Meeting Banner
Abstract #0374

Multi-Stage Deep Learning Enables Accurate Detection of Ischemia in Myocardial Perfusion MRI with Order-of-magnitude Lower Contrast Dose

Khalid Youssef1,2, Luis Zamudio1,3, Bobak Heydari4, Andrew Howarth5, and Behzad Sharif1,3
1Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, United States, 2Krannert Cardiovascular Research Center, Indiana University School of Medicine/IU Health Cardiovascular Institute, Indianapolis, IN, United States, 3Laboratory for Translational Imaging for Microcirculation, Weldon School of Biomedical Engineering, Purdue University, Indianapolis, IN, United States, 4Medicine Department, Harvard University, Boston, MA, United States, 5Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada

Synopsis

Keywords: Diagnosis/Prediction, Ischemia

Motivation: Reducing gadolinium doses in stress/rest perfusion cardiac-MRI (CMR) is highly desirable for patient safety, but lower doses diminish image quality, risking inaccurate myocardial ischemia detection.

Goal(s): Determine if a multi-stage deep learning (MST) myocardial blood flow quantification method can accurately detect myocardial ischemia in stress-perfusion CMR using significantly reduced gadolinium doses.

Approach: Trained an MST model on full-dose perfusion images with data augmentation to simulate low contrast-to-noise acquisition, then assessed its ischemia detection accuracy at reduced contrast doses compared to traditional methods.

Results: The MST method accurately detected myocardial ischemia with up to tenfold lower gadolinium doses, outperforming traditional Fermi-deconvolution in diagnostic accuracy.

Impact: The MST deep learning method enables accurate ischemia detection in stress CMR with significantly reduced gadolinium doses, enhancing patient safety and reducing costs. This advancement could facilitate safer, more accessible stress CMR protocols in clinical practice.

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.

Click here for more information on becoming a member.

Keywords