English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Abnormal iron accumulation in the brain subcortical nuclei has been reportedto be correlated to various neurodegenerative diseases, which can be measuredthrough the magnetic susceptibility from the quantitative susceptibilitymapping (QSM). To quantitively measure the magnetic susceptibility, the nucleishould be accurately segmented, which is a tedious task for clinicians. In thispaper, we proposed a double-branch residual-structured U-Net (DB-ResUNet) basedon 3D convolutional neural network (CNN) to automatically segment such braingray matter nuclei. To better tradeoff between segmentation accuracy and thememory efficiency, the proposed DB-ResUNet fed image patches with highresolution and the patches with low resolution but larger field of view intothe local and global branches, respectively. Experimental results revealed thatby jointly using QSM and T$_\text{1}$ weighted imaging (T$_\text{1}$WI) asinputs, the proposed method was able to achieve better segmentation accuracyover its single-branch counterpart, as well as the conventional atlas-basedmethod and the classical 3D-UNet structure. The susceptibility values and thevolumes were also measured, which indicated that the measurements from theproposed DB-ResUNet are able to present high correlation with values from themanually annotated regions of interest.

Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network