Experiment on the use of Deep Learning to aid in Brain Tumor detection

• Natália Caroline de Oliveira Rodrigues UFOP

DOI: https://doi.org/10.5753/ercas.2024.238716

Abstract

The article proposes an educational experiment to demonstrate the potential of deep learning models in the detection and classification of brain tumors. Using neural networks such as EfficientNetB1, VGG-19, and VGG-16, the study compares their efficacy in analyzing magnetic resonance images to identify tumors. The results show that the EfficientNet-B1 model achieved better performance, highlighting the importance of deep learning in medicine. The experiment stands out for integrating practical applications in an educational setting, contributing to the advancement of knowledge and medical practice

References

Ahmad, J., Muhammad, K., Lee, M. Y., and Baik, S. W. (2017). Endoscopic image classification and retrieval using clustered convolutional features. Journal of medical systems, 41(12):1–12.

Işın, A., Direkoğlu, C., and Şah, M. (2016). Review of mri-based brain tumor image segmentation using deep learning methods. Procedia Computer Science, 102:317–324.

Koerich, A. H., de Campos Lana, G., Damin, S. D. A., and Hedel, M. A. (2024). Deep learning na segmentação de tumores cerebrais em ressonância magnética: uma revisão de literatura. Cuadernos de Educación y Desarrollo, 16(2 Edição Especial).

Sengupta, N., McNabb, C. B., Kasabov, N., and Russell, B. R. (2018). Integrating space, time, and orientation in spiking neural networks: A case study on multimodal brain data modeling. IEEE Transactions on neural Networks and Learning systems, 29(11):5249–5263.

Talebi, S., Gai, S., Sossin, A., Zhu, V., Tong, E., and Mofrad, M. R. (2024). Deep learning for perfusion cerebral blood flow (cbf) and volume (cbv) predictions and diagnostics. Annals of Biomedical Engineering, pages 1–8.

Uema, J. and Silva, L. M. A. F. d. (2022). Deep learning aplicado a neuroimaging.