Analysis of synthetic magnetic resonance images by multi-channel segmentation increases accuracy of volumetry in the putamen and decreases mis-segmentation in the dural sinuses.

Masami GotoIssei FukunagaAkifumi HagiwaraShohei FujitaMasaaki HoriKoji KamagataShigeki AokiOsamu AbeHajime SakamotoYasuaki SakanoShinsuke KyogokuHiroyuki Daida

Published in: Acta radiologica (Stockholm, Sweden : 1987) (2022)

Multi-channel segmentation with T1WI + PDWI provides good results for VBM compared with single-channel and other multi-channel segmentations.

Keyphrases

deep learning
convolutional neural network
magnetic resonance
machine learning
computed tomography
magnetic resonance imaging
optical coherence tomography
contrast enhanced