Why the study?
Accurate segmentation of ventricle and myocardium from LGE-CMR is difficult due to complex enhancement patterns and a lack of labeled samples.
Population
Annotated bSSFP-CMR images and unlabelled LGE-CMR images
Design
Algorithm development and validation study
Loading...
May facilitate automated MI analysis without labeled LGE data; leaves open prospective clinical validation.
An unsupervised LGE-CMR segmentation algorithm using style transfer networks for data augmentation effectively segments ventricles and myocardium without requiring labeled LGE-CMR data.
A 2022 study studied this question.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: