Diagnostic of autism spectrum disorder based on structural brain MRI images using, grid search optimization, and convolutional neural networks

•A two-stage automatic autism spectrum disease (ASD) diagnostic model based on sMRI.•1st stage consists of identifying edges of images by canny edge detection algorithm.•2nd stage, grid search optimization is applied to convolutional neural networks.•Proposed diagnostic method of ASD based on sMRI achieves a success rate of 100%•Superiority is shown by comparing it with recent studies and pre-trained models.