IKONOS: An intelligent tool to support diagnosis of Covid-19 by texture analysis of x-ray images
Authors:
- Juliana Carneiro GomesJGJuliana Carneiro Gomes
- Valter Augusto de Freitas BarbosaVBValter Augusto de Freitas Barbosa
- Maira A. SantanaMSMaira A. Santana
- Mêuser Jorge Silva ValençaMVMêuser Jorge Silva Valença
- Aras Masood IsmaelAIAras Masood Ismael
- Wellington Pinheiro dos SantosWellington Pinheiro dos Santos
Preprint
Abstract
In late 2019, the SARS-Cov-2 spread worldwide. The virus has high rates of proliferation and causes severe respiratory symptoms, such as pneumonia. There is still no specific treatment and diagnosis for the disease. 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. 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. Support vector machines stood out, reaching an average accuracy of 89.78%, average recall and sensitivity of 0.8979, and average precision and specificity of 0.8985 and 0.9963 respectively. The system is able to differentiate Covid-19 from viral and bacterial pneumonia, with low computational cost.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Covid-19: testing timesBMJ, 2020
- Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networksPhysical and Engineering Sciences in Medicine, 2020
- Breast cancer diagnosis based on mammary thermography and extreme learning machinesResearch on Biomedical Engineering, 2018
- A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic imagesExpert Systems with Applications, 2016
- Detection and classification of masses in mammographic images in a multi-kernel approachComputer Methods and Programs in Biomedicine, 2016
- Morphological extreme learning machines applied to detect and classify masses in mammograms2015
- A methodology for classification of lesions in mammographies using Zernike Moments, ELM and SVM Neural Networks in a multi-kernel approach2014
- Summary for Policymakers2014
- Support-vector networksMachine Learning, 1995
- A training algorithm for optimal margin classifiers1992