Related Experiment Video
Updated: Sep 4, 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
14.3K
Feature-level ensemble approach for COVID-19 detection using chest X-ray images
Thi Kieu Khanh Ho1, Jeonghwan Gwak1,2,3,4
1Department of Software, Korea National University of Transportation, Chungju, South Korea.
Plos One
|July 14, 2022
Summary
This study introduces an AI-driven approach for detecting COVID-19 using chest X-rays. An ensemble method combining handcrafted, radiomic, and deep features achieved superior accuracy in distinguishing COVID-19 from pneumonia and healthy controls.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computational Pathology
Background:
- Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of COVID-19, poses significant global health and economic threats.
- Chest X-ray analysis is crucial for rapid COVID-19 diagnosis, especially where laboratory testing is limited.
- Manual interpretation of chest X-rays for COVID-19 is challenging due to visual similarities with other thoracic conditions, leading to potential errors and delays.
Purpose of the Study:
- To develop an automated artificial intelligence (AI) system for accurate COVID-19 detection from chest X-ray images.
- To integrate diverse feature types—local handcrafted, radiomic, and deep learning features—for enhanced diagnostic performance.
- To classify patients with COVID-19, pneumonia, and healthy controls using conventional machine learning classifiers.
Main Methods:
- A customized dataset was created by combining images from publicly available sources.
- An ensemble approach was employed, integrating shallow handcrafted features (local descriptors), radiomic features, and deep features from pre-trained models.
- Conventional machine learning classifiers were utilized to distinguish between COVID-19, pneumonia, and healthy subjects.
Main Results:
- The feature-based ensemble approach significantly outperformed methods relying on single feature types (local, radiomic, or deep features).
- The proposed method achieved state-of-the-art multi-class classification results on available COVID-19 datasets.
- The AI-driven system demonstrated high accuracy in differentiating COVID-19 from other thoracic abnormalities.
Conclusions:
- AI-driven automated diagnosis using an ensemble of diverse features offers a robust and accurate method for COVID-19 detection via chest X-rays.
- This approach can overcome the limitations of manual interpretation, reducing errors and improving diagnostic efficiency.
- The findings highlight the potential of integrated feature strategies in medical image analysis for infectious disease identification.
More Related Videos
Related Concept Videos
01:20Imaging Studies for Cardiovascular System III: X-Ray
293
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...
293
01:30Radiological Investigation I: X-ray and CT
396
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...
396