Liver PDFF estimation using a multi-decoder water-fat separation neural network with a reduced number of echoes

Simple item page
dc.contributor.authorMeneses, Juan Pablo
dc.contributor.authorArrieta, Cristobal
dc.contributor.authordella Maggiora, Gabriel
dc.contributor.authorBesa, Cecilia
dc.contributor.authorUrbina, Jesus
dc.contributor.authorArrese, Marco
dc.contributor.authorGana, Juan Cristobal
dc.contributor.authorGalgani, Jose E.
dc.contributor.authorTejos, Cristian
dc.contributor.authorUribe, Sergio
dc.date.accessioned2025-01-20T20:15:44Z
dc.date.available2025-01-20T20:15:44Z
dc.date.issued2023
dc.description.abstractObjectiveTo 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.
dc.fuente.origenWOS
dc.identifier.doi10.1007/s00330-023-09576-2
dc.identifier.eissn1432-1084
dc.identifier.issn0938-7994
dc.identifier.urihttps://doi.org/10.1007/s00330-023-09576-2
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/92280
dc.identifier.wosidWOS:000964414000003
dc.issue.numero9
dc.language.isoen
dc.pagina.final6568
dc.pagina.inicio6557
dc.revistaEuropean radiology
dc.rightsacceso restringido
dc.subjectLiver
dc.subjectNon-alcoholic fatty Liver disease
dc.subjectBiomarkers
dc.subjectDeep leaning
dc.subjectMagnetic resonance imaging
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleLiver PDFF estimation using a multi-decoder water-fat separation neural network with a reduced number of echoes
dc.typeartículo
dc.volumen33
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas