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

Magnetic Resonance Imaging (MRI) scans are time consuming and precarious,since the patients remain still in a confined space for extended periods oftime. To reduce scanning time, some experts have experimented with undersampledk spaces, trying to use deep learning to predict the fully sampled result.These studies report that as many as 20 to 30 minutes could be saved off a scanthat takes an hour or more. However, none of these studies have explored thepossibility of using masked image modeling (MIM) to predict the missing partsof MRI k spaces. This study makes use of 11161 reconstructed MRI and k spacesof knee MRI images from Facebook's fastmri dataset. This tests a modifiedversion of an existing model using baseline shifted window (Swin) and visiontransformer architectures that makes use of MIM on undersampled k spaces topredict the full k space and consequently the full MRI image. Modificationswere made using pytorch and numpy libraries, and were published to a githubrepository. After the model reconstructed the k space images, the basic Fouriertransform was applied to determine the actual MRI image. Once the model reacheda steady state, experimentation with hyperparameters helped to achieve pinpointaccuracy for the reconstructed images. The model was evaluated through L1 loss,gradient normalization, and structural similarity values. The model producedreconstructed images with L1 loss values averaging to <0.01 and gradientnormalization values <0.1 after training finished. The reconstructed k spacesyielded structural similarity values of over 99% for both training andvalidation with the fully sampled k spaces, while validation loss continuallydecreased under 0.01. These data strongly support the idea that the algorithmworks for MRI reconstruction, as they indicate the model's reconstructed imagealigns extremely well with the original, fully sampled k space.

A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces