Dimension Reduction in fMRI Images based on Metaheuristic Algorithm to Diagnose Autism

Autism Spectrum Disorder (ASD) is a mental disorder and affects a person's linguistic skills and social interactions. With the production of Functional Magnetic Resonance Imaging (fMRI) and the development of their processing tools, the use of these images in identifying and evaluating the brain function of autistic people received a lot of attention. However, in this approach using the functional connectivity matrices leads to the creation of feature space with very high dimensions. Some of these features are dependent, unnecessary and additional, which reduces the quality of detection and increases the number of calculations. Therefore, regarding the large dimensions of the search space, the Particle Swarm Optimization (PSO) algorithm has been used as one of the powerful meta-heuristic search tools in selecting the optimal features.

To evaluate the capability of the proposed method, the principal component analysis (PCA) algorithm is used as a standard dimension reduction method. In this study, the Support Vector Machines (SVM) classifier was used to detect autistic and healthy persons on the ABIDE database data. Feature space has been generated based on a functional connectivity matrix which has 6670 dimensions.

SVM accuracy in high-dimensional specialty space is 56%. The proposed method based on PSO eliminates 3442 redundant features and increases classification accuracy up to 62.19 % that performs better than PCA. The findings show that this meta-heuristic algorithm by removing almost half of the features results in a 6% increase in classification precision.

The results indicate the ability of SVM in comparison with the Random Forest and K-Nearest Neighbor (KNN). PSO algorithm was used for dimension reduction of the input data space.