Meeting Banner
Abstract #3227

Cross-Modal Text Prompts Specified MRI-to-PET Dynamic Image Translation

Yizhou Jiang1, Yuxi Jin1, Haizhou Liu1, Yi An1, Na Zhang1, Hairong Zheng1, Dong Liang1, Jianjun Liu2, Ruohua Chen2, and Zhanli Hu1
1Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 2Department of Nuclear Medicine, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China

Synopsis

Keywords: AI Diffusion Models, PET/MR, Modal-translation

Motivation: MRI is widely used in clinical settings for its high resolution, but it cannot provide the metabolic information as PET scans. However, PET scans rely on radioactive tracers and pose risks for patients. This study aims to reduce reliance on radioactive tracers by generating PET images from MRI with text prompts.

Goal(s): To develop a text-guided MRI-to-PET model using diffusion models, enabling PET synthesis with tracer-specific characteristics.

Approach: A diffusion-based model with cross-modal attention was designed, allowing MRI-to-PET generation based on text prompts.

Results: The model generated text specified PET images from MRI inputs, with strong similarity to real PET scans.

Impact: This approach offers a safer imaging alternative by generating synthesis PET images without radioactive tracers, supporting disease diagnosis and monitoring with reduced patient risk. This development could broaden MRI’s clinical application, fostering multi-tracer insights in resource-limited settings.

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