Keywords: Neuro, Pediatric, Brain age prediction, Myelination, Multi-contrast, Attention-guided Network
Motivation: Comprehending pediatric brain maturation with high precision remains a challenge in clinical practice. This study focuses on the necessity of accurate brain age prediction to assess myelination, a vital factor in early neurodevelopment.
Goal(s): To develop a deep learning model that utilizes T1 and T2 MRI contrasts to accurately predict pediatric brain age, with an emphasis on myelination.
Approach: A dual-branch network architecture with attention guidance was used, directing the model’s focus on white matter to improve sensitivity to developmental changes.
Results: The model achieved an MAE of 0.46 months on training set and 1.61 months on validation/test, effectively highlighting key myelination regions.
Impact: This model improves pediatric brain age prediction by accurately identifying myelination regions, providing clinicians with enhanced insights into early neurodevelopmental progress. This approach presents potential for early intervention and monitoring of neurodevelopmental disorders, developing clinical resources in pediatric neurology.
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