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

Background: The assessment of left ventricular (LV) function by myocardialperfusion SPECT (MPS) relies on accurate myocardial segmentation. The purposeof this paper is to develop and validate a new method incorporating deeplearning with shape priors to accurately extract the LV myocardium forautomatic measurement of LV functional parameters. Methods: A segmentationarchitecture that integrates a three-dimensional (3D) V-Net with a shapedeformation module was developed. Using the shape priors generated by a dynamicprogramming (DP) algorithm, the model output was then constrained and guidedduring the model training for quick convergence and improved performance. Astratified 5-fold cross-validation was used to train and validate our models.Results: Results of our proposed method agree well with those from the groundtruth. Our proposed model achieved a Dice similarity coefficient (DSC) of0.9573(0.0244), 0.9821(0.0137), and 0.9903(0.0041), a Hausdorff distances (HD)of 6.7529(2.7334) mm, 7.2507(3.1952) mm, and 7.6121(3.0134) mm in extractingthe endocardium, myocardium, and epicardium, respectively. Conclusion: Ourproposed method achieved a high accuracy in extracting LV myocardial contoursand assessing LV function.

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images