EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning

Abida Sultana, Md Nahiduzzaman, Sagor Chandro Bakchy, Saleh Mohammed Shahriar iD, Hasibul Islam Peyal, Muhammad E H Chowdhury iD, Amith Khandakar iD, Mohamed Arselene Ayari iD, Mominul Ahsan iD, Julfikar Haider iD

Sensors · 2023

DOI: 10.3390/s23094458 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Abida Sultana und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh. Hauptthemen laut MEDLINE: COVID-19, Pneumonia, Viral. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qatar National Research Fund, Qatar University student grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Pneumonia, ViralHumansArea Under CurveDecision MakingMachine Learning

Stichwörter der Autor:innen

COVID-19bacterial pneumoniachest X-rayfibrosispre-trained CNNtuberculosisviral pneumonia

Autor:innen und Institutionen

  • Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh.
  • Department of Electrical Engineering, Qatar University, Doha 2713, Qatar.
  • Department of Civil and Architectural Engineering, Qatar University, Doha 2713, Qatar.
  • Department of Computer Science, University of York, Deramore Lane, Heslington, York YO10 5GH, UK.
  • Department of Engineering, Manchester Metropolitan University, Chester Street, Manchester M1 5GD, UK.

ORCID-Profile: Saleh Mohammed Shahriar, Muhammad E H Chowdhury, Amith Khandakar, Mohamed Arselene Ayari, Mominul Ahsan, Julfikar Haider

Förderung

  • Qatar National Research Fund
  • Qatar University student grant

Zitieren

APA

Sultana, A., Nahiduzzaman, M., Bakchy, S. C., Shahriar, S. M., Peyal, H. I., Chowdhury, M. E. H., Khandakar, A., Arselene Ayari, M., Ahsan, M., & Haider, J. (2023). A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning. Sensors. https://doi.org/10.3390/s23094458

Vancouver

Sultana A, Nahiduzzaman M, Bakchy SC, Shahriar SM, Peyal HI, Chowdhury MEH, et al. A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning. Sensors. 2023. doi:10.3390/s23094458

BibTeX
@article{Sultana2023,
  author = {Sultana, Abida and Nahiduzzaman, Md and Bakchy, Sagor Chandro and Shahriar, Saleh Mohammed and Peyal, Hasibul Islam and Chowdhury, Muhammad E H and Khandakar, Amith and Arselene Ayari, Mohamed and Ahsan, Mominul and Haider, Julfikar},
  title = {A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23094458}
}
Kostenlos starten →