This project integrates Convolutional Neural Networks (CNN) for tumor classification and a hybrid Particle Swarm Optimization-Whale Optimization Algorithm (PSO-WOA) for precise image segmentation. The CNN model, trained on grayscale MRI scans, categorizes tumors into Glioma, Meningioma, Pituitary, or No Tumor using k-fold cross-validation and data augmentation. For tumor identification, PSO ensures a global search while WOA refines segmentation for accurate boundary detection. This approach enhances automated tumor analysis, aiding radiologists in improved clinical decision-making.
Dataset : https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset/data
CNN Tumor Classification : braintumor_classification CNN.ipynb
Image Segementation using PSO & WOA : imagesegementation using PSO & WOA.ipynb
Result Image
More Details Report.pdf