Keywords: MR-Guided Interventions, MR-Guided Interventions, cardiac catheterization, passive tracking, real time, deep learning
Motivation: MRI-guided cardiac catheterization relies on manual slice tracking during catheter navigation, complicating procedures and limiting catheter visibility. An automated slice tracking approach has been proposed for continuous catheter visualization but relies on operator/subject-specific inputs.
Goal(s): To develop and evaluate a real-time, parameter-free AI-based framework for continuous, automatic tracking of gadolinium-filled balloon catheters during MRI-guided cardiac catheterization.
Approach: A deep-learning framework with two imaging modes was tested on a 3D-printed phantom and pediatric patients, assessing accuracy, sensitivity, and specificity.
Results: The framework demonstrated high accuracy (>98%) and robustness across various anatomies and contrasts, showing feasibility for patient-independent tracking in MRI-guided cardiac procedures.
Impact: This AI-based framework could simplify MRI-guided cardiac catheterization by reducing manual input, potentially decreasing procedural time and enhancing visualization accuracy, supporting broader clinical adoption and improved patient outcomes.
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