• THOTA SIVA PAVANI
• KOMPELLA VENKATA RAMANA

Brain tumors are an aggressive disease, affecting thousands worldwide. In 2023, an estimated 94,390 people will receive a primary brain tumor diagnosis, and around 18,990 people are expected to die from malignant brain tumors (brain cancer). Given their severe physical, cognitive, and psychological impacts, early detection and accurate classification are critical for effective treatment and improved patient outcomes. Magnetic resonance imaging (MRI) is the most reliable technique for brain tumor detection. Leveraging advancements in Deep learning, particularly convolutional neural networks (CNN), has demonstrated high accuracy in image classification and segmentation tasks. This project explores a comparative analysis of deep learning models to detect and classify brain tumors into three categories: gliomas, meningiomas, and pituitary tumors. Using a dataset containing 3,190 T1-weighted, contrast-enhanced images, which were cleaned and augmented, the best-performing CNN model consisted of three convolutional layers and achieved an accuracy of 90%. The proposed system integrates CNN and RCNN models for precise tumor segmentation, enabling faster and more reliable diagnoses and ultimately enhancing patient life expectancy and quality of care.

brain tumor detection, classification, image processing, deep learning, CNN, RCNN, MRI scan, medical diagnostics, automated tumor prediction

"BRAIN TUMOUR DETECTION AND CLASSIFICATION USING IMAGE PROCESSING AND DEEP LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 9, page no.e459-e470, September-2024, Available :http://www.jetir.org/papers/JETIR2409457.pdf

"BRAIN TUMOUR DETECTION AND CLASSIFICATION USING IMAGE PROCESSING AND DEEP LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 9, page no. ppe459-e470, September-2024, Available at : http://www.jetir.org/papers/JETIR2409457.pdf