EUVIMEDEUVIMED entdecken
Crossref

A Robust Deep CNN Framework for Automated Pneumonia Identification from Chest Radiographs

Dr. Rajath A N, Dr. Anand M, Dr. Divya S, Dr. Pradeep Kumar R, Dr. Anitha K, Dr. Aishwarya N Kumar

International Journal of Drug Delivery Technology · 27.04.2026 · 16 (19s)

DOI: 10.25258/ijddt.16.19s.102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 27.04.2026. Verfasst von Dr. Rajath A N und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pneumonia is a common respiratory disorder and a major cause of morbidity and mortality worldwide, particularly among older adults and children under five years of age. Early and accurate diagnosis is essential for effective treatment; however, conventional diagnostic methods based on manual interpretation of chest X-ray images are often timeconsuming and subject to inter-observer variability. To address these limitations, this study proposes an artificial intelligence-based framework for automated pneumonia detection using convolutional neural networks (CNNs).The proposed framework consists of two complementary components: a U-Net-based segmentation model for identifying infected lung regions and a CNN-based classification model for discriminating between normal and pneumonia-infected chest radiographs. The system was trained and evaluated on a dataset of 20,000 chest X-ray images. Experimental results show that the segmentation model achieved a Dice score of 0.9587 and an Intersection over Union (IoU) of 0.9225, while the classification model attained an accuracy of 95%. The findings indicate that the proposed deep learning approach outperforms conventional machine learning methods and achieves performance comparable to that of experienced radiologists. Furthermore, the integration of disease classification with visual localization improves both diagnostic interpretability and clinical reliability. The proposed system therefore offers a promising decision-support tool for efficient and accurate pneumonia screening in healthcare settings.

Zitieren

APA

N, D. R. A., M, D. A., S, D. D., R, D. P. K., K, D. A., & Kumar, D. A. N. (2026). A Robust Deep CNN Framework for Automated Pneumonia Identification from Chest Radiographs. International Journal of Drug Delivery Technology, 16(19s). https://doi.org/10.25258/ijddt.16.19s.102

Vancouver

N DRA, M DA, S DD, R DPK, K DA, Kumar DAN. A Robust Deep CNN Framework for Automated Pneumonia Identification from Chest Radiographs. International Journal of Drug Delivery Technology. 2026;16(19s). doi:10.25258/ijddt.16.19s.102

BibTeX
@article{N2026,
  author = {N, Dr. Rajath A and M, Dr. Anand and S, Dr. Divya and R, Dr. Pradeep Kumar and K, Dr. Anitha and Kumar, Dr. Aishwarya N},
  title = {A Robust Deep CNN Framework for Automated Pneumonia Identification from Chest Radiographs},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {19s},
  doi = {10.25258/ijddt.16.19s.102}
}
Kostenlos starten →