Meeting Banner
Abstract #3100

Feasibility and Clinical Utility of Deep Learning-Based Composite Super-Resolution Reconstruction for Knee MRI

Xi Zhu1,2, Jie Shi3, Jing Ye1, Wennuo Huang1, Wei Xia1, and Zhuqing Bao4
1Department of Radiology, Northern Jiangsu People's Hospital, Yangzhou, China, 2College of Biological Sciences and Medical Engineering, Southeast University, Nanjing, China, 3MR Research, GE Healthcare, Beijing, China, 4Department of Emergency, Northern Jiangsu People's Hospital, Yangzhou, China

Synopsis

Keywords: Joint, Bone

Motivation: The knee joint is prone to degenerative changes and injuries. Conventional knee MRI is important but often has low efficiency and reduced image quality. Deep learning-based super-resolution techniques show potential to address these issues, but clinical validation is needed to confirm practical benefits.

Goal(s): Investigate the clinical benefits of a deep learning-based composite super-resolution reconstruction approach for knee MRI.

Approach: 110 patients with each scanning conventional and composite super-resolution reconstruction knee MRI were included. Image quality was compared using objective and subjective assessments.

Results: The composite super-resolution reconstruction significantly improved image quality, efficiency, and diagnostic value compared to conventional knee MRI.

Impact: The practice of deep learning-based super-resolution reconstruction would be beneficial for knee MRI overall diagnostic quality and efficiency, further enhancing patient comfort and clinical workflow.

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