2026-06-092026-06-092026-01-28COSTA, Edriane dos Socorro Silva. Análise comparativa de arquiteturas de aprendizado profundo na classificação de tumores cerebrais. Orientador: José Jailton Henrique Ferreira Junior. 2026. 19 f. Trabalho de Curso (Bacharelado em Engenharia de Computação) – Faculdade de Engenharia da Computação, Campus Universitário de Castanhal, Universidade Federal do Pará, Castanhal, 2026. Disponível em: https://bdm.ufpa.br/handle/prefix/9590. Acesso em:.https://bdm.ufpa.br/handle/prefix/9590This work presents a comparative analysis of CNN architectures ap plied to the classification of brain tumors in magnetic resonance images. A generic model and transfer learning–based models were evaluated, using the VGG16 and ResNet101 architectures. The dataset underwent preprocessing and data augmentation steps, and the models were evaluated using metrics such as accuracy, precision, recall, and F1-score. The results demonstrated high per formance of the proposed approaches, with emphasis on the ResNet101 archi tecture. The findings highlight the potential of deep learning as a support tool for computer-aided diagnosis.Acesso AbertoAnálise comparativaCâncerDiagnóstico assistido por computadorCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOTrabalho de Curso - Graduação - Artigo