Related Experiment Video
Updated: Oct 18, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
A CNN-LSTM network with multi-level feature extraction-based approach for automated detection of coronavirus from CT
Hamad Naeem1, Ali Abdulqader Bin-Salem1
1School of Computer Science and Technology, Zhoukou Normal University, Zhoukou 466001, Henan, China.
Insights
An intelligent framework using deep learning and multi-level feature extraction accurately detects Coronavirus (Covid-19) from CT scans and X-rays. This method enhances diagnostic speed and reliability for effective pandemic management.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiology
Background:
- The growing global population necessitates intelligent disease detection frameworks for timely and accurate diagnoses.
- Coronavirus (Covid-19) emerged as a severe global health threat, requiring rapid diagnostic solutions.
- Automated detection systems are crucial for mitigating the spread and impact of infectious diseases like Covid-19.
Purpose of the Study:
- To develop an automated framework for Covid-19 identification using CT scans and chest X-rays.
- To enhance the accuracy and robustness of Covid-19 detection through advanced feature extraction techniques.
- To provide a faster diagnostic alternative for effective pandemic response.
Main Methods:
- A combined deep learning and multi-level feature extraction methodology was employed.
- Feature extraction utilized GIST, Scale Invariant Feature Transform (SIFT), and Convolutional Neural Network (CNN).
- Long Short-Term Memory (LSTM) networks were integrated with CNN for feature detection.
Main Results:
- The proposed approach achieved 98.94% accuracy on the Kaggle SARS-CoV-2 CT scan dataset.
- An accuracy of 83.03% was obtained on the Italian SIRM Covid-19 CT scan and chest X-ray dataset.
- The methodology demonstrated significant potential for accurate and robust Covid-19 identification.
Conclusions:
- The developed framework offers an effective tool for radiologists and practitioners in diagnosing Covid-19.
- The integration of deep learning and multi-level feature extraction improves diagnostic accuracy and efficiency.
- This approach can aid in the timely detection and treatment of Covid-19 cases, particularly during pandemics.
Abstract:
Auto-detection of diseases has become a prime issue in medical sciences as population density is fast growing. An intelligent framework for disease detection helps physicians identify illnesses, give reliable and consistent results, and reduce death rates. Coronavirus (Covid-19) has recently been one of the most severe and acute diseases in the world. An automatic detection framework should therefore be introduced as the fastest diagnostic alternative to avoid Covid-19 spread. In this paper, an automatic Covid-19 identification in the CT scan and chest X-ray is obtained with the help of a combined deep learning and multi-level feature extraction methodology. In this method, the multi-level feature extraction approach comprises GIST, Scale Invariant Feature Transform (SIFT), and Convolutional Neural Network (CNN) extract features from CT scans and chest X-rays. The objective of multi-level feature extraction is to reduce the training complexity of CNN network, which significantly assists in accurate and robust Covid-19 identification. Finally, Long Short-Term Memory (LSTM) along the CNN network is used to detect the extracted Covid-19 features. The Kaggle SARS-CoV-2 CT scan dataset and the Italian SIRM Covid-19 CT scan and chest X-ray dataset were employed for testing purposes. Experimental outcomes show that proposed approach obtained 98.94% accuracy with the SARS-CoV-2 CT scan dataset and 83.03% accuracy with the SIRM Covid-19 CT scan and chest X-ray dataset. The proposed approach helps radiologists and practitioners to detect and treat Covid-19 cases effectively over the pandemic.
