Purpose To compare liver MRI with AIR Recon Deep Learning (TM)(ARDL) algorithm applied and turned-off (NON-DL) with conventional high-resolution acquisition (NAiVE) 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 NAiVE 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 NAiVE, ARDL vs NON-DL(all P < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAiVE 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 NAiVE(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 NAiVE (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 NAiVE protocol.

Artificial intelligence based image quality enhancement in liver MRI. a quantitative and qualitative evaluation / Zerunian, Marta; Pucciarelli, Francesco; Caruso, Damiano; Polici, Michela; Masci, Benedetta; Guido, Gisella; De Santis, Domenico; Polverari, Daniele; Principessa, Daniele; Benvenga, Antonella; Iannicelli, Elsa; Laghi, Andrea. - In: LA RADIOLOGIA MEDICA. - ISSN 1826-6983. - 127:10(2022), pp. 1098-1105. [10.1007/s11547-022-01539-9]

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

Zerunian, Marta;Pucciarelli, Francesco;Caruso, Damiano;Polici, Michela;Masci, Benedetta;Guido, Gisella;De Santis, Domenico;Iannicelli, Elsa;Laghi, Andrea
2022

Abstract

Purpose To compare liver MRI with AIR Recon Deep Learning (TM)(ARDL) algorithm applied and turned-off (NON-DL) with conventional high-resolution acquisition (NAiVE) 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 NAiVE 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 NAiVE, ARDL vs NON-DL(all P < 0.013). Regarding DWI, no differences were found for SNR with ARDL vs NAiVE 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 NAiVE(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 NAiVE (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 NAiVE protocol.
2022
artificial intelligence; image quality; scanning time; sequences optimization
01 Pubblicazione su rivista::01a Articolo in rivista
Artificial intelligence based image quality enhancement in liver MRI. a quantitative and qualitative evaluation / Zerunian, Marta; Pucciarelli, Francesco; Caruso, Damiano; Polici, Michela; Masci, Benedetta; Guido, Gisella; De Santis, Domenico; Polverari, Daniele; Principessa, Daniele; Benvenga, Antonella; Iannicelli, Elsa; Laghi, Andrea. - In: LA RADIOLOGIA MEDICA. - ISSN 1826-6983. - 127:10(2022), pp. 1098-1105. [10.1007/s11547-022-01539-9]
File allegati a questo prodotto
File Dimensione Formato  
Zerunian_Artificial-intelligence-based-image-quality_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 1.08 MB
Formato Adobe PDF
1.08 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1675831
Citazioni
  • ???jsp.display-item.citation.pmc??? 24
  • Scopus 31
  • ???jsp.display-item.citation.isi??? 30
social impact