Keywords: Software Tools, AI/ML Software, Cardiac MRI, Cardiac View Planning, Deep Learning, Late gadolinium enhacement
Motivation: Manual planning of the 4 standard cardiac views (2-chamber, 3-chamber, 4-chamber, short axis) is currently a time-consuming process that demands significant operator interaction and expertise.
Goal(s): Our aim is to streamline and automate this process to reduce examination times and minimize dependency on highly trained operators.
Approach: We developed DeepPlanner4Cardio, a deep learning model designed to predict the standard cardiac views simultaneously.
Results: DeepPlanner4Cardio achieved a clinically acceptable accuracy of 94% on the test set with a mean orientation error of 11º and a mean displacement error of 5.9 mm, both within the inter-operator variability ranges.
Impact: DeepPlanner4Cardio effectively supports CMR operators by providing an accessible, automated solution to enable fast and reproducible cardiac view planning, demonstrating great potential to be applied in a clinical setting.
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