AI-based model for automatic identification of multiple sclerosis based on enhanced sea-horse optimizer and MRI scans

Abstract

This study aims to develop an AI-enhanced methodology for the expedited and accurate diagnosis of Multiple Sclerosis (MS), a chronic disease affecting the central nervous system leading to progressive impairment. Traditional diagnostic methods are slow and require substantial expertise, underscoring the need for innovative solutions. Our approach involves two phases: initially, extracting features from brain MRI images using first-order histograms, the gray level co-occurrence matrix, and local binary patterns. A unique feature selection technique combining the Sine Cosine Algorithm with the Sea-horse Optimizer is then employed to identify the most significant features. Utilizing the eHealth lab dataset, which includes images from 38 MS patients (mean age 34.1 ± 10.5 years; 17 males, 21 females) and matched healthy controls, our model achieved a remarkable 97.97% detection accuracy using the k-nearest neighbors classifier. Further validation on a larger dataset containing 262 MS cases (199 females, 63 males; mean age 31.26 ± 10.34 years) and 163 healthy individuals (109 females, 54 males; mean age 32.35 ± 10.30 years) demonstrated a 92.94% accuracy for FLAIR images and 91.25% for T2-weighted images with the Random Forest classifier, outperforming existing MS detection methods. These results highlight the potential of the proposed technique as a clinical decision-making tool for the early identification and management of MS.

Keywords: AI-based diagnosis; Feature selection; Magnetic resonance imaging (MRI); Multiple sclerosis (MS); Sea-horse optimizer (SHO).

Algorithm 1

Steps of the original SHO.

Algorithm 2

The SCA Pseudo code algorithm

Figure 1

The structure of the proposed MS detection method.

Figure 2

Flowchart of the enhanced SHOSCA algorithm.

Algorithm 3

Steps of the proposed MS detection approach.

Figure 3

Brain slices samples from the GRMS dataset. (a) & (b) Two MS slices with multiple plaques. (c) & (d) Two healthy brain slices.

Figure 4

Boxplot of proposed SHOSCA versus state-of-the-art optimization approaches. (a) Accuracy; (b) Precision; (c) Recall; (d) F1 Score.

Figure 5

Convergence curve of the proposed method versus other optimization algorithms.

Figure 6

Convergence curve of the developed method in comparison to other hybrid models of the SHO.

Figure 7

Boxplots for comparison between Random Forest (RF) and K-Nearest Neighbors (KNN) classifiers for the MS detection method. (a) Accuracy; (b) Precision; (c) Recall; (d) F1 Score.

Figure 8

Sample of brain slices from the eHealth lab and GRMS datasets. (a) & (b) Two MS slices from the eHealth lab dataset with delineated plaques (Lesions are surrounded by red lines). (c) & (d) Two healthy brain slices from our GRMS dataset.