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

Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental tobuilding statistical cardiac anatomy models and understanding functionalmechanisms from motion patterns. However, due to the low through-planeresolution of cine MR and high inter-subject variance, accurately segmentingcardiac images and reconstructing the 3D volume are challenging. In this study,we propose an end-to-end latent-space-based framework, DeepRecon, thatgenerates multiple clinically essential outcomes, including accurate imagesegmentation, synthetic high-resolution 3D image, and 3D reconstructed volume.Our method identifies the optimal latent representation of the cine image thatcontains accurate semantic information for cardiac structures. In particular,our model jointly generates synthetic images with accurate semantic informationand segmentation of the cardiac structures using the optimal latentrepresentation. We further explore downstream applications of 3D shapereconstruction and 4D motion pattern adaptation by the different latent-spacemanipulation strategies.The simultaneously generated high-resolution imagespresent a high interpretable value to assess the cardiac shape andmotion.Experimental results demonstrate the effectiveness of our approach onmultiple fronts including 2D segmentation, 3D reconstruction, downstream 4Dmotion pattern adaption performance.

DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method