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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Liver tumor segmentation in CT images is a critical step in the diagnosis,surgical planning and postoperative evaluation of liver disease. An automaticliver and tumor segmentation method can greatly relieve physicians of the heavyworkload of examining CT images and better improve the accuracy of diagnosis.In the last few decades, many modifications based on U-Net model have beenproposed in the literature. However, there are relatively few improvements forthe advanced UNet++ model. In our paper, we propose an encoding featuresupervised UNet++(ES-UNet++) and apply it to the liver and tumor segmentation.ES-UNet++ consists of an encoding UNet++ and a segmentation UNet++. Thewell-trained encoding UNet++ can extract the encoding features of label mapwhich are used to additionally supervise the segmentation UNet++. By addingsupervision to the each encoder of segmentation UNet++, U-Nets of differentdepths that constitute UNet++ outperform the original version by average 5.7%in dice score and the overall dice score is thus improved by 2.1%. ES-UNet++ isevaluated with dataset LiTS, achieving 95.6% for liver segmentation and 67.4%for tumor segmentation in dice score. In this paper, we also concluded somevaluable properties of ES-UNet++ by conducting comparative anaylsis betweenES-UNet++ and UNet++:(1) encoding feature supervision can accelerate theconvergence of the model.(2) encoding feature supervision enhances the effectof model pruning by achieving huge speedup while providing pruned models withfairly good performance.

Encoding feature supervised UNet++: Redesigning Supervision for liver and tumor segmentation