Multi-atlas segmentation of the skeleton from whole-body MRI-Impact of iterative background masking.

Jakub CerankaSabrina VergaMaryna KvasnytsiaFrédéric LecouvetNicolas MichouxJohan de MeyHubert RaeymaekersThierry MetensJulie AbsilJef Vandemeulebroucke

Published in: Magnetic resonance in medicine (2019)

A registration strategy, relying on the use of atlas segmentations as mask during image registration was proposed and evaluated for multi-atlas segmentation of whole-body MRI. The approach significantly improved registration and final segmentation accuracy and may be applicable to other structures of interest.

Keyphrases

deep learning
convolutional neural network
single cell
contrast enhanced
magnetic resonance imaging
diffusion weighted imaging
machine learning
high resolution
computed tomography
image quality
mass spectrometry
positive airway pressure