DEEP MACHINE LEARNING FOR BRAIN TUMOR DIAGNOSIS THROUGH IMAGE ANALYSIS

Abstract

– The research addresses deep machine learning, also known as "deep learning", an area of ​​Artificial Intelligence that uses artificial neural networks to identify brain tumors from image exams. The study focuses on the application of these networks to recognize images in which the presence of brain tumors has been detected. A computational application was developed using AI techniques and algorithms, specifically the VGG16 architecture, one of the most popular Convolutional Neural Networks (CNNs) in computer vision. Several computational tools were used in the development of the project. The designed model achieved a 70% accuracy rate in images with and without brain tumors, with expectations of continuous improvement.