EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ChestCovidNet: an effective deep learning based approach for COVID-19, lung opacity, and pneumonia detection using chest radiograph images

Naeem Ullah, Javed Ali Khan iD, Sultan Almakdi iD, Mohammed S Alshehri iD, Mimonah Al Qathrady, Muhammad Shahid Anwar iD, Ikram Syed iD

Biochemistry and Cell Biology · 2026

DOI: 10.1139/bcb-2023-0265 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biochemistry and Cell Biology, 2026. Verfasst von Naeem Ullah und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Software Engineering, University of Engineering and Technology, Taxila 4400, Pakistan. Hauptthemen laut MEDLINE: COVID-19, Deep Learning, Lung, Pneumonia. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Currently used lung disease screening tools are expensive in terms of money and time. Therefore, chest radiograph images (CRIs) are employed for prompt and accurate COVID-19 identification. Recently, many researchers have applied deep learning (DL) based models to detect COVID-19 automatically. However, their model could have been more computationally expensive and less robust, i.e., its performance degrades when evaluated on other datasets. This study proposes a trustworthy, robust, and lightweight network (ChestCovidNet) that can detect COVID-19 by examining various CRI datasets. The ChestCovidNet model has only 11 learned layers, 8 convolutional (Conv) layers, and 3 fully connected (FC) layers. The framework employs both the Conv and group Conv layers, Leaky Relu activation function, shufflenet unit, Conv kernels of 3 × 3 and 1 × 1 to extract features at different scales, and two normalization procedures that are cross-channel normalization and batch normalization, which make it a novel COVID-19 identification framework. We used data augmentation techniques to increase the number of images and validate the generalizability of the suggested model. We used 9013 CRIs for training, whereas 3863 CRIs for testing the proposed ChestCovidNet approach. Furthermore, we compared the classification results of the proposed framework with hybrid methods in which we employed DL frameworks for feature extraction and support vector machines (SVM) for classification. The study’s findings demonstrated that the embedded low-power ChestCovidNet model worked well and achieved a classification accuracy of 98.12% and recall, F1-score, and precision of 95.75% for the four class classifications of CRIs (COVID-19, normal, pneumonia, and lung opacity (LO)).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Deep LearningLungPneumoniaRadiography, ThoracicHumansSARS-CoV-2

Stichwörter der Autor:innen

COVID-19chest radiograph imagesdeep learninghealthcarelung opacitypneumonia

Autor:innen und Institutionen

  • Department of Software Engineering, University of Engineering and Technology, Taxila 4400, Pakistan.
  • Department of Computer Science, School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UK.
  • Department of Computer Science, College of Computer Science and Information System, Najran University, Najran 55461, Saudi Arabia.
  • Departments of Information Systems, College of Computer Science and Information Systems, Najran University, Najran 61441, Saudi Arabia.
  • Department of AI and Software Gachon University, Seongnam-si 13120, South Korea.

ORCID-Profile: Javed Ali Khan, Sultan Almakdi, Mohammed S Alshehri, Muhammad Shahid Anwar, Ikram Syed

Zitieren

APA

Ullah, N., Khan, J., Almakdi, S., Alshehri, M., Al Qathrady, M., Anwar, M., & Syed, I. (2026). ChestCovidNet: an effective deep learning based approach for COVID-19, lung opacity, and pneumonia detection using chest radiograph images. Biochemistry and Cell Biology. https://doi.org/10.1139/bcb-2023-0265

Vancouver

Ullah N, Khan J, Almakdi S, Alshehri M, Al Qathrady M, Anwar M, et al. ChestCovidNet: an effective deep learning based approach for COVID-19, lung opacity, and pneumonia detection using chest radiograph images. Biochemistry and Cell Biology. 2026. doi:10.1139/bcb-2023-0265

BibTeX
@article{Ullah2026,
  author = {Ullah, Naeem and Khan, Javed Ali and Almakdi, Sultan and Alshehri, Mohammed S and Al Qathrady, Mimonah and Anwar, Muhammad Shahid and Syed, Ikram},
  title = {ChestCovidNet: an effective deep learning based approach for COVID-19, lung opacity, and pneumonia detection using chest radiograph images},
  journal = {Biochemistry and Cell Biology},
  year = {2026},
  doi = {10.1139/bcb-2023-0265}
}
Kostenlos starten →