Related Experiment Video
Updated: Nov 2, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.4K
COVID-19 pneumonia on chest X-rays: Performance of a deep learning-based computer-aided detection system
Eui Jin Hwang1,2, Ki Beom Kim3, Jin Young Kim4
1Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
Plos One
|June 7, 2021
Summary
A computer-aided detection (CAD) system shows radiologist-level performance in identifying COVID-19 pneumonia on chest X-rays (CXRs). This CAD tool significantly improves non-radiologist physicians' diagnostic accuracy, aiding triage in resource-limited settings.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Infectious Disease Diagnostics
Background:
- Chest X-rays (CXRs) are crucial for triaging Coronavirus disease (COVID-19) patients, especially in resource-constrained areas.
- Computer-aided detection (CAD) systems can assist in identifying pneumonia on CXRs where radiologists are scarce.
- Limited research exists on the performance of CAD for COVID-19 and associated pneumonia detection using CXRs.
Purpose of the Study:
- To evaluate the performance of a commercialized, regulatory-approved CAD system in identifying COVID-19 and pneumonia on CXRs.
- To compare the CAD system's performance against expert radiologists and non-radiologist physicians.
- To assess the impact of CAD assistance on the diagnostic performance and inter-reader agreement of physicians.
Main Methods:
- Retrospective collection of CXRs from patients with and without COVID-19 confirmed by RT-PCR.
- Analysis of CXRs using a commercial CAD system and interpretation by 5 thoracic radiologists and 5 non-radiologist physicians.
- Performance evaluation using area under the receiver operating characteristic curves (AUCs) with RT-PCR and chest CT as references.
Main Results:
- The CAD system achieved radiologist-level performance (AUCs of 0.714 vs. RT-PCR, 0.790 vs. CT), outperforming non-radiologist physicians (AUCs of 0.584-0.650).
- Non-radiologist physicians demonstrated significantly improved diagnostic performance when assisted by the CAD (AUCs improved to 0.664-0.738).
- CAD assistance also enhanced inter-reader agreement among physicians (Fleiss' kappa coefficient increased from 0.209 to 0.322).
Conclusions:
- The CAD system demonstrates radiologist-level accuracy in detecting COVID-19 and associated pneumonia on CXRs.
- CAD assistance significantly boosts the diagnostic capabilities of non-radiologist physicians.
- This CAD technology offers a valuable tool for supporting physicians and enabling image-based triage of COVID-19 patients in underserved regions.
More Related Videos
Related Concept Videos
01:30Pneumonia III: Complications and Assessment
548
Pneumonia poses the potential for numerous complications that warrant consideration. These complications include the following:
548
01:20Imaging Studies for Cardiovascular System III: X-Ray
333
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
333
01:30Radiological Investigation I: X-ray and CT
616
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
616