AI Hits 99% Accuracy in Brain Tumor Diagnosis

A new study shows combining neuroimaging with artificial intelligence can significantly enhance brain tumor diagnosis, achieving near-perfect accuracy.

Brain tumors are among the most complex neurological conditions to diagnose. Researchers developed a fusion approach integrating MRI data with three machine learning models: convolutional neural networks (CNN), random forest (RF), and support vector machines (SVM).

The study analyzed 7,023 MRI images spanning four categories: glioma, meningioma, pituitary tumor, and no tumor. The CNN model achieved the highest accuracy at 99.29%, followed by RF at 99.06% and SVM at 98.36%.

Accurate classification is critical as treatment strategies vary significantly between tumor types. AI-driven tools could support radiologists in making faster, more reliable decisions.

Despite promising results, the model was trained on a single dataset with no external validation, raising questions about generalisability. Researchers suggest future work should focus on multi-centre datasets and real-world clinical integration.