The human brain stands as the master controller of the intricate humanoid system. Anomalous cell proliferation within this vital organ can give rise to brain tumors, eventually progressing to the dire state of brain cancer. Within the domain of human health, the integration of Computer Vision emerges as a formidable ally, mitigating human error and furnishing precise diagnostic outcomes. Among the array of imaging modalities, including CT scans, X-rays, and MRI scans, magnetic resonance imaging (MRI) reigns supreme for its reliability and safety. In order to increase patient survival rates, brain tumors—one of the most serious neurological conditions—need to be diagnosed as soon as possible. Conventional diagnostic techniques mostly depend on radiologists' manual interpretation of Magnetic Resonance Imaging (MRI) data, which can be laborious and prone to human error. Automated medical image analysis has greatly improved with recent deep learning advances. In order to accurately detect brain tumours from MRI scans, this research suggests a deep learning method utilising convolutional neural networks (CNN). The suggested model automatically separates pertinent MRI scan information and divides the images into tumour and non-tumor groups. A publicly accessible brain MRI dataset is used to train and assess the system. When compared to conventional machine learning methods, experimental results show that the CNN model delivers great accuracy and dependability in tumour identification. Medical practitioners can use the suggested framework to help with clinical decision-making and early diagnosis.

: Brain tumor, Magnetic resonance imaging, Adaptive Bilateral Filter, Convolution Neural Network