Abstract #1687

DeepGrasp-T2 Mapping: Accelerated T2 Mapping Combining Radial Acquisition, Self-Supervised Deep Learning Reconstruction, and EMC Modeling

Haoyang Pei^1,2,3, Mahesh Keerthivasan⁴, Justin Quimbo^1,2, Yuhui Huang^1,2, Fei Han⁵, Iman Khodarahmi^1,2, Angela Tong^1,2, Hersh Chandarana^1,2, and Li Feng^1,2

¹Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States, ²Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States, ³Department of Electrical and Computer Engineering, NYU Tandon School of Engineering, New York, NY, United States, ⁴MR R&D Collaborations, Siemens Medical Solutions USA Inc, New York, NY, United States, ⁵MR R&D Collaborations, Siemens MedicalSolutions USA, Inc, Los Angeles, CA, United States

Synopsis

Keywords: Quantitative Imaging, AI/ML Image Reconstruction, T2 Mapping

Motivation: GRASP MRI has been adapted for quantitative T1 mapping and combined with deep learning reconstruction to improve image quality, acceleration rates, and reconstruction speed. Extending this to quantitative T2 mapping holds great clinical potential.

Goal(s): In this work, we present an extended version of this technique, called DeepGrasp-T2 mapping, for accelerated quantitative T2 mapping.

Approach: DeepGrasp-T2 employs a combination of self-supervised learning reconstruction and GPU-accelerated parallel fitting, incorporating a novel low-rank subspace-assisted strategy to enhance image quality and accelerate training speed.

Results: DeepGrasp-T2 allows for efficient and accurate T2 mapping.

Impact: This work proposed DeepGrasp-T2, a self-supervised learning based approach that allows for rapid and accurate T2 mapping without requiring reference images for network training, offerring potential for different clinical applications such as prostate T2 mapping.

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.