Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Dec;31(6):895-903.
doi: 10.1007/s10278-018-0093-8.

Combination of rs-fMRI and sMRI Data to Discriminate Autism Spectrum Disorders in Young Children Using Deep Belief Network

Maryam Akhavan Aghdam  1 , Arash Sharifi  2 , Mir Mohsen Pedram  3
Affiliations

Combination of rs-fMRI and sMRI Data to Discriminate Autism Spectrum Disorders in Young Children Using Deep Belief Network

Maryam Akhavan Aghdam et al. J Digit Imaging. 2018 Dec.

Abstract

In recent years, the use of advanced magnetic resonance (MR) imaging methods such as functional magnetic resonance imaging (fMRI) and structural magnetic resonance imaging (sMRI) has recorded a great increase in neuropsychiatric disorders. Deep learning is a branch of machine learning that is increasingly being used for applications of medical image analysis such as computer-aided diagnosis. In a bid to classify and represent learning tasks, this study utilized one of the most powerful deep learning algorithms (deep belief network (DBN)) for the combination of data from Autism Brain Imaging Data Exchange I and II (ABIDE I and ABIDE II) datasets. The DBN was employed so as to focus on the combination of resting-state fMRI (rs-fMRI), gray matter (GM), and white matter (WM) data. This was done based on the brain regions that were defined using the automated anatomical labeling (AAL), in order to classify autism spectrum disorders (ASDs) from typical controls (TCs). Since the diagnosis of ASD is much more effective at an early age, only 185 individuals (116 ASD and 69 TC) ranging in age from 5 to 10 years were included in this analysis. In contrast, the proposed method is used to exploit the latent or abstract high-level features inside rs-fMRI and sMRI data while the old methods consider only the simple low-level features extracted from neuroimages. Moreover, combining multiple data types and increasing the depth of DBN can improve classification accuracy. In this study, the best combination comprised rs-fMRI, GM, and WM for DBN of depth 3 with 65.56% accuracy (sensitivity = 84%, specificity = 32.96%, F1 score = 74.76%) obtained via 10-fold cross-validation. This result outperforms previously presented methods on ABIDE I dataset.

Keywords: Autism spectrum disorder; Deep belief network; Gray matter; White matter; rs-fMRI; sMRI.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Structure of RBM
Fig. 2
Fig. 2
Architecture of DBN
Fig. 3
Fig. 3
Illustration of combination of rs-fMRI, GM, and WM to discriminate ASD using DBN
See this image and copyright information in PMC

References

    1. Rapin I, Tuchman RF. What is new in autism? Curr Opin Neurol. 2008;21(2):143–149. doi: 10.1097/WCO.0b013e3282f49579. - DOI - PubMed
    1. Mueller S, Keeser D, Reiser MF, Teipel S, Meindl T. Functional and Structural MR Imaging in Neuropsychiatric Disorders, Part 2: Application in Schizophrenia and Autism. AJNR Am J Neuroradiol. 2012;33:2033–2037. doi: 10.3174/ajnr.A2800. - DOI - PMC - PubMed
    1. Office of Special Education Programs, United States Department Of Education, Twenty-Seventh Annual Report to Congress on the Implementation of the Individuals with Dis- abilities Education Act, 2005.
    1. Levy SE, Mandell DS, Schultz RT. Autism. The Lancet. 2009;374(9701):1627–1638. doi: 10.1016/S0140-6736(09)61376-3. - DOI - PMC - PubMed
    1. Coleman M, Gillberg C: The Autisms. Oxford; Oxford University Press, 2012