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

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.

Influence of Adaptive Statistical Iterative Reconstructions on CT Radiomic Features in Oncologic Patients.

Iterative reconstructions (IR) might alter radiomic features extraction. We aim to evaluate the influence of Adaptive Statistical Iterative Reconstruction-V (ASIR-V) on CT radiomic features. Patients who underwent unenhanced abdominal CT (Revolution Evo, GE Healthcare, USA) were retrospectively enrolled. Raw data of filtered-back projection (FBP) were reconstructed with 10 levels of ASIR-V (10-100%). CT texture analysis (CTTA) of liver, kidney, spleen and paravertebral muscle for all datasets was performed. Six radiomic features (mean intensity, standard deviation (SD), entropy, mean of positive pixel (MPP), skewness, kurtosis) were extracted and compared between FBP and all ASIR-V levels, with and without altering the spatial scale filter (SSF). CTTA of all organs revealed significant differences between FBP and all ASIR-V reconstructions for mean intensity, SD, entropy and MPP (all p < 0.0001), while no significant differences were observed for skewness and kurtosis between FBP and all ASIR-V reconstructions (all p > 0.05). A per-filter analysis was also performed comparing FBP with all ASIR-V reconstructions for all six SSF separately (SSF0-SSF6). Results showed significant differences between FBP and all ASIR-V reconstruction levels for mean intensity, SD, and MPP (all filters p < 0.0315). Skewness and kurtosis showed no differences for all comparisons performed (all p > 0.05). The application of incremental ASIR-V levels affects CTTA across various filters. Skewness and kurtosis are not affected by IR and may be reliable quantitative parameters for radiomic analysis.