A Noninvasive System for the Automatic Detection of Gliomas Based on Hybrid Features and PSO-KSVM

Abstract

Due to their location, malignant brain tumors are one of humanity's greatest killers, among these tumors, gliomas are the most common. The early detection of gliomas can contribute to the design of proper treatment schemes and, thus, improve the survival rate of patients. However, it is a challenging task to detect the gliomas within the complex structure of the brain. The conventional artificial diagnosis is timeconsuming and relies on the clinical experience of radiologists. To detect gliomas more efficiently, this paper proposes a noninvasive automatic diagnosis system for gliomas based on the machine learning methods. First, image standardization, including size normalization and background removal, is applied to produce standard images; then, the modified dynamic histogram equalization is implemented to enhance the low-contrast standard brain images, and skull removal based on outlier detection is presented. Furthermore, hybrid features, including gray-level co-occurrence matrix, pyramid histogram of the oriented gradient, modified completed local binary pattern, and intensity-based features are extracted together from the enhanced images, and their dimensions are reduced by principal component analysis. Kernel support vector machine (KSVM) combined with the particle swarm optimization is eventually adopted to train classifiers; in this paper, brain magnetic resonance imaging images are labeled with normal, glioma, and other. The experimental results show that the accuracy, sensitivity, and specificity of the proposed method can reach 98.36%, 99.17%, and 97.83%, respectively, which indicates that the proposed method performs better than many current systems. INDEX TERMS Modified CLBP, PSO-KSVM, Glioma detection, hybrid features, skull removal. FIGURE 3. The process of background removal based on an adaptive threshold.

A Survey on Recent Advancements for AI Enabled Radiomics in Neuro-Oncology

“…LBP feature extractor is known for its efficiency in utilizing the computation power, but its effectiveness reduces with an increase in noise in the image [43]. Another commonly used method to extract radiomics features is Histogram of Oriented Gradient (HOG) [50] [57] where the number of oriented gradient occurrences in certain image regions are counted to create a histogram. Depending on the application, different regions can be used to capture local shape and edge information from the images, which is further converted into a feature vector using the HOG descriptor.…”

An Automatic Diagnosis Scheme for Gliomas Using Gray Level Co- occurrence Matrix, Histogram of Oriented Gradient,Discrete Wavelet Transformation, Intensity-based Features andHierarchical PSO-SVM

“…In general, filters are usually adopted for the image recognition tasks, as noises can be amplified by the contrast enhancement algorithms. 13 However, 14 indicates that the introduction of filters can damage the classifier performance, for which the reason is that the magnetic resonance images have high quality in nature and the application of filters can damage the detail information. As a result, no filters are applied before the process of contrast enhancement.…”

“…In this system, two typical contrast enhancement methods, including contrast stretching and histogram equalization (HE) are implemented. Contrast stretching (CS) is one of the simplest contrast enhancement methods, and the mathematical definition of CS is described in equation 1, 14 where f stands for the input brain image while g represents the output brain image, m and n denote adjustable parameters. This algorithm can map the pixels with the intensity lower than m in input images to the pixels with low intensity in the narrow range in output images, while it maps the pixels with intensity larger than m in input images to the pixels with high intensity in the narrow range in output images.…”

“…3 (f), the image is further enhanced. The main procedures of histogram equalization can be described as the following: 14,17 Step 1: Acquire the graylevels hi of the input images, where i=0,1...M-1, and M stands for thetotal number of gray levels.…”

Value of Virtual Reality Technology in Image Inspection and 3D Geometric Modeling

“…Then they used a probabilistic neural network to detect the image. Song et al [19] changed the classifier, used kernel support vector machine, and used particle swarm optimization algorithm to train KSVM. This document compares the proposed PSO-KSVM with the optimized classification method, and the classification performance of the improved classifier is obviously improved.…”