Generative Embedding Demonstrates Altered Structural Connectivity in Autism Spectrum Disorder

Loading...
Thumbnail Image
Penn collection
School of Engineering and Applied Science::Department of Bioengineering::Departmental Papers (BE)
Degree type
Discipline
Biomedical Engineering and Bioengineering
Computer Sciences
Neuroscience and Neurobiology
Subject
Autism
Diffusion tensor imaging
Generative network modeling
Spatial embedding
Variational autoencoder
Structural connectivity
Funder
Grant number
Copyright date
2021-09
Distributor
Related resources
Author
Osmanlıoğlu, Yusuf
Parker, Drew
Aunapu, Darien
Yerys, Benjamin E.
Tunç, Birkan
Verma, Ragini
Contributor
Abstract

Studies on neurobiology of autism predominantly focus on describing topological properties of brain connectivity, offering little insight into mechanisms that give rise to associated alterations. Recently, generative network modeling has been proposed to uncover those mechanisms with parameterized wiring rules. However, most models utilize predefined wiring rules, which may not be the best characterization. Here we propose a novel deep learning based generative modeling to infer underlying mechanisms that drive atypical network growth. We demonstrate high similarity of generated network to observed structural networks, with their latent features predicting autism diagnosis. Given the neurobiological interpretability of embedding, our approach shows potential in providing connectomic biomarkers for autism.

Advisor
Date of presentation
2021-09
Conference name
SIIM Conference on Machine Intelligence in Medical Imaging (CMIMI)
Conference dates
2021-09
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection