Diagnosis of COVID-19 Disease Using Lung CT-scan Image Processing Techniques
Introduction: Today, several methods are used for detecting COVID-19 such as disease-related clinical symptoms, and more accurate diagnostic methods like lung CT-scan imaging. This study aimed to achieve an accurate diagnostic method for intelligent and automatic diagnosis of COVID-19 using lung CT-...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Kerman University of Medical Sciences
2021-06-01
|
| Series: | مجله انفورماتیک سلامت و زیست پزشکی |
| Subjects: | |
| Online Access: | http://jhbmi.ir/article-1-529-en.html |
| Summary: | Introduction: Today, several methods are used for detecting COVID-19 such as disease-related clinical symptoms, and more accurate diagnostic methods like lung CT-scan imaging. This study aimed to achieve an accurate diagnostic method for intelligent and automatic diagnosis of COVID-19 using lung CT-scan image processing techniques and utilize the results of this method as an accurate diagnostic tool complementing the CT-scan devices.
Method: Based on digital image processing algorithms such as segmentation and feature extraction and using various methods of statistical analysis on the features extracted from images, CT-scan images of 79 male and female patients in different ages were analyzed and the effects of this disease on the infected lungs of patients were evaluated. This research was conducted in the spring of 2020 in the Faculty of Medical Sciences and Technologies, Science and Research Branch in Tehran.
Results: This intelligent method based on feature extraction from lung CT-scan images can diagnose COVID-19 with high accuracy on different categories (gender, type of injury caused by the disease). The analysis of lung tissue involvement in patients with COVID-19 revealed that most patients had tissue damage in the lower parts of both lungs to a greater extent than the middle and upper lung lobes.
Conclusion: The algorithm presented in this study can accurately detect and differentiate the data of images taken from the lungs of healthy people and patients with coronavirus disease. |
|---|---|
| ISSN: | 2423-3870 2423-3498 |