A novel lightweight CNN for chest X-ray-based lung disease identification on heterogeneous embedded system
Applied Intelligence · 2024-03 · 54 (6) · 4756-4780
DOI: 10.1007/s10489-024-05420-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Intelligence, online erschienen am 04.04.2024. Verfasst von Theodora Sanida und 1 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Western Macedonia.
Abstract (Originalsprache)
The global spread of epidemic lung diseases, including COVID-19, underscores the need for efficient diagnostic methods. Addressing this, we developed and tested a computer-aided, lightweight Convolutional Neural Network (CNN) for rapid and accurate identification of lung diseases from 29,131 aggregated Chest X-ray (CXR) images representing seven disease categories. Employing the five-fold cross-validation method to ensure the robustness of our results, our CNN model, optimized for heterogeneous embedded devices, demonstrated superior diagnostic performance. It achieved a 98.56% accuracy, outperforming established networks like ResNet50, NASNetMobile, Xception, MobileNetV2, DenseNet121, and ViT-B/16 across precision, recall, F1-score, and AUC metrics. Notably, our model requires significantly less computational power and only 55 minutes of average training time per fold, making it highly suitable for resource-constrained environments. This study contributes to developing efficient, lightweight networks in medical image analysis, underscoring their potential to enhance point-of-care diagnostic processes.
Förderung
- University of Western Macedonia
Zitieren
APA
Sanida, T., & Dasygenis, M. (2024). A novel lightweight CNN for chest X-ray-based lung disease identification on heterogeneous embedded system. Applied Intelligence, 54(6), 4756-4780. https://doi.org/10.1007/s10489-024-05420-2
Vancouver
Sanida T, Dasygenis M. A novel lightweight CNN for chest X-ray-based lung disease identification on heterogeneous embedded system. Applied Intelligence. 2024;54(6):4756-4780. doi:10.1007/s10489-024-05420-2
BibTeX
@article{Sanida2024,
author = {Sanida, Theodora and Dasygenis, Minas},
title = {A novel lightweight CNN for chest X-ray-based lung disease identification on heterogeneous embedded system},
journal = {Applied Intelligence},
year = {2024},
volume = {54},
number = {6},
pages = {4756--4780},
doi = {10.1007/s10489-024-05420-2}
}
EUVIMED