Optimized Brain Tumour Segmentation and Classification Using VGG UNET and VGG-19 with ABC-WOA Algorithm

Accurate brain tumour classification is essential for treatment planning and patient care in medical image analysis. In this study, we used sophisticated deep learning algorithms to improve brain tumour categorization. We used VGG-UNET for segmentation to precisely delineate tumour locations in MRI scans and VGG-19 for classification, a popular convolutional neural network architecture for image classification. We used a hybrid ABC-WOA hyperparameter tweaking technique to increase the accuracy and resilience of our VGG-19 model. We compared our model against ResNet- 50 and AlexNet, two popular convolutional neural network designs, on accuracy, precision, recall, and F1-scores. Hyperparameter-tuned VGG-19 model had excellent discrimination, with accuracy metrics topping 99.1% and a remarkable AUC value of 0.99. ResNet-50 and AlexNet performed well, however they were not as accurate and precise as VGG-19. These data show that our technique could revolutionize brain tumour classification, providing doctors with a trustworthy tool for precise diagnosis and treatment planning. Future study might examine the scalability and generalizability of our findings in larger datasets and clinical contexts, improving patient outcomes and neuro-oncology research. VGG-UNET segmentation, VGG-19 classification, and a hybrid ABC-WOA hyperparameter tuning approach improve brain tumour classification accuracy. The hyperparameter-tuned VGG-19 model’s proven performance makes it a promising choice for clinical brain tumour classification tasks, providing physicians with accurate diagnosis and prognosis.