Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Feb 24;41(8):1961–1974. doi: 10.1109/TMI.2022.3154599

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/

PMC Copyright notice

Fig. 2. — An overview of MulViMotion. We use a hybrid 2D/3D network to estimate a 3D motion field from the input multi-view images. In the hybrid network, FeatureNet learns multi-view motion feature and multi-view shape feature from the input, followed by MotionNet which generates based on . A shape regularization module leverages anatomical shape information for 3D motion estimation. It encourages the predicted 3D edge maps of the myocardial wall (predicted from using ShapeNet) and the warped 3D edge map (warped from ED frame to the -th frame by ) to be consistent with the ground truth 2D edge maps defined on multi-view images. Shape regularization is only used during training.

Inline graphic — An overview of MulViMotion. We use a hybrid 2D/3D network to estimate a 3D motion field from the input multi-view images. In the hybrid network, FeatureNet learns multi-view motion feature and multi-view shape feature from the input, followed by MotionNet which generates based on . A shape regularization module leverages anatomical shape information for 3D motion estimation. It encourages the predicted 3D edge maps of the myocardial wall (predicted from using ShapeNet) and the warped 3D edge map (warped from ED frame to the -th frame by ) to be consistent with the ground truth 2D edge maps defined on multi-view images. Shape regularization is only used during training.