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

Generative adversarial networks (GANs) have shown remarkable success ingenerating realistic images and are increasingly used in medical imaging forimage-to-image translation tasks. However, GANs tend to suffer from a frequencybias towards low frequencies, which can lead to the removal of importantstructures in the generated images. To address this issue, we propose a novelfrequency-aware image-to-image translation framework based on the supervisedRegGAN approach, which we call fRegGAN. The framework employs a K-space loss toregularize the frequency content of the generated images and incorporateswell-known properties of MRI K-space geometry to guide the network trainingprocess. By combine our method with the RegGAN approach, we can mitigate theeffect of training with misaligned data and frequency bias at the same time. Weevaluate our method on the public BraTS dataset and outperform the baselinemethods in terms of both quantitative and qualitative metrics when synthesizingT2-weighted from T1-weighted MR images. Detailed ablation studies are providedto understand the effect of each modification on the final performance. Theproposed method is a step towards improving the performance of image-to-imagetranslation and synthesis in the medical domain and shows promise for otherapplications in the field of image processing and generation.

fRegGAN with K-space Loss Regularization for Medical Image Translation