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

Several variants of Convolutional Neural Networks (CNN) have been developedfor Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shownto be the baseline architecture for MR image reconstruction. However,sub-sampling is performed by its pooling layers, causing information loss whichin turn leads to blur and missing fine details in the reconstructed image. Wepropose a modification to the U-Net architecture to recover fine structures.The proposed network is a wavelet packet transform based encoder-decoder CNNwith residual learning called CNN. The proposed WCNN has discrete wavelettransform instead of pooling and inverse wavelet transform instead of unpoolinglayers and residual connections. We also propose a deep cascaded framework(DC-WCNN) which consists of cascades of WCNN and k-space data fidelity units toachieve high quality MR reconstruction. Experimental results show that WCNN andDC-WCNN give promising results in terms of evaluation metrics and betterrecovery of fine details as compared to other methods.

DC-WCNN: A deep cascade of wavelet based convolutional neural networks for MR Image Reconstruction