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

Segmenting anatomical structures in medical images has been successfullyaddressed with deep learning methods for a range of applications. However, thissuccess is heavily dependent on the quality of the image that is beingsegmented. A commonly neglected point in the medical image analysis communityis the vast amount of clinical images that have severe image artefacts due toorgan motion, movement of the patient and/or image acquisition related issues.In this paper, we discuss the implications of image motion artefacts on cardiacMR segmentation and compare a variety of approaches for jointly correcting forartefacts and segmenting the cardiac cavity. The method is based on ourrecently developed joint artefact detection and reconstruction method, whichreconstructs high quality MR images from k-space using a joint loss functionand essentially converts the artefact correction task to an under-sampled imagereconstruction task by enforcing a data consistency term. In this paper, wepropose to use a segmentation network coupled with this in an end-to-endframework. Our training optimises three different tasks: 1) image artefactdetection, 2) artefact correction and 3) image segmentation. We train thereconstruction network to automatically correct for motion-related artefactsusing synthetically corrupted cardiac MR k-space data and uncorrectedreconstructed images. Using a test set of 500 2D+time cine MR acquisitions fromthe UK Biobank data set, we achieve demonstrably good image quality and highsegmentation accuracy in the presence of synthetic motion artefacts. Weshowcase better performance compared to various image correction architectures.

Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation