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

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neurology

Background:

• Multiple Sclerosis (MS) diagnosis is challenging, requiring expertise and time.
• Current diagnostic methods for MS can be slow and resource-intensive.
• There is a need for efficient and accurate tools for early MS detection.

Purpose of the Study:

• To develop an AI-enhanced methodology for expedited and accurate Multiple Sclerosis (MS) diagnosis.
• To improve early identification and management of MS through advanced imaging analysis.
• To create a novel feature selection technique for enhanced diagnostic accuracy.

Main Methods:

• Feature extraction from brain MRI using first-order histograms, Gray Level Co-occurrence Matrix (GLCM), and Local Binary Patterns (LBP).
• A hybrid feature selection method combining Sine Cosine Algorithm (SCA) and Sea-horse Optimizer (SHO).
• Classification using k-nearest neighbors (KNN) and Random Forest (RF) algorithms on distinct datasets.

Main Results:

• Achieved 97.97% accuracy on the eHealth lab dataset (38 MS patients) using KNN.
• Demonstrated 92.94% accuracy for FLAIR and 91.25% for T2-weighted images on a larger dataset (262 MS cases) using RF.
• The proposed AI methodology outperformed existing methods for MS detection.

Conclusions:

• The AI-enhanced methodology shows significant potential for clinical decision-making in MS diagnosis.
• This approach facilitates expedited and accurate identification of Multiple Sclerosis.
• The study highlights the effectiveness of advanced feature selection and machine learning for neurological disorder diagnosis.