Abstract #3839

Multimodal Feature-Guided Diffusion Model for Low-Dose PET Image Denoising with MRI

Yuxi Jin¹, Gengjia Lin², Haizhou Liu³, Chao Zhou⁴, Xu Zhang⁴, Wei Fan⁴, Na Zhang⁵, Hairong Zheng⁶, Dong Liang⁵, Peng Cao⁷, and Zhanli Hu¹

¹Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, ²College of Computer Science and Engineering, Northeastern University, Shenzhen, China, ³National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital and Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China, ⁴Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China, ⁵Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, ⁶Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, ⁷College of Computer Science and Engineering, Northeastern University, Shenyang, China

Synopsis

Keywords: AI Diffusion Models, Data Processing, MRI-Aided Low-Dolse PET Imaging, Diffusion Model, Multi-Modal Fusion

Motivation: With the advent of integrated PET/MR imaging devices, the high-resolution anatomical information from MRI can help enhance the quality of PET images.

Goal(s): Utilizing MRI structural information to optimize the quality of low-dose PET imaging, thereby reducing the risk of radiation exposure for patients.

Approach: We use a cross-modal guided restoration network to fully exploit the modality-specific features of LPET and MR images and employ cross-attention mechanisms and positional encoding at multiple feature levels for better feature fusion.

Results: The images generated by our proposed network showed superior performance compared to those produced by other networks in both qualitative and quantitative evaluations.

Impact: The research can enhance the quality of low-dose PET imaging and reduce the radiation risk for patients, and it also inspires more feasible imaging solutions for the global health field, holding significant scientific and clinical importance.

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.