Enhancing Brain Tumor Diagnosis: A Cutting-Edge Ensemble Deep Learning Approach

Brain cancer is a severe and intricate neurological condition that is expected to impact 13.2 million individuals worldwide by 2030. Brain tumors pose a significant challenge among the different types of cancer, primarily because of their complex characteristics and profound effects on health. Existing detection techniques, such as Magnetic Resonance Imaging (MRI), are efficient but primarily depend on human experience, resulting in a time-consuming and subjective procedure. This study utilizes advanced deep learning techniques, notably convolutional neural networks (CNNs), to improve the diagnostic process for brain tumors and overcome the difficulties associated with it. The proposed ensemble model combines a VGG Residual Learning Network with CBAM attention and an Inception convolutional filters block. The purpose model aims to enhance the efficacy of feature extraction and classification by leveraging the capabilities of both components. The model is trained and validated using the brain tumor dataset consisting of 2,513 images of tumor and 2,087 healthy images, obtained from Kaggle. The results indicate that the ensemble model attains improved performance measured in accuracy of 98.04%, recall of 96.81%, precision of 97.43%, F1-score of 97.11%, and AUC of 100.00%. These metrics clearly demonstrate its superiority over traditional models such as InceptionV3, ResNet50, and VGG16. Grad-CAM visuals validate the model's attention towards pertinent brain regions, hence improving the comprehensibility. The proposed ensemble model provides a strong, effective, and understandable strategy for identifying brain tumors, greatly improving the capacities of existing diagnostic techniques.