EUVIMEDEUVIMED entdecken
Crossref

Deep Learning Approaches for Multiclass Chest X-Ray Classification: COVID-19, Viral Pneumonia, and Healthy Lungs

Nilesh Goriya, Ajay Upadhyaya

International Journal of Drug Delivery Technology · 01.06.2026 · 16 (42s)

DOI: 10.25258/ijddt.16.42s.54 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 01.06.2026. Verfasst von Nilesh Goriya und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CXR classification for COVID-19, viral pneumonia, and healthy lungs faces challenges from overlapping opacities and limited data, where deep learning offers transformative solutions through CNNs (ResNet, DenseNet), Vision Transformers, and ensembles achieving 95-98% accuracy on datasets like COVID-19 Radiography Database. Transfer learning, augmentation, and attention mechanisms address imbalances and artifacts, while Grad-CAM enhances interpretability; however, domain shifts, overfitting, and privacy concerns persist. Future multimodal fusion with CT/clinical data, federated learning, and edge deployment promise clinically viable AI-radiologist collaboration for global respiratory diagnostics.

Zitieren

APA

Goriya, N., & Upadhyaya, A. (2026). Deep Learning Approaches for Multiclass Chest X-Ray Classification: COVID-19, Viral Pneumonia, and Healthy Lungs. International Journal of Drug Delivery Technology, 16(42s). https://doi.org/10.25258/ijddt.16.42s.54

Vancouver

Goriya N, Upadhyaya A. Deep Learning Approaches for Multiclass Chest X-Ray Classification: COVID-19, Viral Pneumonia, and Healthy Lungs. International Journal of Drug Delivery Technology. 2026;16(42s). doi:10.25258/ijddt.16.42s.54

BibTeX
@article{Goriya2026,
  author = {Goriya, Nilesh and Upadhyaya, Ajay},
  title = {Deep Learning Approaches for Multiclass Chest X-Ray Classification: COVID-19, Viral Pneumonia, and Healthy Lungs},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {42s},
  doi = {10.25258/ijddt.16.42s.54}
}
Kostenlos starten →