EUVIMEDEUVIMED entdecken
Crossref

Lung-Attnet: An Attention Mechanism-Based Cnn Architecture For Lung Cancer Detection With Federated Learning

Mrs. S. Nandhini Devi, Mrs. D. Maalini, R. Yutha, S. Yuvasudhan, M. Aathika, S. Abinaya

International Journal of Drug Delivery Technology · 16.04.2026 · 16 (13s)

DOI: 10.25258/ijddt.16.13s.22 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 16.04.2026. Verfasst von Mrs. S. Nandhini Devi und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer is one of the most serious threats to human health today and it is responsible for a large proportion of deaths from cancer each year. In order to improve survival rates and provide timely intervention, early and accurate detection of lung cancer is essential. This project proposes a smart lung cancer detection system using deep learning techniques on computed tomography (CT) scan images to automate the detection of lung cancer through the use of an artificial intelligence (AI) based Convolutional Neural Network (CNN) model. The CNN model uses automatically learnt complex representations of CT images to extract relevant features and patterns associated with cancerous lung nodules, and this allows the model to identify malignant lung tissues from non-malignant lung tissues with high accuracy, sensitivity, and specificity. The dataset for this project consists of publicly available CT images from both lung cancer patients and benign patients. During training, the CNN model learns how to identify the small variations between the patterns of the CT images resulting from lung cancer and the patterns resulting from being benign. The results from extensive experimental analysis demonstrate that the proposed system can reliably detect lung cancer. The use of an automated detection system decreases the reliance on visual inspection by a physician, and subsequently, reduces the occurrence of diagnostic errors. The approach proposed in this study is a non-invasive decision support tool that provides a reliable and efficient way for radiologists to diagnose lung cancer earlier than before and thus enhance the quality of care for patients treated for lung cancer.

Zitieren

APA

Devi, M. S. N., Maalini, M. D., Yutha, R., Yuvasudhan, S., Aathika, M., & Abinaya, S. (2026). Lung-Attnet: An Attention Mechanism-Based Cnn Architecture For Lung Cancer Detection With Federated Learning. International Journal of Drug Delivery Technology, 16(13s). https://doi.org/10.25258/ijddt.16.13s.22

Vancouver

Devi MSN, Maalini MD, Yutha R, Yuvasudhan S, Aathika M, Abinaya S. Lung-Attnet: An Attention Mechanism-Based Cnn Architecture For Lung Cancer Detection With Federated Learning. International Journal of Drug Delivery Technology. 2026;16(13s). doi:10.25258/ijddt.16.13s.22

BibTeX
@article{Devi2026,
  author = {Devi, Mrs. S. Nandhini and Maalini, Mrs. D. and Yutha, R. and Yuvasudhan, S. and Aathika, M. and Abinaya, S.},
  title = {Lung-Attnet: An Attention Mechanism-Based Cnn Architecture For Lung Cancer Detection With Federated Learning},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {13s},
  doi = {10.25258/ijddt.16.13s.22}
}
Kostenlos starten →