BIR-CAT Optimization Technique for Automatic Segmentation and Classification of Brain Tumours on Pre- and Post-Operative MRI

Abstract

The main goal of this research is to find brain tumours by use MRI scan. After that, to find all the abnormalities in the brain and put them into groups. It is a challenging task to detect and segment the tumour tissues and other tissues from the brain. The MRI is initially fed into the preprocessing system and is then segmented using the Region Growing segmentation algorithm. This will produce the segmented area and is then forwarded for classification. In the classification step, the Bir-Cat optimization algorithm is used. This is a deep learning idea that trains the neural network using a Deep Belief Network. The Bird-Swarm algorithm and the Cat-Swarm algorithm are both parts of the Bir-Cat algorithm. This will give the classified tumour tissues and also classify the different types of tissues or abnormalities in a brain tumour. The extended idea is the segmentation and classification of a brain tumour after surgery. This includes all of the image processing steps that were done for the MRI before surgery. Finally, the segmented results of the pre-operative MRI and the post-operative MRI were compared to see if any pixels had changed. These both identify the post-surgery new tumour that has developed and demonstrates how well the procedure was performed.