Abstract
Despite countless studies on autism spectrum disorder (ASD), diagnosis relies on specific behavioral criteria and neuroimaging biomarkers for the disorder are still relatively scarce and irrelevant for diagnostic workup. Many researchers have focused on functional networks of brain activities using resting-state functional magnetic resonance imaging (rsfMRI) to diagnose brain diseases, including ASD. Although some existing methods are able to reveal the abnormalities in functional networks, they are either highly dependent on prior assumptions for modeling these networks or do not focus on latent functional connectivities (FCs) by considering discriminative relations among FCs in a nonlinear way. In this article, we propose a novel framework to model multiple networks of rsfMRI with data-driven approaches. Specifically, we construct large-scale functional networks with hierarchical clustering and find discriminative connectivity patterns between ASD and normal controls (NC). We then learn features and classifiers for each cluster through discriminative restricted Boltzmann machines (DRBMs). In the testing phase, each DRBM determines whether a test sample is ASD or NC, based on which we make a final decision with a majority voting strategy. We assess the diagnostic performance of the proposed method using public datasets and describe the effectiveness of our method by comparing it to competing methods. We also rigorously analyze FCs learned by DRBMs on each cluster and discover dominant FCs that play a major role in discriminating between ASD and NC. Hum Brain Mapp 38:5804–5821, 2017.
Original language | English |
---|---|
Pages (from-to) | 5804-5821 |
Number of pages | 18 |
Journal | Human Brain Mapping |
Volume | 38 |
Issue number | 11 |
DOIs | |
Publication status | Published - 2017 Nov |
Bibliographical note
Funding Information:Contract grant sponsor: The National Research Foundation of Korea (NRF), Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT); Contract grant numbers: NRF-2015R1C1A1A01052216, IITP-2015-1107 and 2017-0-00451. *Correspondence to: Seong-Whan Lee; Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea. E-mail: [email protected] Received for publication 26 December 2016; Revised 25 July 2017; Accepted 7 August 2017. DOI: 10.1002/hbm.23769 Published online 28 August 2017 in Wiley Online Library (wileyonlinelibrary.com).
Publisher Copyright:
© 2017 Wiley Periodicals, Inc.
Keywords
- autism spectrum disorder
- discriminative restricted Boltzmann machine
- functional magnetic resonance imaging
- functional network analysis
- hierarchical clustering
- multiple clusters
ASJC Scopus subject areas
- Anatomy
- Radiological and Ultrasound Technology
- Radiology Nuclear Medicine and imaging
- Neurology
- Clinical Neurology