Related Experiment Video
Updated: Dec 6, 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
14.6K
Deep learning approaches for COVID-19 detection based on chest X-ray images
Aras M Ismael1, Abdulkadir Şengür2
1Sulaimani Polytechnic University, College of Informatics, Information Technology Department, Sulaymaniyah, Iraq.
Expert Systems with Applications
|October 5, 2020
Summary
Deep learning models effectively detect COVID-19 from chest X-rays. The ResNet50 model with Support Vector Machines achieved the highest accuracy (94.7%) for classifying COVID-19 versus healthy lungs.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Infectious Diseases
Background:
- COVID-19 pandemic necessitates rapid diagnostic tools.
- Chest X-rays are valuable for assessing lung conditions, including COVID-19.
- Deep learning offers potential for automated analysis of medical images.
Purpose of the Study:
- To evaluate deep learning approaches for classifying COVID-19 from normal chest X-ray images.
- To compare the performance of deep feature extraction, fine-tuning, and end-to-end CNN training.
- To identify the most effective deep learning model for COVID-19 detection using X-rays.
Main Methods:
- Utilized deep feature extraction with pretrained Convolutional Neural Networks (CNNs) like ResNet and VGG, followed by Support Vector Machine (SVM) classification.
- Applied fine-tuning to pretrained CNN models.
- Developed and trained a novel CNN model from scratch using an end-to-end approach.
- Experimented on a dataset of 180 COVID-19 and 200 normal chest X-ray images.
Main Results:
- The highest classification accuracy of 94.7% was achieved using deep features from ResNet50 and an SVM classifier with a Linear kernel.
- Fine-tuned ResNet50 yielded 92.6% accuracy.
- End-to-end training of the developed CNN model resulted in 91.6% accuracy.
- Deep learning methods outperformed traditional local texture descriptors.
Conclusions:
- Deep learning techniques demonstrate significant potential for accurate COVID-19 detection from chest X-ray images.
- The combination of ResNet50 deep features and SVM classification is a highly effective strategy.
- Automated analysis using deep learning can aid in the rapid diagnosis of COVID-19.
Related Concept Videos
01:20Imaging Studies for Cardiovascular System III: X-Ray
389
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...
389
01:30Radiological Investigation I: X-ray and CT
890
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...
890