Enhancing Neurological Care: Multi-Label Classification Framework for Brain Disease Detection Using MRI

Brain diseases, including traumas, tumors, haemorrhages, and other neurological abnormalities, present significant risks to human health and may result in life-threatening effects. Traditional healthcare often encounters challenges in the concurrent identification of various disorders, hence limiting the therapeutic efficacy of identifying brain diseases using MRI analysis. This paper presents a multiple-label classification model tailored for brain disease diagnosis using a large-scale MRI dataset. Our approach employs multi-label classification, a methodology previously unexplored in this context, to uniquely address the challenge of identifying multiple diseases from a single MRI scan. Comprehensive experiments rigorously evaluated the proposed model, achieving state-of-the-art performance with an overall accuracy of 98.43%, surpassing existing models in terms of both diagnostic precision and computational efficiency. The results demonstrate the potential for more accurate, rapid, and efficient brain disease diagnosis, ultimately improving patient management. In addition to advancing the field of medical image analysis, our work paves the way for future research that aims to further enhance automated systems in healthcare diagnostics.