Revolutionizing Multiple Sclerosis Detection with MSNet: A Deep Learning Framework

Multiple sclerosis (MS) is a chronic, immune-mediated neurological disorder that affects the central nervous system, impacting millions globally. In the absence of a definitive cure, early detection and prompt intervention are critical for managing symptoms and potentially mitigating disease advancement. The intended research demonstrated a Convolutional Neural Network (CNN) architecture entitled MSNet for diagnosing MS at an early stage, employing a brain dataset of magnetic resonance imaging (MRI). Extensive research was conducted to select the optimal activation function, optimizer, loss function, layers, and filter configurations, leveraging insights from pre-trained networks to develop MSNet. MSNet, a minimalist CNN, attained 99% accuracy on the dataset, surpassing conventional methods and pre-trained networks while requiring fewer computational resources and less processing time.