Automated Multiple Sclerosis Detection Using Hybrid CNN-Attention Model

Multiple Sclerosis is a neurodegenerative disease which has no definitive diagnostic test or cure. This makes early detection crucial for effective treatment. The widely used method of detection is manual analysis of MRI scans for lesions in the brain or the spinal cord. This can be time-consuming, labor-intensive, and susceptible to human error. An alternative to manual diagnosis is automated detection using deep learning models. However, existing approaches often lack the precision and robustness needed for clinical application. This paper proposes a novel deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction and Multi Head Attention Mechanisms to capture global dependencies. The proposed framework outperforms conventional CNN-based models by achieving high lesion detection accuracy. The experimental results demonstrate the efficacy of the hybrid model in improving diagnostic precision, thus paving the way for clinical deployment. The findings support the development of more accurate and efficient computer-aided diagnosis tools for clinical use.