Year: 2023
Type: preprint
Abstract: Brain surface-based image registration, an important component of brain image analysis, establishes spatial correspondence between cortical surfaces. Existing iterative and learning-based approaches focus on accurate registration of folding patterns of the cerebral cortex, and assume that geometry predicts function and thus functional areas will also be well aligned. However, structure/functional variability of anatomically corresponding areas across subjects has been widely reported. In this work, we introduce a learning-based cortical registration framework, JOSA, which jointly aligns folding patterns and functional maps while simultaneously learning an optimal atlas. We demonstrate that JOSA can substantially improve registration performance in both anatomical and functional domains over existing methods. By employing a semi-supervised training strategy, the proposed framework obviates the need for functional data during inference, enabling its use in broad neuroscientific domains where functional data may not be observed. The source code of JOSA will be released to the public at https://voxelmorph.net.
Source: PubMed
Institutions: Harvard University, Massachusetts General Hospital, Athinoula A. Martinos Center for Biomedical Imaging, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Harvard–MIT Division of Health Sciences and Technology, MIT Computer Science and Artificial Intelligence Laboratory
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: James S. McDonnell Foundation, Massachusetts General Hospital, Massachusetts Life Sciences Center, National Institutes of Health, National Institute on Aging, National Institute of Mental Health, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, National Center for Research Resources
Awards: G106490469, G15294626, G1624508038, Brainstem Connectome Mapping to Guide Targeted Stimulant Therapy in Patients with Traumatic Coma, G323562261, Segmenting Brain Structures for Neurological Disorders, G3449921146, G3871521202, Inferring in Vivo Cytoarchitectural Borders in the Medial Temporal Lobe, The Human Connectome Project (HCP), OCTology: histology using optical coherence tomography, A Connectome-Based Clinical Trial Platform to Promote Early Recovery of Consciousness after Traumatic Coma, Deep Learning Algorithms for FreeSurfer, G4899427087, G5047070131, G5100925459, Nobrainer: A robust and validated neural network tool suite for imagers, Computeserver Structural &Functional Image Analysis, G6296793415, Neuropathology of CTE and Delayed Effects of TBI: Toward In-Vivo Diagnostics, MRI, Genetics & Cognitive Precursors of AD and Dementia, Open-source software for multi-scale mapping of the human brain, Clinical & biological signatures of post-traumatic neurodegeneration: Toward in vivo diagnosis of the late effects of TBI., G676694993, Deep Learning Algorithms for FreeSurfer, Software Tools for Automated Modeling of White Matter Fascicles from Diffusion MR, G7692753977, G7736301671, G8465508463, G8466584972, Epidemiology of Dementia in the Framingham Study, A Storage Area Network for Structural and Functional Image Analysis, G9000008748, G9000012841, G9000052245, G9000118446, G9000185783, G9000209268, G9000339556, Functionally guided adult whole brain cell atlas in human and NHP, FreeSurfer Development, Maintenance, and Hardening, Silicon Graphics Prism Extreme 128P/1TB
OpenAlex ID: W4323545007