Fast T2-weighted liver MRI: Image quality and solid focal lesions conspicuity using a deep learning accelerated single breath-hold HASTE fat-suppressed sequence - 19/05/22

Doi : 10.1016/j.diii.2022.05.001

Sébastien Mulé ^a,^b,^c,^⁎ , Rym Kharrat ^a, Pierre Zerbib ^a, Aurélien Massire ^d, Marcel Dominik Nickel ^e, Khalid Ambarki ^d, Edouard Reizine ^a,^b,^c, Laurence Baranes ^a, Benhalima Zegai ^a, Frederic Pigneur ^a, Hicham Kobeiter ^a,^b, Alain Luciani ^a,^b,^c
^a Service d'Imagerie Médicale, AP-HP, Hôpitaux Universitaires Henri Mondor, Créteil 94000, France
^b Faculté de Santé, Université Paris Est Créteil, Créteil 94000, France
^c INSERM IMRB, U 955, Equipe 18, Créteil 94000, France
^d Siemens Healthcare SAS, Saint-Denis 93200, France
^e MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen 91058, Germany

^⁎Corresponding author.

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Thursday 19 May 2022
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Highlights

•	HASTE_DL sequence reduces liver T2-weighted acquisition time at 1.5 T.
•	HASTE_DL improves image quality and focal liver lesion contrast-to-noise ratio, notably in patients with chronic liver disease.
•	HASTE_DL could be favorably embedded in abbreviated liver MRI protocols.

Le texte complet de cet article est disponible en PDF.

Abstract

Purpose

Acceleration of MRI acquisitions and especially of T2-weighted sequences is essential to reduce the duration of MRI examinations but also kinetic artifacts in liver imaging. The purpose of this study was to compare the acquisition time and the image quality of a single-shot fat-suppressed turbo spin-echo (TSE) T2-weighted sequence with deep learning reconstruction (HASTE_DL) with that of a fat-suppressed T2-weighted BLADE TSE sequence in patients with focal liver lesions.

Materials and methods

Ninety-five patients (52 men, 43 women; mean age: 61 ± 14 [SD]; age range: 28–87 years) with 42 focal liver lesions (17 hepatocellular carcinomas, 10 sarcoidosis lesions, 9 myeloma lesions, 3 liver metastases and 3 focal nodular hyperplasias) who underwent liver MRI at 1.5 T including HASTE_DL and BLADE sequences were retrospectively included. Overall image quality, noise level in the liver, lesion conspicuity and sharpness of liver lesion contours were assessed by two independent readers. Liver signal-to-noise ratio (SNR) and lesion contrast-to-noise ratio (CNR) were measured and compared between the two sequences, as well as the mean duration of the sequences (Student t-test or Wilcoxon test for paired data).

Results

Median overall quality on HASTE_DL images (3; IQR: 3, 3) was significantly greater than that on BLADE images (2; IQR: 1, 3) (P < 0.001). Median noise level in the liver on HASTE_DL images (0; IQR: 0, 0.5) was significantly lower than that on BLADE images (1; IQR: 1, 2) (P < 0.001). On HASTE_DL images, mean liver SNR (107.3 ± 39.7 [SD]) and mean focal liver lesion CNR (87.0 ± 76.6 [SD]) were significantly greater than those on BLADE images (67.1 ± 23.8 [SD], P < 0.001 and 48.6 ± 43.9 [SD], P = 0.027, respectively). Acquisition time was significantly shorter with the HASTE_DL sequence (18 ± [0] s; range: 18–18 s) compared to BLADE sequence (152 ± 47 [SD] s; range: 87–263 s) (P < 0.001).

Conclusion

By comparison with the BLADE sequence, HASTE_DL sequence significantly reduces acquisition time while improving image quality, liver SNR and focal liver lesions CNR.

Le texte complet de cet article est disponible en PDF.

Keywords : Deep learning, Liver neoplasms, Magnetic resonance imaging

Abbreviations : CI, CNR, HASTE_DL, HCC, IQR, MRI, ROI, SD, SI, SNR, TSE