Hyper Parameter Tuning In Convolutional Neural Networks for Precise Tumor Image Classification

Background/Objectives: The human brain regulates physiological processes, cognitive functions, and emotional responses. Brain-related conditions, such as neurological disorders, strokes, and tumors, are complex and pose significant challenges to medical professionals. Among these, brain tumors are particularly critical due to their impact on essential functions and the difficulty in achieving accurate diagnosis and classification. This study aims to explore the application of deep learning models in brain tumor image classification, focusing on improving diagnostic accuracy through model optimization. Methods: This research conducts a comparative analysis of four deep learning architectures: CNN, VGG-19, Inception V3, and ResNet-10. Each model's performance is evaluated on validation accuracy over ten epochs, both with and without hyper parameter tuning. Key hyper parameters, such as learning rate and optimizer selection, are adjusted to enhance model performance. Results: The CNN achieved a baseline validation accuracy of 77.86%, which improved to 89.31% after hyper parameter tuning. VGG-19, with tuning, reached a validation accuracy of 70.23%. ResNet-10 performed the worst, maintaining an accuracy of 51.91%, even with tuning. Inception V3 showed moderate performance, achieving a validation accuracy of 55.73%. The results highlight the significant impact of hyper parameter optimization on model accuracy. Conclusions: Fine-tuning hyper parameters and selecting appropriate models are critical to improving the accuracy of brain tumor classification. These findings provide insights into developing practical and efficient deep learning models, paving the way for advancements in diagnostic imaging, early detection, and clinical neuroscience.