Keywords: Data Acquisition, Machine Learning/Artificial Intelligence, Causality, Confounder-free learning
Motivation: Enabling rapid and accurate assessment of thoracic aortic morphology from MR imaging is essential for effective cardiovascular risk evaluation and informed clinical decision-making
Goal(s): Implementation of an inline deep learning (DL) model on the MR scanner to automate aortic segmentation and morphology measurements, with evaluation of different MR angiography (MRA) sequences.
Approach: A residual-UNET-based DL model was deployed on a 3T-MR scanner, analyzing non-contrast-enhanced MRA data inline. Automated segmentation and measurements were displayed immediately after scanning.
Results: High test-retest reliability was achieved with the MRA sequences, confirming model robustness. Preliminary tests with a novel research Dixon-MRA sequence shows potential for a wider application.
Impact: Integration of deep learning image analysis for thoracic aorta inline on the MR scanner accelerates aortic morphology assessment across multiple sequences. Visualizing the results directly on the scanner supports rapid clinical decisions and advances cardiovascular imaging workflows.
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