Manav Mohini, Goyal Monika, Kumar Anuj
Department of Physics, GLA University, Mathura, Uttar Pradesh, India.
Department of Radiotherapy, S N Medical College, Agra, Uttar Pradesh, India.
J Med Phys. 2023 Apr-Jun;48(2):195-203. doi: 10.4103/jmp.jmp_104_22. Epub 2023 Jun 29.
The objective of the present study is to classify chest X-ray (CXR) images into COVID-positive and normal categories with the optimal number of features extracted from the images. The successful optimal feature selection algorithm that can represent images and the classification algorithm with good classification ability has been determined as the result of experiments.
This study presented a framework for the automatic detection of COVID-19 from the CXR images. To enhance small details, textures, and contrast of the images, contrast limited adaptive histogram equalization was used. Features were extracted from the first-order statistics, Gray-Level Co-occurrence Matrix, Gray-Level Run Length Matrix, local binary pattern, Law's Texture Energy Measures, Discrete Wavelet Transform, and Zernikes' Moments using an image feature extraction tool "pyFeats. For the feature selection, three nature-inspired optimization algorithms, Grey Wolf Optimization, Particle Swarm Optimization (PSO), and Genetic Algorithm, were used. For classification, Random Forest classifier, K-Nearest Neighbour classifier, support vector machine (SVM) classifier, and light gradient boosting model classifier were used.
For all the feature selection methods, the SVM classifier gives the most accurate and precise result compared to other classification models. Furthermore, in feature selection methods, PSO gives the best result as compared to other methods for feature selection. Using the combination of the SVM classifier with the PSO method, it was observed that the accuracy, precision, recall, and F1-score were 100%.
The result of the study indicates that with optimal features with the best choice of the classifier algorithm, the most accurate computer-aided diagnosis of CXR can be achieved. The approach presented in this study with optimal features may be utilized as a complementary tool to assist the radiologist in the early diagnosis of disease and making a more accurate decision.
本研究的目的是从胸部X光（CXR）图像中提取最佳数量的特征，将其分为新冠阳性和正常两类。实验结果确定了能够表示图像的成功的最佳特征选择算法以及具有良好分类能力的分类算法。
本研究提出了一个从CXR图像中自动检测新冠病毒的框架。为增强图像的小细节、纹理和对比度，使用了对比度受限自适应直方图均衡化。使用图像特征提取工具“pyFeats”从一阶统计量、灰度共生矩阵、灰度行程长度矩阵、局部二值模式、劳氏纹理能量测度、离散小波变换和泽尼克矩中提取特征。对于特征选择，使用了三种自然启发式优化算法，即灰狼优化算法、粒子群优化算法（PSO）和遗传算法。对于分类，使用了随机森林分类器、K近邻分类器、支持向量机（SVM）分类器和轻梯度提升模型分类器。
对于所有特征选择方法，与其他分类模型相比，SVM分类器给出的结果最准确、精确。此外，在特征选择方法中，与其他特征选择方法相比，PSO给出的结果最佳。使用SVM分类器与PSO方法的组合，观察到准确率、精确率、召回率和F1分数均为100%。
研究结果表明，通过选择最佳分类算法的最佳特征，可以实现最准确的CXR计算机辅助诊断。本研究中提出的具有最佳特征的方法可作为一种辅助工具，帮助放射科医生进行疾病的早期诊断并做出更准确的决策。
