MRI Brain Cancer Image Detection: Application of an Integrated U-Net and ResNet50 Architecture

Brain cancer results in the deaths of many people each year. Magnetic Resonance Imaging (MRI) is used to segment different regions of brain tumors, such as edema and tumor cores, which is challenging due to differences in location, size, shape, and intensity. In this study, we apply an integrated CNN model that combines aspects of both ResNet50 and U-Net, leveraging the strengths of each. Specifically, we replaced the last 5 layers of ResNet50 with 10 additional layers, thereby serving as the encoder in the U-Net architecture. Our results with ResNet50 offer precision and IoU scores of 0.98 and 0.97, respectively. Our approach appears to show great promise in terms of how well the model detects and pinpoints brain cancer.