Related Experiment Video
Updated: Aug 8, 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
Detection of COVID-19 Case from Chest CT Images Using Deformable Deep Convolutional Neural Network
Md Foysal1, A B M Aowlad Hossain1, Abdulsalam Yassine2
1Department of Electronics and Communication Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh.
Journal of Healthcare Engineering
|February 27, 2023
Summary
This study introduces deformable deep learning models for COVID-19 detection using chest CT scans. The deformable ResNet-50 model achieved high accuracy, offering a promising alternative for rapid COVID-19 diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Science
Background:
- COVID-19 poses a significant global health threat, necessitating rapid and accurate detection methods.
- While RT-PCR is standard, chest CT scans offer a viable alternative, especially when RT-PCR is limited.
- Deep learning for COVID-19 detection from CT images is an emerging and crucial area of research.
Purpose of the Study:
- To propose and evaluate novel deformable deep learning networks for COVID-19 detection from chest CT images.
- To compare the performance of deformable models against their conventional counterparts.
- To assess the effectiveness of the deformable ResNet-50 model for clinical application.
Main Methods:
- Development of two deformable deep networks: one based on Convolutional Neural Network (CNN) and another on ResNet-50.
- Comparative analysis of deformable models versus standard models.
- Utilizing Gradient Class Activation Mapping (Grad-CAM) for visualizing model attention.
- Training and testing on a dataset of 2481 chest CT images with an 80:10:10 split.
Main Results:
- Deformable models demonstrated superior prediction performance compared to their normal counterparts.
- The proposed deformable ResNet-50 model outperformed the deformable CNN model.
- The deformable ResNet-50 model achieved 99.5% training accuracy and 97.6% test accuracy.
- High specificity (98.5%) and sensitivity (96.5%) were recorded for the deformable ResNet-50 model.
- Grad-CAM visualization confirmed excellent localization of targeted regions.
Conclusions:
- Deformable deep learning networks, particularly the deformable ResNet-50, show significant potential for accurate COVID-19 detection from chest CT scans.
- The proposed models offer a robust and efficient alternative for clinical settings, especially when rapid diagnosis is critical.
- The findings support the integration of advanced AI techniques in medical diagnostics for infectious diseases.
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
56
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
56
01:10Computed Tomography
4.7K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.7K