Meeting Banner
Abstract #3858

Specialized Coil Informed Deep Learning for High SNR Carotid Imaging

Lisha Zeng1,2, Meng Lu1, Yin-Chen Hsu1, Mary Keushkerian3,4, Kim-Lien Nguyen3,4, Kevin Johnson5, Maria Altbach5,6, H. Douglas Morris7, J. Kevin DeMarco7, Vibhas Deshpande8, Dimitrios Mitsouras9, David Saloner9, Scott McNally 10, Seong-Eun Kim10, John Roberts10, Rock Hadley 10, Gerald Treiman11, Dennis Parker10, Debiao Li1,2, and Yibin Xie1
1Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, United States, 2Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, United States, 3Departments of Cardiology, Radiology, and Bioengineering, University of California, Los Angeles, Los Angeles, CA, United States, 4VA Greater Los Angeles Healthcare System, Los Angeles, CA, United States, 5Department of Medical Imaging, University of Arizona, Tucson, AZ, United States, 6Department of Biomedical Engneering, University of Arizona, Tucson, AZ, United States, 7Walter Reed National Military Medical Center, Bethesda, MD, United States, 8Siemens Medical Solutions, Austin, TX, United States, 9Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 10Department of Radiology & Imaging Sciences, University of Utah, Salt Lake City, UT, United States, 11VA Salt Lake City, Salt Lake City, UT, United States

Synopsis

Keywords: AI/ML Image Reconstruction, Blood vessels, Denoising; Plaque Characterization; MRA

Motivation: Noise from standard commercial head-neck coils used for carotid MR hinders effective evaluation of high-risk plaque characteristics, while specialized carotid coils remain costly and are not widely available.

Goal(s): We aim to match the signal-to-noise ratio and quality of images obtained from standard head-neck coils to those of dedicated carotid coils.

Approach: A supervised deep learning method was developed to improve carotid MR image quality using data acquired with specialized carotid coil as the reference.

Results: Significant improvements in SNR and image quality were observed for multi-contrast images and T1/ T2 maps.

Impact: With the use of our DL model, high SNR images are achievable with standard head-neck coils, which may help radiologists to be more confident and efficient in evaluating carotid plaque characteristics.

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