Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Apr 2;13(7):1319.
doi: 10.3390/diagnostics13071319.

Simultaneous Super-Resolution and Classification of Lung Disease Scans

Heba M Emara  1 , Mohamed R Shoaib  2 , Walid El-Shafai  3   4 , Mohamed Elwekeil  4 , Ezz El-Din Hemdan  5 , Mostafa M Fouda  6 , Taha E Taha  4 , Adel S El-Fishawy  4 , El-Sayed M El-Rabaie  4 , Fathi E Abd El-Samie  4   7
Affiliations

Simultaneous Super-Resolution and Classification of Lung Disease Scans

Heba M Emara et al. Diagnostics (Basel). .

Abstract

Acute lower respiratory infection is a leading cause of death in developing countries. Hence, progress has been made for early detection and treatment. There is still a need for improved diagnostic and therapeutic strategies, particularly in resource-limited settings. Chest X-ray and computed tomography (CT) have the potential to serve as effective screening tools for lower respiratory infections, but the use of artificial intelligence (AI) in these areas is limited. To address this gap, we present a computer-aided diagnostic system for chest X-ray and CT images of several common pulmonary diseases, including COVID-19, viral pneumonia, bacterial pneumonia, tuberculosis, lung opacity, and various types of carcinoma. The proposed system depends on super-resolution (SR) techniques to enhance image details. Deep learning (DL) techniques are used for both SR reconstruction and classification, with the InceptionResNetv2 model used as a feature extractor in conjunction with a multi-class support vector machine (MCSVM) classifier. In this paper, we compare the proposed model performance to those of other classification models, such as Resnet101 and Inceptionv3, and evaluate the effectiveness of using both softmax and MCSVM classifiers. The proposed system was tested on three publicly available datasets of CT and X-ray images and it achieved a classification accuracy of 98.028% using a combination of SR and InceptionResNetv2. Overall, our system has the potential to serve as a valuable screening tool for lower respiratory disorders and assist clinicians in interpreting chest X-ray and CT images. In resource-limited settings, it can also provide a valuable diagnostic support.

Keywords: Coronavirus; chest X-ray radiographs; convolutional neural network; image super-resolution; multi-class SVM.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 3
Figure 3
Block diagram of the proposed DCNN image SR model.
Figure 1
Figure 1
Main architecture of the proposed framework.
Figure 2
Figure 2
Samples of augmented images.
Figure 4
Figure 4
Overall scheme of the InceptionResNetv2 network.
Figure 5
Figure 5
Overall architecture of the Inception-resnet modules. (a) Inception-resnet-A. (b) Inception-resnet-B. (c) Inception-resnet-C.
Figure 6
Figure 6
Reduction-A and Reduction-B modules (a,b).
Figure 7
Figure 7
Confusion matrix for InceptionResNetv2-MCSVM-based model with image SR using dataset #1.
Figure 8
Figure 8
ROC curve for InceptionResNetv2-MCSVM-based model with image SR using dataset #1.
Figure 9
Figure 9
Training progress curve for InceptionResNetv2-MCSVM-based model with image SR using dataset #1.
Figure 10
Figure 10
Confusion matrix for InceptionResnetv2 model with image SR using dataset #2.
Figure 11
Figure 11
ROC curve for InceptionResnetv2 model with image SR using dataset #2.
Figure 12
Figure 12
Training progress curve for InceptionResnetv2 model with image SR using dataset #2.
Figure 13
Figure 13
Confusion matrix for InceptionResNetv2 model with image SR using dataset #3.
Figure 14
Figure 14
ROC curve for InceptionResNetv2 model with image SR using dataset #3.
Figure 15
Figure 15
Training progress for InceptionResNetv2 model for dataset #3.
Figure 16
Figure 16
t-SNE plot of the extracted features from the fully-connected layer for dataset #1.
Figure 17
Figure 17
t-SNE plot of the extracted features from the fully-connected layer for dataset #2.
Figure 18
Figure 18
t-SNE plot of the extracted features from the fully-connected layer for dataset #3.
Figure 19
Figure 19
Accuracies rates for the proposed approaches.
See this image and copyright information in PMC

References

    1. Cruz A.A. Global Surveillance, Prevention and Control of Chronic Respiratory Diseases: A Comprehensive Approach. World Health Organization; Geneva, Switzerland: 2007.
    1. GBD Chronic Respiratory Disease Collaborators Prevalence and attributable health burden of chronic respiratory diseases, 1990–2017: A systematic analysis for the Global Burden of Disease Study 2017. Lancet Respir. Med. 2020;8:585–596. doi: 10.1016/S2213-2600(20)30105-3. - DOI - PMC - PubMed
    1. WHO . World Health Organization Coronavirus Disease 2019 (COVID-19) Situation Report. World Health Organization; Geneva, Switzerland: 2020.
    1. Rahaman M.M., Li C., Yao Y., Kulwa F., Rahman M.A., Wang Q., Qi S., Kong F., Zhu X., Zhao X. Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches. J. X-ray Sci. Technol. 2020;28:821–839. doi: 10.3233/XST-200715. - DOI - PMC - PubMed
    1. Alqudah A., Alqudah A.M. Sliding window based deep ensemble system for breast cancer classification. J. Med. Eng. Technol. 2021;45:313–323. doi: 10.1080/03091902.2021.1896814. - DOI - PubMed