Keywords: Segmentation, Machine Learning/Artificial Intelligence, fast imaging，whole brain segmentation
Motivation: 3D structural brain MRI and accurate region segmentation are important for neurological research and clinical applications, but they are time-consuming in both acquisition and processing.
Goal(s): This study aims to achieve simultaneous high-resolution 3D T1W brain imaging and precise whole-brain segmentation in just 36 seconds.
Approach: A dual-task transformer-based network was developed to perform both image enhancement and brain region segmentation using data acquired in 36-second on a 5.0T MRI system.
Results: The proposed method produced high-quality images and accurate segmentation (Dice 0.83） comparable to 3-min 36-second standard scans, offering an ultra-fast solution for clinical applications.
Impact: This study implemented a dual-task transformer-based network on a 5.0T MRI platform, enabling high-resolution 3D T1W brain imaging and accurate segmentation in 36 seconds. With performance comparable to conventional 3-min 36-second scans, this approach offers a promising ultra-fast clinical solution.
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