Hybrid deep learning and feature optimization approach for early detection of multiple sclerosis

The healthcare field increasingly relies on autonomous systems for the detection and analysis of Multiple Sclerosis (MS) to minimize diagnostic delays, resource burdens, reduce the progression of disability, and enhance clinical decision-making efficiency. Such systems ensure accurate and timely treatment, ultimately improved patient outcomes. In this study, a hybrid framework combining deep learning-based feature extraction, metaheuristic feature selection, and machine learning (ML) classifiers is proposed for accurate MS classification. All MRI images were preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE), resizing, and normalization to enhance contrast and standardize the input dimensions. Deep features were extracted using the pretrained VGG16 convolutional neural network (CNN), in which the fully connected layers were removed, and the convolutional base was used to obtain high-dimensional features per image. To reduce dimensionality and improve classification performance, the Whale Optimization Algorithm (WOA) was employed to select the most discriminative subset of features using a Support Vector Machine (SVM)-based fitness function. Multiple classifiers were then trained and evaluated using the optimized feature set. Among them, the Artificial Neural Network integrated with WOA (ANN+WOA) achieved the highest classification accuracy of 98%, demonstrating the potential of the proposed model for reliable, efficient, and automated MS diagnosis.