A New Approach to Detect COVID-19 in X-Ray Images of Indonesians

Anggraini Dwi Sensusiati, Aji Sapta Pramulen, Dewinda Julianensi Rumala, I Ketut Eddy Purnama, Alfian Nur Rosyid, Muhammad Amin, Rofida Lathifah

Abstract

The coronavirus disease 2019 or COVID-19 is a current global pandemic. This disease has a high prevalence in Indonesia, with 307,120 positive cases and 11,253 deaths on October 6, 2020. COVID-19 can be detected in various manners, one of which is through chest X-Ray. This present research applies an approach to COVID-19 detection through X-Ray that features preprocessing, augmentation, ELU activation function application, and optimizer use. The results show that the best performance is generated by applying the ReLU activation function at epoch 76 with a testing accuracy of 96.44%, the sensitivity of 97.4%, specificity of 95.95%, and DICE of 95.77%.

 

 

Keywords: COVID-19, X-ray, augmentation.

 

 

 


Full Text:

PDF


References


BOLDOG P., TEKELI T., VIZI Z., and DÉNES. Risk Assessment of Novel Coronavirus COVID-19 Outbreaks Outside China. Journal of Clinical Medicine, 2020, 9(2): 1-12. https://doi.org/10.3390/jcm9020571

WORLDOMETER. COVID-19 Coronavirus Pandemic. Worldometer, 2021. https://www.worldometers.info/coronavirus/

WANG D., HU B., HU C., and ZHU. Clinical Characteristics of 138 Hospitalized Patients with 2019 Novel Coronavirus-Infected Pneumonia in Wuhan, China. Journal of the American Medical Association, 2020, 323(11): 1061–1069. https://doi.org/10.1001/jama.2020.1585

ABBAS A., ABDELSAMEA M. M., and GABER M. M. Classification of COVID-19 in Chest X-ray Images Using DeTraC Deep Convolutional Neural Network. Applied Intelligence, 2021, 51: 854–864. https://doi.org/10.1007/s10489-020-01829-7

KHUZANI A. Z., HEIDARI M., and SHARIATI S. A. COVID-Classifier: An Automated Machine Learning Model to Assist in Diagnosing COVID-19 Infection in Chest X-Ray Images. Scientific Reports, 2021, 11. https://doi.org/10.1038/s41598-021-88807-2

ELAZIZ M. A., HOSNY K. M. and SALAH A. New Machine Learning Method for Image-Based Diagnosis of COVID-19. Publuc Library of Science One, 2020, 15(6): 1-18. https://doi.org/10.1371/journal.pone.0235187

CHE AZEMIN M. Z., HASSAN R., MOHD TAMRIN M. I., and ALI M. M. A. COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings. International Journal of Biomedical Imaging, 2020. https://doi.org/10.1155/2020/8828855

ALLAOUZI I,. & AHMED M. B. A Novel Approach for Multi-Label Chest X-ray Classification of Common Thorax Diseases. Institute of Electrical and Electronic Engineeers Access, 2019, 7: 64279-64288. https://doi.org/10.1109/ACCESS.2019.2916849

SINGH S., & KRISHNAN S. Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks. Institute of Electrical and Electronic Engineeers/ The Computer Vision Foundation Conference on Computer Vision and Pattern Recognition, 2020: 11237-11246. https://arxiv.org/pdf/1911.09737.pdf

HOWARD A., SANDLER M., and CHU G. Searching for MobileNetV3. 2019 Institute of Electrical and Electronic Engineeers/ The Computer Vision Foundation International Conference on Computer Vision, 2019: 1314-1324. https://doi.org/10.1109/ICCV.2019.00140

YANG X., YU Y., XU J., and SHU. Clinical Course and Outcomes of Critically Ill Patients with SARS-CoV-2 Pneumonia in Wuhan, China: A Single-Centered, Retrospective, Observational Study. The Lancet Respiratory Medicine, 2020, 8(5): 475-481. https://doi.org/10.1016/s2213-2600(20)30079-5

DEWINDA J. R., EKO M. Y., and REZA F. R. Activation Functions Evaluation to Improve Performance of Convolutional Neural Network in Brain Disease Classification Based on Magnetic Resonance Images. 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia, 2020. https://doi.org/10.1109/CENIM51130.2020.9297862


Refbacks

  • There are currently no refbacks.