الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 160 |  |  |
| | | from | 160 | | |
Abstract
The coronavirus disease caused by SARS-Cov-2 is a pandemic with millions of confirmed cases around the world and a high death toll. In clinical practice, easily accessible imaging test such as chest X-ray (CXR) and computed tomography (CT) are extremely helpful and have been widely used for the detection and diagnosis of COVID-19.
Given the anticipated shortage of intensive care unit (ICU) beds and mechanical ventilators in many hospitals, CXR has the potential to play a critical role in decision-making to determine which patients to put on a mechanical ventilator, monitor disease progression and treatment effects during mechanical ventilation, and determine when it is safe to extubate.
The application of artificial intelligence in image diagnosis has been studied for many years. AI has the potential to facilitate disease diagnosis, diseases severity staging, and longitudinal monitoring of disease progression.
The aim of the present study was to evaluate diagnostic accuracy of conventional radiography (CXR) using deep learning (DL) algorithms for the detection of pneumonia in COVID-19 patients and considering CT chest findings as a reference.
This was a retrospective study, conducted at Ain Shams University Hospitals on a total of 33 patients from November 2020 to May 2021.
The main results of the study revealed that:
57.6% were males and 42.4% were females with mean age of the study group were 44.12±29.67 years ranged from 0.5 to 86 years.
Regarding AI findings, 72.7% of patients had consolidations on left lung and 81.8% on right lung. Mean score of AI was 72% ± 32% ranged from 0% to 99%.
Regarding relation between age and AI score, there was moderate positive correlation with significant p-Value as it was (<0.05).
There was significant difference between grades of x-ray and grades of CT as p-Value was (< 0.05). The most correlated grades was grade IV, 100 % of patients had grade IV by x-ray also had grade IV by CT.
There was significant direct proportional between both grades of CT and AI score as p-Value was (< 0.05).
Regarding the sensitivity and specificity of X-ray and AI consolidations on both lungs using CT consolidations as a reference, the sensitivity was more in AI, while specificity was more in than x-ray with significant difference in both x-ray and AI as{in left lung: p-Value was (<0.05). AUC for x-ray and AI was 0.858 & 0.815 respectively}&{in right lung: p-Value was (<0.05). AUC for x-ray and AI was 0.879 & 0.823 respectively.