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/

Zendy Plus

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

Zendy Tools

Zendy Open

Hyperthermia (HT) in combination with radio- and/or chemotherapy has becomean accepted cancer treatment for distinct solid tumour entities. In HT, tumourtissue is exogenously heated to temperatures between 39 and 43 $^\circ$C for 60minutes. Temperature monitoring can be performed non-invasively using dynamicmagnetic resonance imaging (MRI). However, the slow nature of MRI leads tomotion artefacts in the images due to the movements of patients during imageacquisition. By discarding parts of the data, the speed of the acquisition canbe increased - known as undersampling. However, due to the invalidation of theNyquist criterion, the acquired images might be blurry and can also producealiasing artefacts. The aim of this work was, therefore, to reconstruct highlyundersampled MR thermometry acquisitions with better resolution and with fewerartefacts compared to conventional methods. The use of deep learning in themedical field has emerged in recent times, and various studies have shown thatdeep learning has the potential to solve inverse problems such as MR imagereconstruction. However, most of the published work only focuses on themagnitude images, while the phase images are ignored, which are fundamentalrequirements for MR thermometry. This work, for the first time, presents deeplearning-based solutions for reconstructing undersampled MR thermometry data.Two different deep learning models have been employed here, the FourierPrimal-Dual network and the Fourier Primal-Dual UNet, to reconstruct highlyundersampled complex images of MR thermometry. The method reduced thetemperature difference between the undersampled MRIs and the fully sampled MRIsfrom 1.3 $^\circ$C to 0.6 $^\circ$C in full volume and 0.49 $^\circ$C to 0.06$^\circ$C in the tumour region for an acceleration factor of 10.

Complex-valued neural networks to speed-up MR Thermometry during Hyperthermia using Fourier PD and PDUNet