Improved multiple sclerosis diagnosis with advanced deep learning techniques

White matter pathologies analysis is important for segmenting multiple sclerosis (MS) lesions in MRI slices. Myelin damage affects motor function, sensory conflicts, paralysis, and vision. Extracting an optimistic number of hidden characteristic features induces high feature maps and reduces redundancy and dimensionality. A framework based on Hybrid Deep Convolutional Neural Networks (HD-CNN) is presented to classify MS based on the acquired optimistic feature characteristic. First, Chaotic Leader-Selective Particle Swarm Optimization uses the pixel intensity ratio of the targeted region to extract the most hidden white matter features. Second, Refined Slime Mold categorizes hidden features and ensures that the necessary features are selected effectively for a better segmentation result. An effective inbuilt Maximum Bidirectional Gradient Classifier accurately classifies MS lesions by detecting white matter spots in the target region. Finally, we will evaluate the proposed HD-CNN framework using the industry-standard University Medical Centre Ljubljana (UMCL) and international symposium on biomedical imaging (ISBI) 2015 datasets as benchmarks. It reaches 98.56%, 93.15%, and 98.44% accuracy for FLAIR, T1W, and T2W, respectively. Our HD-CNN improves MS classification over other state-of-the-art techniques, compared with accuracy, F-score, Recall, Precision, Dice, and Jaccard indexes values.