The Added Value of Artificial Intelligence to Chest Computed Tomography in Early Diagnosis of Chronic Obstructive Airway Disease. | ||
| Suez Canal University Medical Journal | ||
| Article 4, Volume 27, Issue 2, February 2024, Pages 23-34 PDF (497.48 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/scumj.2025.217284.1444 | ||
| Authors | ||
| Maha M. Saad* 1; Ahmed A Bayoumy2; Magdy M. El-Nisr1; Noha M. Zaki3; Tarek H. Khalil1; Ahmed F. Elserafi1 | ||
| 1Department of Diagnostic Radiology, Faculty of Medicine, Suez Canal University, Ismailia, Egypt | ||
| 2Chest unit, Department of Internal Medicine, Faculty of Medicine, Suez Canal University Ismailia, Egypt. | ||
| 3Department of Diagnostic Radiology, Faculty of Medicine, Ain Shams University, Cairo, Egypt | ||
| Abstract | ||
| Background: Recent developments in Artificial Intelligence (AI) applications allow for the automatic identification and measurement of Chronic Obstructive Pulmonary Disease (COPD) on chest computed tomography (CT). The forced expiratory volume in the first second (FEV1) levels on pulmonary function test (PFT), while useful as the main technique of staging and measuring COPD severity, do not provide an accurate status on both the type of COPD and the degree of lung involvement detected on chest CT. Aim:The purpose of this study is to clarify the function of AI in estimating COPD severity. Methods: We employed an 80-case cross-sectional investigation with a non-contrast CT chest and a computer-aided detection (CAD) system (Coreline Soft's AVIEW). Expiratory Low Attenuation Area% -856 (%LAA -856 HUEXP) and Air Trapping Index (ATI) are used to diagnose small airway disease. The severity of COPD was determined using spirometry, which was computed as the ratio of forced expiratory volume in the first second (FEV1) to forced vital capacity (FVC). Results: The patients were split into four groups based on the spirometry results: mild (n=23), moderate (n=39), severe (n=17), and extremely severe (n=1). Group 3 of the Global Initiative for Obstructive Lung Disease (GOLD) staging scheme had Exp. LAA-856 (%) that was significantly higher than groups 2 and 1. Additionally, ATI in group 3 was considerably higher compared to groups 2 and 1 .Conclusions: Exp.LAA-856% and ATI were found to be significantly related to COPD severity as measured by dyspnea scale and spirometry. | ||
| Keywords | ||
| Artificial intelligence; Small airway disease; Expiratory Low Attenuation Area; Air Trapping Index | ||
|
Statistics Article View: 10 PDF Download: 2 |
||
