EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Flexible Multi-Channel Deep Network Leveraging Texture and Spatial Features for Diagnosing New COVID-19 Variants in Lung CT Scans

Shervan Fekri-Ershad iD, Khalegh Behrouz Dehkordi

Tomography · 2025

DOI: 10.3390/tomography11090099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Shervan Fekri-Ershad und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Na.C., Islamic Azad University, Najafabad 8514143131, Iran. Hauptthemen laut MEDLINE: COVID-19, Tomography, X-Ray Computed, SARS-CoV-2, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The COVID-19 pandemic has claimed thousands of lives worldwide. While infection rates have declined in recent years, emerging variants remain a deadly threat. Accurate diagnosis is critical to curbing transmission and improving treatment outcomes. However, the similarity of COVID-19 symptoms to those of the common cold and flu has spurred the development of automated diagnostic methods, particularly through lung computed-tomography (CT) scan analysis. Methodology: This paper proposes a novel deep learning-based approach for detecting diverse COVID-19 variants using advanced textural feature extraction. The framework employs a dual-channel convolutional neural network (CNN), where one channel processes texture-based features and the other analyzes spatial information. Unlike existing methods, our model dynamically learns textural patterns during training, eliminating reliance on predefined features. A modified local binary pattern (LBP) technique extracts texture data in matrix form, while the CNN’s adaptable internal architecture optimizes the balance between accuracy and computational efficiency. To enhance performance, hyperparameters are fine-tuned using the Adam optimizer and focal loss function.

Results

The proposed method is evaluated on two benchmark datasets, COVID-349 and Italian COVID-Set, which include diverse COVID-19 variants.

Conclusions

The results demonstrate its superior accuracy (94.63% and 95.47%, respectively), outperforming competing approaches in precision, recall, and overall diagnostic reliability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Tomography, X-Ray ComputedSARS-CoV-2Deep LearningLungHumansNeural Networks, ComputerRadiographic Image Interpretation, Computer-Assisted

Stichwörter der Autor:innen

computer tomography scanconvolution neural networkdeep networkfeature extractiontexture image analysis

Autor:innen und Institutionen

  • Department of Computer Engineering, Na.C., Islamic Azad University, Najafabad 8514143131, Iran.
  • Big Data Research Center, Na.C., Islamic Azad University, Najafabad 8514143131, Iran.

ORCID-Profile: Shervan Fekri-Ershad

Zitieren

APA

Fekri-Ershad, S., & Dehkordi, K. B. (2025). A Flexible Multi-Channel Deep Network Leveraging Texture and Spatial Features for Diagnosing New COVID-19 Variants in Lung CT Scans. Tomography. https://doi.org/10.3390/tomography11090099

Vancouver

Fekri-Ershad S, Dehkordi KB. A Flexible Multi-Channel Deep Network Leveraging Texture and Spatial Features for Diagnosing New COVID-19 Variants in Lung CT Scans. Tomography. 2025. doi:10.3390/tomography11090099

BibTeX
@article{FekriErshad2025,
  author = {Fekri-Ershad, Shervan and Dehkordi, Khalegh Behrouz},
  title = {A Flexible Multi-Channel Deep Network Leveraging Texture and Spatial Features for Diagnosing New COVID-19 Variants in Lung CT Scans},
  journal = {Tomography},
  year = {2025},
  doi = {10.3390/tomography11090099}
}
Kostenlos starten →