External authors:

• Juan Pablo Meneses ( Pontificia Universidad Catolica de Chile , Millennium Inst Intelligent Healthcare Engn iHEALT )
• Cristobal Arrieta ( Universidad Alberto Hurtado , Millennium Inst Intelligent Healthcare Engn iHEALT )
• Gabriel della Maggiora ( Pontificia Universidad Catolica de Chile )
• Cecilia Besa ( Pontificia Universidad Catolica de Chile , Millennium Inst Intelligent Healthcare Engn iHEALT )
• Jesus Urbina ( Pontificia Universidad Catolica de Chile , Millennium Inst Intelligent Healthcare Engn iHEALT )
• Marco Arrese ( Pontificia Universidad Catolica de Chile )
• Juan Cristobal Gana ( Pontificia Universidad Catolica de Chile )
• Jose E. Galgani ( Pontificia Universidad Catolica de Chile , Monash University )
• Sergio Uribe ( Pontificia Universidad Catolica de Chile , Millennium Inst Intelligent Healthcare Engn iHEALT )
• Marco Arrese ( Pontificia Universidad Catolica de Chile )

Abstract:

ObjectiveTo accurately estimate liver PDFF from chemical shift-encoded (CSE) MRI using a deep learning (DL)-based Multi-Decoder Water-Fat separation Network (MDWF-Net), that operates over complex-valued CSE-MR images with only 3 echoes.MethodsThe proposed MDWF-Net and a U-Net model were independently trained using the first 3 echoes of MRI data from 134 subjects, acquired with conventional 6-echoes abdomen protocol at 1.5 T. Resulting models were then evaluated using unseen CSE-MR images obtained from 14 subjects that were acquired with a 3-echoes CSE-MR pulse sequence with a shorter duration compared to the standard protocol. Resulting PDFF maps were qualitatively assessed by two radiologists, and quantitatively assessed at two corresponding liver ROIs, using Bland Altman and regression analysis for mean values, and ANOVA testing for standard deviation (STD) (significance level: .05). A 6-echo graph cut was considered ground truth.ResultsAssessment of radiologists demonstrated that, unlike U-Net, MDWF-Net had a similar quality to the ground truth, despite it considered half of the information. Regarding PDFF mean values at ROIs, MDWF-Net showed a better agreement with ground truth (regression slope = 0.94, R-2 = 0.97) than U-Net (regression slope = 0.86, R-2 = 0.93). Moreover, ANOVA post hoc analysis of STDs showed a statistical difference between graph cuts and U-Net (p < .05), unlike MDWF-Net (p = .53).ConclusionMDWF-Net showed a liver PDFF accuracy comparable to the reference graph cut method, using only 3 echoes and thus allowing a reduction in the acquisition times.