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

1

Non-alcoholic fatty liver disease (NAFLD) is linked to hepatic fat content and can be assessed non-invasively using chemical shift-encoded MRI.
2

The proposed multi-decoder water-fat separation neural network (MDWF-Net) estimates water-only, fat-only images, R2*, and Δf maps from fewer echoes.
3

MDWF-Net aims to achieve liver PDFF estimation accuracy comparable to the traditional 6-echo graph cut technique using only 3 echoes.
4

Reducing the number of echoes in MRI scans can significantly shorten acquisition times, improving patient comfort and efficiency.
5

The study utilized a dataset from 134 volunteers, including both healthy and fatty-liver subjects, to validate the effectiveness of MDWF-Net.

European Radiology

by Juan Pablo Meneses, Cristobal Arrieta, Gabriel della Maggiora, Cecilia Besa, Jesús Urbina, Marco Arrese, Juan Cristóbal Gana, Jose E. Galgani, Cristian Tejos, Sergio Uribe
April 4, 2023

1