Integrating functional connectivity and MVPA through a multiple constraint network analysis

• Published in: NeuroImage (Orlando, Fla.) Vol. 208; p. 116412
• Main Authors: McNorgan, Chris, Smith, Gregory J., Edwards, Erica S.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01-03-2020; Elsevier Limited; Elsevier
• Subjects: Activity patterns; Adolescent; Adult; Algorithms; Brain; Brain mapping; Brain Mapping - methods; Brain Mapping - standards; Cerebral cortex; Cerebral Cortex - diagnostic imaging; Cerebral Cortex - physiology; Classification; Cognitive ability; Computational modeling; Concept Formation - physiology; Connectivity; Connectome - methods; Connectome - standards; Female; Functional magnetic resonance imaging; Humans; Imagination - physiology; Information sources; Learning algorithms; Machine learning; Magnetic Resonance Imaging - methods; Magnetic Resonance Imaging - standards; Male; Models, Theoretical; MVPA; Neural networks; Neural Networks, Computer; Neuroimaging; Perception - physiology; Recognition, Psychology - physiology; Semantic memory; Semantics; Studies; Young Adult; Connectivity; Semantic memory; Computational modeling; MVPA; Brain mapping
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2019.116412

Traditional general linear model-based brain mapping efforts using functional neuroimaging are complemented by more recent multivariate pattern analyses (MVPA) that apply machine learning techniques to identify the cognitive states associated with regional BOLD activation patterns, and by connectivity analyses that identify networks of interacting regions that support particular cognitive processes. We introduce a novel analysis representing the union of these approaches, and explore the insights gained when MVPA and functional connectivity analyses are allowed to mutually constrain each other within a single model. We explored multisensory semantic representations of concrete object concepts using a self-paced multisensory imagery task. Multilayer neural networks learned the real-world categories associated with macro-scale cortical BOLD activity patterns from the task, with some models additionally encoding regional functional connectivity. Models trained to encode functional connections demonstrated superior classification accuracy and more pronounced lesion-site appropriate category-specific impairments. We replicated these results in a data set from the openneuro.org open fMRI data repository. We conclude that mutually constrained network analyses encourage parsimonious models that may benefit from improved biological plausibility and facilitate discovery.
•We introduce a data-driven method for bootstrapping biologically plausible models.•Mutually-constraining analyses finds models that best fit all available evidence.•Functional connectivity constraints improved MVPA accuracy.•Mutual-constraint networks simulated lesion-site appropriate impairment.•Models support direct tests of causation between connectivity and representation.