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

MRI, a widespread non-invasive medical imaging modality, is highly sensitiveto patient motion. Despite many attempts over the years, motion correctionremains a difficult problem and there is no general method applicable to allsituations. We propose a retrospective method for motion quantification andcorrection to tackle the problem of in-plane rigid-body motion, apt forclassical 2D Spin-Echo scans of the brain, which are regularly used in clinicalpractice. Due to the sequential acquisition of k-space, motion artifacts arewell localized. The method leverages the power of deep neural networks toestimate motion parameters in k-space and uses a model-based approach torestore degraded images to avoid ''hallucinations''. Notable advantages are itsability to estimate motion occurring in high spatial frequencies without theneed of a motion-free reference. The proposed method operates on the wholek-space dynamic range and is moderately affected by the lower SNR of higherharmonics. As a proof of concept, we provide models trained using supervisedlearning on 600k motion simulations based on motion-free scans of 43 differentsubjects. Generalization performance was tested with simulations as well asin-vivo. Qualitative and quantitative evaluations are presented for motionparameter estimations and image reconstruction. Experimental results show thatour approach is able to obtain good generalization performance on simulateddata and in-vivo acquisitions.

SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space