Abstract

Tumors of the brain are malignant growths that can arise within the brain itself or in the surrounding tissues. Individuals affected by brain tumors often face significant challenges in terms of their overall health and quality of life. The prompt identification and precise diagnosis of brain tumors are crucial for formulating an effective treatment plan. Over the years, convolutional neural networks (CNNs) have emerged as a promising approach in the field of medical imaging and artificial intelligence (AI). These advancements have led to the development of automated techniques for diagnosing brain tumors. In this study, we propose a CNN-based method for identifying brain cancers using MRI images. The proposed CNN architecture consists of multiple layers of convolutional processing, followed by maximum pooling, batch normalization, and dropout processing. To ensure the accuracy of the model, it is trained using a large dataset that includes various types of brain MRI scans, including both normal and tumor images. Our team conducted an investigation of this proposed procedure using a dataset comprising brain MRI pictures obtained from different locations.