Reflective CNN Implementation for Brain Tumor Segmentation

This repository provides the implementation of a simplified encoder–decoder CNN applied to brain tumor MRI segmentation. It accompanies our paper submitted for presentation at the 22nd International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE 2025), Mexico City. The code includes dataset preprocessing, CNN training, Bayesian hyperparameter tuning, and evaluation metrics. T. Berghout, "A Reflective Study on Deep Learning in Brain Tumor Segmentation," 2025 22nd International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), Mexico City, Mexico, 2025, pp. 1-5, doi: 10.1109/CCE67728.2025.11271939.