Dataset Information

Deep sr-DDL: Deep structurally regularized dynamic dictionary learning to integrate multimodal and dynamic functional connectomics data for multidimensional clinical characterizations.

ABSTRACT: We propose a novel integrated framework that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract biomarkers of brain connectivity predictive of behavior. Our framework couples a generative model of the connectomics data with a deep network that predicts behavioral scores. The generative component is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying subject-specific loadings. We use the DTI tractography to regularize this matrix factorization and learn anatomically informed functional connectivity profiles. The deep component of our framework is an LSTM-ANN block, which uses the temporal evolution of the subject-specific sr-DDL loadings to predict multidimensional clinical characterizations. Our joint optimization strategy collectively estimates the basis networks, the subject-specific time-varying loadings, and the neural network weights. We validate our framework on a dataset of neurotypical individuals from the Human Connectome Project (HCP) database to map to cognition and on a separate multi-score prediction task on individuals diagnosed with Autism Spectrum Disorder (ASD) in a five-fold cross validation setting. Our hybrid model outperforms several state-of-the-art approaches at clinical outcome prediction and learns interpretable multimodal neural signatures of brain organization.

SUBMITTER: D'Souza NS

PROVIDER: S-EPMC8528511 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Schizophrenia is a very complex syndrome that involves widespread brain multi-dysconnectivity. Neural circuits within specific brain regions and their links to corresponding regions are abnormal in the illness. Theoretical models of dysconnectivity and the investigation of connectomics and brain network organization have been examined in schizophrenia since the early nineteenth century. In more recent years, advancements have been achieved with the development of neuroimaging tools that have provided further clues to the structural and functional organization of the brain and global neural networks in the illness. Neural circuitry that extends across prefrontal, temporal and parietal areas of the cortex as well as limbic and other subcortical brain regions is disrupted in schizophrenia. As a result, many patients have a poor response to antipsychotic treatment and treatment failure is common. Treatment resistance that is specific to positive, negative, and cognitive domains of the illness may be related to distinct circuit phenotypes unique to treatment-refractory disease. Currently, there are no customized neural circuit-specific and targeted therapies that address this neural dysconnectivity. Investigation of targeted therapeutics that addresses particular areas of substantial regional dysconnectivity is an intriguing approach to precision medicine in schizophrenia. This review examines current findings of system and circuit-level brain dysconnectivity in treatment-resistant schizophrenia based on neuroimaging studies. Within a connectome context, on-off circuit connectivity synonymous with excitatory and inhibitory neuronal pathways is discussed. Mechanistic cellular, neurochemical and molecular studies are included with specific emphasis given to cell pathology and synaptic communication in glutamatergic and GABAergic systems. In this review we attempt to deconstruct how augmenting treatments may be applied within a circuit context to improve circuit integration and treatment response. Clinical studies that have used a variety of glutamate receptor and GABA interneuron modulators, nitric oxide-based therapies and a variety of other strategies as augmenting treatments with antipsychotic drugs are included. This review supports the idea that the methodical mapping of system-level networks to both on (excitatory) and off (inhibitory) cellular circuits specific to treatment-resistant disease may be a logical and productive approach in directing future research toward the advancement of targeted pharmacotherapeutics in schizophrenia.

Dataset Information

Deep sr-DDL: Deep structurally regularized dynamic dictionary learning to integrate multimodal and dynamic functional connectomics data for multidimensional clinical characterizations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets