Open Access

ARTICLE

A Novel Image Categorization Strategy Based on Salp Swarm Algorithm to Enhance Efficiency of MRI Images

by Mohammad Behrouzian Nejad, Mohammad Ebrahim Shiri Ahmadabadi

1 Department of Computer Engineering, Borujerd Branch, Islamic Azad University, Borujerd, Iran.
2 Department of Mathematics and Computer Science, Amirkabir University, Tehran, Iran.
* Corresponding Author: Mohammad Ebrahim Shiri Ahmadabadi. Email: Shiri@aut.ac.ir.

Computer Modeling in Engineering & Sciences 2019, 119(1), 185-205. https://doi.org/10.32604/cmes.2019.01838

Abstract

The main target of this paper is presentation of an efficient method for MRI images classification so that it can be used to diagnose patients and non-patients. Image classification is one of the prominent subset topics of machine learning and data mining that the most important image technique is the auto-categorization of images. MRI images with high resolution and appropriate accuracy allow physicians to decide on the diagnosis of various diseases and treat them. The auto categorization of MRI images toward diagnosing brain diseases has been being used to accurately diagnose hospitals, clinics, physicians and medical research centers. In this paper, an effective method is proposed for categorizing MRI images, which emphasizes the classification stage. In this method, images have been firstly collected and tagged, and then the discrete wavelet transform method has been implemented to extract the relevant properties. All the ready features in a matrix will be subsequently held, and PCA method has been applied to reduce the features dimension. Furthermore, a new model using support vector machine classifier with radial basis function kernel i.e. SVM+RBF has been performed. The SVM Algorithm must bimanually initialized, while, these values have been automatically entered into the SVM classifier by Salp Swarm Algorithm (SSA): Due to high performance of SSA in fast and accurate solution of nonlinear problem as compared to other optimization algorithms, it has been applied to optimally solve the designed problem. Finally, after applying the optimal parameters and SVM classification training, the test data has been utilized and evaluated. The results have transparently suggested the effectiveness of the proposed method in the Accuracy criteria with 0.9833, the Sensitivity with 1, Specificity with 0.9818 and Error with 0.0167 in best iteration as compared to the conventional SVM method.

---

Keywords

---