Brain tumor classification using Hybrid RF+ DenseNet121

Classifying brain tumors is the first and most crucial stage in evaluating potentially fatal abnormal tissues and developing effective treatment plans to aid patients' recoveries. Several medical imaging devices may detect brain pathologies. The lack of ionizing radiation and high image quality made possible by magnetic resonance imaging (MRI) make it a popular choice for medical imaging. Several proposals for medical image analysis approaches have used deep learning techniques to monitor and diagnose health issues from brain MRI scans. The key process is to investigate the brain tumor through the detection and classification with appropriate methods. Brain tumor can be detected using a variety of medical imaging methods like CT, MRI, PET, etc. In this research, we presented a novel method for brain tumor detection and classification using brain tumor MRI images that combines Random Forest (RF) and DenseNet121. We can see that our strategy outperforms the competition and is more accurate from the findings.