Magnetic Resonance Imaging (MRI) is a well-established technique for delivering anatomical data, with ongoing research aimed at enhancing its capacity to convey biological function information. Brain abnormalities, including neurodegenerative diseases, psychiatric disorders, and ageing, frequently correlate with structural alterations in the brain. Brain tumours are the most common type of abnormality, and finding them with an MRI is very important in medical image processing. CT, MRI, and PET are some of the imaging techniques that are used. MRI is the best because it gives the most detailed information about the brain. Nonetheless, identifying tumours via MRIs is difficult because the brain's shape and structure are different in each person. This study seeks to create an effective segmentation and classification system through the application of innovative image processing methods, including Distribution-based Adaptive Median Filtering (DMAF), Skull Removal, Neighbourhood Differential Edge Detection (NDED), Intensity Variation Pattern Analysis (IVPA), and Weighted Machine Learning (WML), to enhance disease diagnosis and categorisation.
Keywords: Brain Tumor, Stroke, MRI, Machine Learning, Deep Learning, Image Segmentation, Feature Extraction.
How to cite this article: Satyajeet, Ram OP, Upadhyay P, Raj N, Kumar H, Shukla KK, Study and Analysis of Brain Tumor and Stroke Detection using MRI Images and Artificial Intelligence. Int J Drug Deliv Technol. 2026;16(2s): 366-375; DOI: 10.25258/ijddt.16.366-375