Electrotechnical and Computer Engineering
Vol. 40 No. 03 (2025): Proceedings of the Faculty of Technical Sciences
DETERMINING THE TYPE OF BRAIN TUMOR BASED ON MRI IMAGES OF THE ENDOCRANIUM USING ARTIFICIAL INTELLIGENCE METHODS
Abstract
The goal of the work is a faster and more reliable classification of the type of tumor using artificial intelligence methods. Solving the problem of classifying MRI images into tumor types. The solution was implemented by fine-tuning parameters on three pre-trained models, Resnet50, DenseNet121, and EfficientNet-B3. The best result was obtained by fine-tuning the parameters on the pre-trained EfficientNet-B3 model, with an accuracy of 98%.
References
[1] https://www.abta.org/about-brain-tumors/brain-tumor-education/ (pristupljeno u avgustu 2024.)
[2] D. N. Louis et al., "The 2016 World Health Organization classification of tumors of the central nervous system: a summary," Acta Neuropathologica, 2016.
[3] Q. T. Ostrom et al., "CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2012–2016," Neuro-oncology, 2019.
[4] J. Hardy and J. Rees, "Pituitary tumours: diagnosis and management," Postgraduate Medical Journal, 2008.
[5] World Health Organization, "Global health workforce statistics," 2022.
[6] J. Smith and A. Lee, Advances in brain tumor classification and detection, Springer, 2023.
[7] https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri?resource=download (pristupljeno u avgustu 2024.)