Brain Tumor Classification using Region-based CNN with Chicken Swarm Optimization

Abstract

Diagnosing and segmenting brain tumors manually through MRI imaging is a complex and time-consuming process. However, advancements in machine learning (ML) and deep learning (DL) technologies have enabled the automatic identification and categorization of brain tumors using computer-aided design. This study utilizes MRI data to develop a system for the automatic identification and categorization of brain tumors based on region-based convolutional neural networks (R-CNN). The proposed RCNN approach, coupled with Chicken Swarm Optimization (CSO) technique, enables the identification and classification of brain tumors into stages. This method involves processing, segmenting, extracting features, and organizing the MRI images. Image preparation includes adaptive fuzzy filtering (AFF) to eliminate noise and enhance the quality of MRI images. To detect regions of brain injury, MRI scans undergo cranial segmentation and classification (CSO) based on Tsallis entropy-based image segmentation. A Residual Network (ResNet) is employed to fuse handcrafted and deep features, generating a meaningful set of feature vectors. Extensive simulations are conducted on the BRATS 2015 dataset to evaluate the improved performance in classifying brain tumors. The RCNN-CSO method demonstrates superior performance compared to other contemporary techniques, achieving a precision of 92.35%, sensitivity of 93.52%, specificity of 94.52 % and an accuracy of 96 % . This represents a significant improvement in brain tumor classification and its outomst accuracy.