Abstract
Brain tumors are life-threatening neurological disorders that require timely and accurate diagnosis for effective treatment planning. Traditional MRI-based diagnosis depends heavily on expert radiologists, making the process time-consuming and susceptible to human error. Although deep learning models have shown high accuracy in brain tumor classification, most remain confined to research settings without real-time clinical integration. This paper reviews existing literature on AI-driven brain tumor detection and highlights the limitations of current systems, including lack of interpretability, limited deployment, and absence of automated reporting mechanisms. BrainAI is proposed as an intelligent diagnostic support system that leverages Convolutional Neural Networks and transfer learning models to classify MRI scans into multiple tumor categories while generating confidence scores and structured reports, thereby enhancing clinical efficiency and supporting informed medical decision-making processes.
Open public full textRights: UNKNOWN · cc-by-nc · Source: journal-auto-sync:external:CROSSREF_ISSN