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

Recently, deep learning has become much more popular in computer vision area.The Convolution Neural Network (CNN) has brought a breakthrough in imagessegmentation areas, especially, for medical images. In this regard, U-Net isthe predominant approach to medical image segmentation task. The U-Net not onlyperforms well in segmenting multimodal medical images generally, but also insome tough cases of them. However, we found that the classical U-Netarchitecture has limitation in several aspects. Therefore, we appliedmodifications: 1) designed efficient CNN architecture to replace encoder anddecoder, 2) applied residual module to replace skip connection between encoderand decoder to improve based on the-state-of-the-art U-Net model. Followingthese modifications, we designed a novel architecture--DC-UNet, as a potentialsuccessor to the U-Net architecture. We created a new effective CNNarchitecture and build the DC-UNet based on this CNN. We have evaluated ourmodel on three datasets with tough cases and have obtained a relativeimprovement in performance of 2.90%, 1.49% and 11.42% respectively comparedwith classical U-Net. In addition, we used the Tanimoto similarity to replacethe Jaccard similarity for gray-to-gray image comparisons.

DC-UNet: Rethinking the U-Net Architecture with Dual Channel Efficient CNN for Medical Images Segmentation