A Deep-Generative Hybrid Model to Integrate Multimodal and Dynamic Connectivity for Predicting Spectrum-Level Deficits in Autism

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: D'Souza, Niharika Shimona, Nebel, Mary Beth, Crocetti, Deana, Wymbs, Nicholas, Robinson, Joshua, Mostofsky, Stewart, Venkataraman, Archana
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916491165696000
author D'Souza, Niharika Shimona
Nebel, Mary Beth
Crocetti, Deana
Wymbs, Nicholas
Robinson, Joshua
Mostofsky, Stewart
Venkataraman, Archana
author_facet D'Souza, Niharika Shimona
Nebel, Mary Beth
Crocetti, Deana
Wymbs, Nicholas
Robinson, Joshua
Mostofsky, Stewart
Venkataraman, Archana
contents We propose an integrated deep-generative framework, that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract predictive biomarkers of a disease. The generative part of our framework 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 patient-specific loadings. This matrix factorization is guided by the DTI tractography matrices to learn anatomically informed connectivity profiles. The deep part of our framework is an LSTM-ANN block, which models the temporal evolution of the patient sr-DDL loadings to predict multidimensional clinical severity. Our coupled optimization procedure collectively estimates the basis networks, the patient-specific dynamic loadings, and the neural network weights. We validate our framework on a multi-score prediction task in 57 patients diagnosed with Autism Spectrum Disorder (ASD). Our hybrid model outperforms state-of-the-art baselines in a five-fold cross validated setting and extracts interpretable multimodal neural signatures of brain dysfunction in ASD.
format Preprint
id arxiv_https___arxiv_org_abs_2007_01931
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle A Deep-Generative Hybrid Model to Integrate Multimodal and Dynamic Connectivity for Predicting Spectrum-Level Deficits in Autism
D'Souza, Niharika Shimona
Nebel, Mary Beth
Crocetti, Deana
Wymbs, Nicholas
Robinson, Joshua
Mostofsky, Stewart
Venkataraman, Archana
Machine Learning
Signal Processing
We propose an integrated deep-generative framework, that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract predictive biomarkers of a disease. The generative part of our framework 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 patient-specific loadings. This matrix factorization is guided by the DTI tractography matrices to learn anatomically informed connectivity profiles. The deep part of our framework is an LSTM-ANN block, which models the temporal evolution of the patient sr-DDL loadings to predict multidimensional clinical severity. Our coupled optimization procedure collectively estimates the basis networks, the patient-specific dynamic loadings, and the neural network weights. We validate our framework on a multi-score prediction task in 57 patients diagnosed with Autism Spectrum Disorder (ASD). Our hybrid model outperforms state-of-the-art baselines in a five-fold cross validated setting and extracts interpretable multimodal neural signatures of brain dysfunction in ASD.
title A Deep-Generative Hybrid Model to Integrate Multimodal and Dynamic Connectivity for Predicting Spectrum-Level Deficits in Autism
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2007.01931