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/

Zendy Plus

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

Zendy Tools

Zendy Open

Automatic neonatal brain tissue segmentation in preterm born infants is aprerequisite for evaluation of brain development. However, automaticsegmentation is often hampered by motion artifacts caused by infant headmovements during image acquisition. Methods have been developed to remove orminimize these artifacts during image reconstruction using frequency domaindata. However, frequency domain data might not always be available. Hence, inthis study we propose a method for removing motion artifacts from the alreadyreconstructed MR scans. The method employs a generative adversarial networktrained with a cycle consistency loss to transform slices affected by motioninto slices without motion artifacts, and vice versa. In the experiments 40T2-weighted coronal MR scans of preterm born infants imaged at 30 weekspostmenstrual age were used. All images contained slices affected by motionartifacts hampering automatic tissue segmentation. To evaluate whethercorrection allows more accurate image segmentation, the images were segmentedinto 8 tissue classes: cerebellum, myelinated white matter, basal ganglia andthalami, ventricular cerebrospinal fluid, white matter, brain stem, corticalgray matter, and extracerebral cerebrospinal fluid. Images corrected for motionand corresponding segmentations were qualitatively evaluated using 5-pointLikert scale. Before the correction of motion artifacts, median image qualityand quality of corresponding automatic segmentations were assigned grade 2(poor) and 3 (moderate), respectively. After correction of motion artifacts,both improved to grades 3 and 4, respectively. The results indicate thatcorrection of motion artifacts in the image space using the proposed approachallows accurate segmentation of brain tissue classes in slices affected bymotion artifacts.

Generative adversarial network for segmentation of motion affected neonatal brain MRI