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

Purpose: This paper proposes a new network framework called EAR-U-Net, whichleverages EfficientNetB4, attention gate, and residual learning techniques toachieve automatic and accurate liver segmentation. Methods: The proposed methodis based on the U-Net framework. First, we use EfficientNetB4 as the encoder toextract more feature information during the encoding stage. Then, an attentiongate is introduced in the skip connection to eliminate irrelevant regions andhighlight features of a specific segmentation task. Finally, to alleviate theproblem of gradient vanishment, we replace the traditional convolution of thedecoder with a residual block to improve the segmentation accuracy. Results: Weverified the proposed method on the LiTS17 and SLiver07 datasets and comparedit with classical networks such as FCN, U-Net, Attention U-Net, and AttentionRes-U-Net. In the Sliver07 evaluation, the proposed method achieved the bestsegmentation performance on all five standard metrics. Meanwhile, in the LiTS17assessment, the best performance is obtained except for a slight inferior onRVD. Moreover, we also participated in the MICCIA-LiTS17 challenge, and theDice per case score was 0.952. Conclusion: The proposed method's qualitativeand quantitative results demonstrated its applicability in liver segmentationand proved its good prospect in computer-assisted liver segmentation.

EAR-U-Net: EfficientNet and attention-based residual U-Net for automatic liver segmentation in CT