A Novel MRI Brain Tumor Detection Method Incorporated Residual Dendritic Learning

In this study, we present a novel method for brain tumor detection that emphasizes dendritic learning for feature mapping. We use the RegNet module to extract high-quality features from brain MRI images, capturing complex features and structures effectively. These features are then classified using a custom-designed dendritic neuron model, which leverages the principles of dendritic learning to achieve high accuracy. To evaluate the performance of the proposed method, we conduct extensive experiments on a benchmark brain tumor dataset. The results demonstrate that our method significantly enhances classification accuracy. Our findings suggest that integrating advanced feature extraction modules like RegNet with dendritic learning-based classification neurons can greatly improve the performance of brain tumor detection systems. This study opens new avenues for further research in developing efficient and accurate neural network architectures for various medical image processing tasks.