IKONOS: an intelligent tool to support diagnosis of COVID-19 by texture analysis of X-ray images

• Published in: Research on biomedical engineering Vol. 38; no. 1; pp. 15 - 28
• Main Authors: Gomes, Juliana C., Barbosa, Valter A. de F., Santana, Maíra A., Bandeira, Jonathan, Valença, Mêuser Jorge Silva, de Souza, Ricardo Emmanuel, Ismael, Aras Masood, dos Santos, Wellington P.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.03.2022
• Subjects: Biomaterials; Biomedical Engineering and Bioengineering; Biomedical Engineering/Biotechnology; Engineering; Original; Original Article; Special Issue: Emerging Technologies for Fighting COVID-19; COVID-19; SARS-Cov-2; X-ray; Artificial intelligence; Diagnosis support; Machine learning
• ISSN: 2446-4732; 2446-4740
• DOI: 10.1007/s42600-020-00091-7

Purpose In late 2019, the SARS-CoV-2 virus spread worldwide. The virus has high rates of proliferation and causes severe respiratory symptoms, such as pneumonia. The standard diagnostic method for pneumonia is chest X-ray image. There are many advantages to using COVID-19 diagnostic X-rays: low cost, fast, and widely available. Methods We propose an intelligent system to support diagnosis by X-ray images. We tested Haralick and Zernike moments for feature extraction. Experiments with classic classifiers were done. Results Support vector machines stood out, reaching an average accuracy of 89 . 78%, average sensitivity of 0 . 8979, and average precision and specificity of 0 . 8985 and 0 . 9963, respectively. Conclusion Using features based on textures and shapes combined with classical classifiers, the developed system was able to differentiate COVID-19 from viral and bacterial pneumonia with low computational cost.