What type of study is this?

This is a Experimental Study study.

September 17, 2025

Clinical Translation of Deep Learning-based Ascending Aortic Morphology Characterization Using 3D Non-Contrast-enhanced MRA

Key Points

Automated aortic segmentation and measurements were displayed immediately after scanning, enhancing workflow efficiency.
High test-retest reliability was achieved with various MRA sequences, affirming the robustness of the deep learning model.
Preliminary tests with the Dixon-MRA sequence indicate a promising path for expanding applications beyond current methods.
Integration of deep learning on the MR scanner supports timely cardiovascular risk evaluations and informed clinical decisions.

Abstract

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.

KI fragen

Bookmark