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

Since medical image data sets contain few samples and singular features,lesions are viewed as highly similar to other tissues. The traditional neuralnetwork has a limited ability to learn features. Even if a host of feature mapsis expanded to obtain more semantic information, the accuracy of segmenting thefinal medical image is slightly improved, and the features are excessivelyredundant. To solve the above problems, in this paper, we propose a novelend-to-end semantic segmentation algorithm, DT-Net, and use two new convolutionstrategies to better achieve end-to-end semantic segmentation of medicalimages. 1. In the feature mining and feature fusion stage, we construct amulti-directional integrated convolution (MDIC). The core idea is to use themulti-scale convolution to enhance the local multi-directional feature maps togenerate enhanced feature maps and to mine the generated features that containmore semantics without increasing the number of feature maps. 2. We also aim tofurther excavate and retain more meaningful deep features reduce a host ofnoise features in the training process. Therefore, we propose a convolutionthresholding strategy. The central idea is to set a threshold to eliminate alarge number of redundant features and reduce computational complexity. Throughthe two strategies proposed above, the algorithm proposed in this paperproduces state-of-the-art results on two public medical image datasets. Weprove in detail that our proposed strategy plays an important role in featuremining and eliminating redundant features. Compared with the existing semanticsegmentation algorithms, our proposed algorithm has better robustness.

DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution