Meeting Banner
Abstract #0932

LGEDiffusion: A Multi-Sequence Guided Diffusion Model for Virtual Contrast-Free LGE Generation in Myocardial Infarction

Jing Qi1, Xiuzheng Yue1,2, Miao Hu1, Jianan Li1, Tao Li3, and Kunlun He1
1Medical Innovation Research Department, Chinese PLA General Hospital, Beijing, China, 2Philips Healthcare, Beijing, China, 3Department of Radiology, the First Medical Center, Chinese PLA General Hospital, Beijing, China

Synopsis

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence

Motivation: Virtual LGE generation technology could reduce cardiac MRI (CMR) scan time, avoid gadolinium-based contrast agent (GBCA) risks, and benefit patients with GBCA contraindications.

Goal(s): To develop and evaluate a multi-sequence CMR-guided virtual LGE generation technique, focusing on accuracy, effectiveness, and stability.

Approach: A virtual LGE generation model based on a diffusion model was developed, leveraging Cine motion and T2 edema information for condition guidance.

Results: Virtual LGE demonstrated high consistency with native LGE for identifying myocardial infarction lesions in terms of location and size, suggesting potential clinical applicability.

Impact: This study highlights the potential of denoising diffusion probabilistic models for multi-sequence-guided MRI translation, emphasizing the value of virtual LGE as a viable contrast-free imaging alternative for myocardial infarction assessment.

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