el 23(1): e2

Research Article

Covid-19 Diagnosis by Gray-level Cooccurrence Matrix and Genetic Algorithm

Download314 downloads
  • @ARTICLE{10.4108/eetel.v8i1.2344,
        author={Xiaoyan Jiang and Mackenzie Brown and Zuojin Hu and Hei-Ran Cheong},
        title={Covid-19 Diagnosis by Gray-level Cooccurrence Matrix and Genetic Algorithm},
        journal={EAI Endorsed Transactions on e-Learning},
        volume={8},
        number={1},
        publisher={EAI},
        journal_a={EL},
        year={2022},
        month={8},
        keywords={Gray-level Cooccurrence Matrix, Genetic Algorithm, optimization, Feedforward Neural Network, K-fold cross-validation, COVID-19, Diagnosis},
        doi={10.4108/eetel.v8i1.2344}
    }
    
  • Xiaoyan Jiang
    Mackenzie Brown
    Zuojin Hu
    Hei-Ran Cheong
    Year: 2022
    Covid-19 Diagnosis by Gray-level Cooccurrence Matrix and Genetic Algorithm
    EL
    EAI
    DOI: 10.4108/eetel.v8i1.2344
Xiaoyan Jiang1,*, Mackenzie Brown2, Zuojin Hu1, Hei-Ran Cheong3
  • 1: Nanjing Normal University of Special Education
  • 2: Edith Cowan University
  • 3: University of Ulsan
*Contact email: j_njty@163.com

Abstract

Currently, improving the identification of COVID-19 with the help of computer vision and artificial intelligence has received great attention from researchers. This paper proposes a novel method for automatic detection of COVID-19 based on chest CT to help radiologists improve the speed and reliability of tests for diagnosing COVID-19. Our algorithm is a hybrid approach based on the Gray-level Cooccurrence Matrix and Genetic Algorithm. The Gray-level Cooccurrence Matrix (GLCM) was used to extract CT scan image features, GA algorithm was used as an optimizer, and a feedforward neural network was used as a classifier. Finally, we use 296 chest CT scan images to evaluate the detection performance of our proposed method. To more accurately evaluate the accuracy of the algorithm, 10-run 10-fold cross-validation was introduced. Experimental results show that our proposed method outperforms state-of-the-art methods in terms of Sensitivity, Accuracy, F1, MCC, and FMI.