Brain tumor detection and segmentation
Topic: Brain tumor detection and segmentation
Abstract: “Brain Tumor Detection and Segmentation from MRI Images using CNN and U-Net Models” The CNN model is used to detect whether a tumor is present or not. After 15 epochs of training, the accuracy calculated was 99.6%. The U-Net model is used to segment tumors in MRI images of the brain. After 10 epochs of training, the accuracy calculated was 98%. These deep neural networks are implemented using the Keras functional API. The trained models can be used to detect and segment tumors on brain MRI images, resulting in a satisfactory outcome.
You can download the U-net trained model from: Unet and CNN trained model from: CNN
Please feel free to contact me if you need help making it work.
For access to the code, please refer to my GitHub repository.
