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

Multi-modal image registration is a challenging problem that is also animportant clinical task for many real applications and scenarios. As a firststep in analysis, deformable registration among different image modalities isoften required in order to provide complementary visual information. Duringregistration, semantic information is key to match homologous points andpixels. Nevertheless, many conventional registration methods are incapable incapturing high-level semantic anatomical dense correspondences. In this work,we propose a novel multi-task learning system, JSSR, based on an end-to-end 3Dconvolutional neural network that is composed of a generator, a registrationand a segmentation component. The system is optimized to satisfy the implicitconstraints between different tasks in an unsupervised manner. It firstsynthesizes the source domain images into the target domain, then anintra-modal registration is applied on the synthesized images and targetimages. The segmentation module are then applied on the synthesized and targetimages, providing additional cues based on semantic correspondences. Thesupervision from another fully-annotated dataset is used to regularize thesegmentation. We extensively evaluate JSSR on a large-scale medical imagedataset containing 1,485 patient CT imaging studies of four different contrastphases (i.e., 5,940 3D CT scans with pathological livers) on the registration,segmentation and synthesis tasks. The performance is improved after jointtraining on the registration and segmentation tasks by 0.9% and 1.9%respectively compared to a highly competitive and accurate deep learningbaseline. The registration also consistently outperforms conventionalstate-of-the-art multi-modal registration methods.

JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans