A Novel Approach for Brain Tumor Classification Using an Ensemble of Deep and Hand-Crafted Features

Abstract

One of the most severe types of cancer caused by the uncontrollable proliferation of brain cells inside the skull is brain tumors. Hence, a fast and accurate tumor detection method is critical for the patient’s health. Many automated artificial intelligence (AI) methods have recently been developed to diagnose tumors. These approaches, however, result in poor performance; hence, there is a need for an efficient technique to perform precise diagnoses. This paper suggests a novel approach for brain tumor detection via an ensemble of deep and hand-crafted feature vectors (FV). The novel FV is an ensemble of hand-crafted features based on the GLCM (gray level co-occurrence matrix) and in-depth features based on VGG16. The novel FV contains robust features compared to independent vectors, which improve the suggested method’s discriminating capabilities. The proposed FV is then classified using SVM or support vector machines and the k-nearest neighbor classifier (KNN). The framework achieved the highest accuracy of 99% on the ensemble FV. The results indicate the reliability and efficacy of the proposed methodology; hence, radiologists can use it to detect brain tumors through MRI (magnetic resonance imaging). The results show the robustness of the proposed method and can be deployed in the real environment to detect brain tumors from MRI images accurately. In addition, the performance of our model was validated via cross-tabulated data.

A Novel Technique for Brain Tumor Detection and Classification using T1-Weighted MR Image

“…Parameters have been set based on the results of multiple iterations of the genetic algorithm. In this analysis, we employ a fitness-proportionate selection approach, and our selection probability, f, is calculated using equation (2).…”

“…Magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) scans were used to obtain these images. MRI scans are preferred by radiologists and medical professionals to detect brain tumors because they produce high-quality images of soft tissues [2]. When manually diagnosing tumors through ocular inspection, the surrounding healthy tissues often result in blurred tumor edges.…”

Global Self-Attention Module Based Convolutional Neural Network for Brain Tumor Classification

“…In this technique, a discrete probability density function is utilized to construct a normalized histogram which is presented in Eq. (2).…”

“…The various types of brain tumors are, gliomas obtained from the glial cells, meningiomas arising from the meninges, and metastatic tumor, which are spread from the body to the brain [1]. Brain tumor symptoms are detected through image processing and the incorporation of Machine Learning (ML) in medical images [2]. Early diagnosis by identifying the abnormal patterns involves precise segmentation and classification, which aids in identifying the neurological disorders [3].…”

Optimizing Brain Tumor Classification: A Comparative Analysis of Nature Inspired Algorithms with GLCM Features

“…Hareem Kibriya et al [7] addressed the critical requirement for accurate brain tumor detection by introducing an innovative approach that combines deep features from the VGG16 model with hand-crafted features based on the gray level co-occurrence matrix (GLCM). These feature vectors (FV) were subsequently classified using support vector machines (SVM) and the knearest neighbor classifier (KNN), resulting in an exceptional accuracy rate of 93%.…”