Abstract
As the autism spectrum disorder (ASD) is highly heritable, pervasive and prevalent, the clinical diagnosis of ASD is vital. In the existing literature, a single neural network (NN) is generally used to classify ASD patients from typical controls (TC) based on functional MRI data and the accuracy is not very high. Thus, the new method named as the random NN cluster, which consists of multiple NNs was proposed to classify ASD patients and TC in this article. Fifty ASD patients and 42 TC were selected from autism brain imaging data exchange (ABIDE) database. First, five different NNs were applied to build five types of random NN clusters. Second, the accuracies of the five types of random NN clusters were compared to select the highest one. The random Elman NN cluster had the highest accuracy, thus Elman NN was selected as the best base classifier. Then, we used the significant features between ASD patients and TC to find out abnormal brain regions which include the supplementary motor area, the median cingulate and paracingulate gyri, the fusiform gyrus (FG) and the insula (INS). The proposed method provides a new perspective to improve classification performance and it is meaningful for the diagnosis of ASD.
Highlights
Autism spectrum disorder (ASD) characterized by impairments in social deficits and communication (Knaus et al, 2008) is a typically neurological disease with high heredity (Baird et al, 2006) and prevalence (Chakrabarti and Fombonne, 2001)
One of the ways is the usage of the neuroimaging technique, such as Electroencephalogram (EEG; Peters et al, 2013), positron emission tomography (PET; Pagani et al, 2017), structural magnetic resonance imaging and functional magnetic resonance imaging
It is referred that the accuracies of the random Competition neural network (NN) cluster and the accuracies of the random learning vector quantization (LVQ) NN cluster are not high; the accuracies of the random Elman NN cluster fluctuate around 95%, even nearly reach to 100%; the accuracies of the random BP NN cluster and the random Probabilistic NN cluster are higher than the random Competition NN cluster and the random LVQ NN cluster
Summary
Autism spectrum disorder (ASD) characterized by impairments in social deficits and communication (Knaus et al, 2008) is a typically neurological disease with high heredity (Baird et al, 2006) and prevalence (Chakrabarti and Fombonne, 2001). The traditional diagnostic methods are mainly based on clinical interviews and behavior observation, which makes the diagnosis inaccurate. There are two ways that could be applied to improve the diagnostic accuracy of ASD. One of the ways is the usage of the neuroimaging technique, such as Electroencephalogram (EEG; Peters et al, 2013), positron emission tomography (PET; Pagani et al, 2017), structural magnetic resonance imaging (sMRI; Sato et al, 2013) and functional magnetic resonance imaging (fMRI; Ren et al, 2014). The specific properties of fMRI make it widely used (Bennett et al, 2017). Another way is the usage of machine learning which could automatically improve the algorithm performance based on the previous experiences (Jordan and Mitchell, 2015). Iidaka (2015) applied probabilistic neural
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
