Keywords: Analysis/Processing, AI/ML Software, Segmentation, Super-resolution, Motion Estimation, Cardiac
Motivation: High-quality cine MRI and accurate segmentation tools are key requirements for assessing cardiac morphology and function. Supervised neural networks have achieved promising segmentation accuracies but lack generalization performance when trained on annotated data that insufficiently represent the global patient population.
Goal(s): To overcome this limitation, we propose an instance-optimized multi-task implicit neural representation.
Approach: The model learns to propagate the segmentation label of a single segmented frame throughout the entire cardiac cycle by learning deformation fields for accurate cine reconstructions.
Results: The model was trained on 34 subjects with various heart conditions, and its performance was compared to the state-of-the-art [1].
Impact: The proposed model has the potential to speed up cardiac function assessment, by diffusing a single manual segmentation across successive temporal frames and slices, while also providing motion information and offering the possibility to reconstruct a super-resolved volume.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords