the gallbladder with ARDL a, c NAÏVE b, d showing significant differences in SNR and CNR between ARDL and NAÏVE images

Fig. 2

Comparison of ARDL, NAÏVE, NON-DL dataset on SSFSE T2, DWI and ADC. Female, 28-years old underwent unenhanced upper-abdomen MRI. Axial images showing SSFSE T2 sequences with ARDL a, NAÏVE b, NON-DL c dataset respectively; DWI sequences with ARDL d, NAÏVE e, NON-DL f; ADC maps with ARDL g, NAÏVE h and NON-DL i. Anonymized datasets were obtained to perform qualitative image analysis with 5-point Likert scale assessing Sharpness, Contrast, Truncation artefacts, Motion artifacts and Overall image quality. ARDL dataset showed higher image quality in all datasets in terms of overall image quality compared to NAÏVE and NON-DL dataset.