A hybrid approach for analysis of brain lateralisation in autistic children using graph theory techniques and deep belief networks. (3rd June 2022)

• Record Type: Journal Article
• Authors: Srinivasan, Vidhusha; Udayakumar, N.; Liang, Hualou; Anandan, Kavitha
• Is Part Of: International journal of biomedical engineering and technology. Volume 39:Number 1(2022)
• Page Start: 40
• Page End: 64
• Publication Date: 2022-06-03
• Subjects: autism -- autism spectrum disorder -- ASD -- functional magnetic resonance imaging -- fMRI -- lateralisation -- language processing in autism -- high functioning autistic -- HFA -- graph theory -- deep belief networks -- DBNs; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

Lateralisation is the quality of a neural function specialised towards one hemisphere of the brain over the other for a specific activity. Autism individuals possess reduced language processing and impaired communication. This work analyses the lateralisation patterns present at the language regions of the brain for controls, low functioning (LFA) and high functioning autistic (HFA) individuals using resting state fMRI. Totally, 101 participants were considered for this study. The active and inactive regions in the left and right hemisphere, responsible for language processing have been analysed through graph theory. Results showed overall left hemisphere (LH) activation for controls while impaired LH activation for LFAs and unique right hemisphere (RH) activation for the HFAs. Using deep belief networks, the classification accuracy for lateralisation was measured. The accuracy was highest in LH for controls with 97.88% and LFA measuring 78.17% in LH while, the HFA group showed dominance at RH with 94.23%.