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

Magnetic resonance imaging (MRI) is a valuable clinical tool for displayinganatomical structures and aiding in accurate diagnosis. Medical imagesuper-resolution (SR) reconstruction using deep learning techniques can enhancelesion analysis and assist doctors in improving diagnostic efficiency andaccuracy. However, existing deep learning-based SR methods predominantly relyon convolutional neural networks (CNNs), which inherently limit the expressivecapabilities of these models and therefore make it challenging to discoverpotential relationships between different image features. To overcome thislimitation, we propose an A-network that utilizes multiple convolution operatorfeature extraction modules (MCO) for extracting image features using multipleconvolution operators. These extracted features are passed through multiplesets of cross-feature extraction modules (MSC) to highlight key featuresthrough inter-channel feature interactions, enabling subsequent featurelearning. An attention-based sparse graph neural network module is incorporatedto establish relationships between pixel features, learning which adjacentpixels have the greatest impact on determining the features to be filled. Toevaluate our model's effectiveness, we conducted experiments using differentmodels on data generated from multiple datasets with different degradationmultiples, and the experimental results show that our method is a significantimprovement over the current state-of-the-art methods.

Convolutional neural network based on sparse graph attention mechanism for MRI super-resolution