Image Segmentation and Classification Using CNN Model to Detect Brain Tumors

Abstract

Brain tumors are classified using a biopsy in brain surgery, the Enhancement technique and machine learning may assist tumor diagnosis without invasive procedures. where is a convolutional neural network CNN is a popular method in deep learning that has produced considerable success in image segmentation and classification (CNN). this paper presents a brain tumor segmentation and classification architecture with three tumor modalities. The neural network has been created and its much simple than what actually the current pre trained networks and also has been tested using contrast-enhanced magnetic resonance images MRI from T1. The capacity of the network to generalize has been evaluated using one of the 10 times, subject-specific cross-validation techniques and tested by an enlarged images in dataset. The best result was achieved for the 10-fold cross-validation technique for the record-oriented cross-validation of the increased data set, and the accuracy in this instance was 96.56 percent. The newly designed CNN architecture may be utilized as an effective decision support tool for radiologists in medical diagnosis with high generalization capacity and fast performance speed.