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

The segmentation and classification of carotid plaques in ultrasound imagesplay important roles in the treatment of atherosclerosis and assessment for therisk of stroke. Although deep learning methods have been used for carotidplaque segmentation and classification, two-stage methods will increase thecomplexity of the overall analysis and the existing multi-task methods ignoredthe relationship between the segmentation and classification. These will leadto suboptimal performance as valuable information might not be fully leveragedacross all tasks. Therefore, we propose a multi-task learning framework(RCCM-Net) for ultrasound carotid plaque segmentation and classification, whichutilizes a region confidence module (RCM) and a sample category confidencemodule (CCM) to exploit the correlation between these two tasks. The RCMprovides knowledge from the probability of plaque regions to the classificationtask, while the CCM is designed to learn the categorical sample weight for thesegmentation task. A total of 1270 2D ultrasound images of carotid plaques werecollected from Zhongnan Hospital (Wuhan, China) for our experiments. Theresults showed that the proposed method can improve both segmentation andclassification performance compared to existing single-task networks (i.e.,SegNet, Deeplabv3+, UNet++, EfficientNet, Res2Net, RepVGG, DPN) and multi-taskalgorithms (i.e., HRNet, MTANet), with an accuracy of 85.82% for classificationand a Dice-similarity-coefficient of 84.92% for segmentation. In the ablationstudy, the results demonstrated that both the designed RCM and CCM werebeneficial in improving the network's performance. Therefore, we believe thatthe proposed method could be useful for carotid plaque analysis in clinicaltrials and practice.

A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification