JOSA: Joint surface-based registration and atlas construction of brain geometry and function
This work addresses the challenge of aligning brain function across subjects in medical image analysis, particularly for higher-order cognitive areas, offering a novel approach that could improve downstream applications in neuroscience and clinical settings.
The paper tackled the problem of cortical registration by addressing the mismatch between brain geometry and function, proposing JOSA, a framework that jointly models this mismatch and learns an unbiased atlas, achieving superior registration performance in both geometry and function compared to state-of-the-art methods without requiring functional data at inference.
Surface-based cortical registration is an important topic in medical image analysis and facilitates many downstream applications. Current approaches for cortical registration are mainly driven by geometric features, such as sulcal depth and curvature, and often assume that registration of folding patterns leads to alignment of brain function. However, functional variability of anatomically corresponding areas across subjects has been widely reported, particularly in higher-order cognitive areas. In this work, we present JOSA, a novel cortical registration framework that jointly models the mismatch between geometry and function while simultaneously learning an unbiased population-specific atlas. Using a semi-supervised training strategy, JOSA achieves superior registration performance in both geometry and function to the state-of-the-art methods but without requiring functional data at inference. This learning framework can be extended to any auxiliary data to guide spherical registration that is available during training but is difficult or impossible to obtain during inference, such as parcellations, architectonic identity, transcriptomic information, and molecular profiles. By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of the brain structure and function.