Keywords: AI/ML Image Reconstruction, AI/ML Image Reconstruction, 4D-MRI\Super-resolution\Spatiatemporal Information
Motivation: Four-dimensional MRI (4D-MRI) holds significant potential for abdominal radiotherapy, yet it faces a persistent trade-off between spatial and temporal resolution, often leading to undersampled images with motion artifacts.
Goal(s): Existing super-resolution models struggle to recover fine details under these conditions. We introduce MCRNet, a multi-frame compensated network designed to enhance abdominal 4D-MRI by leveraging frame redundancy across respiratory cycles.
Approach: MCRNet integrates two key modules: the Frame Synergy Attention Module (FSAM) and the Structure-Aware Consolidation Module (SaCM), which together enhance anatomical feature extraction while suppressing artifacts.
Results: Comprehensive experiments demonstrate that MCRNet surpasses state-of-the-art methods, effectively restoring anatomical features with minimal artifacts.
Impact: MCRNet significantly improves 4D-MRI quality by achieving high spatiotemporal resolution, reducing noise and artifacts, and restoring anatomical structures.
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.
Keywords