Automatic diagnosis of schizophrenia and attention deficit hyperactivity disorder in rs-fMRI modality using convolutional autoencoder model and interval type-2 fuzzy regression

Nowadays, many people worldwide suffer from brain disorders, and their health is in danger. So far, numerous methods have been proposed for the diagnosis of Schizophrenia (SZ) attention deficit hyperactivity disorder (ADHD), among which functional magnetic resonance imaging (fMRI) modalities are known as a popular method physicians. This paper presents an SZ ADHD intelligent detection resting-state fMRI (rs-fMRI) modality using new deep learning method. The University California Los Angeles dataset, contains rs-fMRI patients, has used experiments. FMRIB software library toolbox first performed preprocessing on data. Then, convolutional Autoencoder model with number layers to extract features In classification step, fuzzy called interval type-2 regression (IT2FR) introduced then optimized by genetic algorithm, particle swarm optimization, gray wolf optimization (GWO) techniques. Also, results IT2FR compared multilayer perceptron, k-nearest neighbors, support vector machine, random forest, decision tree, adaptive neuro-fuzzy inference system methods. experiment show that GWO algorithm achieved satisfactory other classifier Finally, technique was able provide 72.71% accuracy.