EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review

Hammad Iqbal, Arshad Khan, Narayan Nepal, Faheem Khan, Yeon-Kug Moon

Electronics · 27.11.2024 · 13 (23) · 4688

DOI: 10.3390/electronics13234688 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Electronics, online erschienen am 27.11.2024. Verfasst von Hammad Iqbal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Culture, Sports and Tourism in 2024, Sejong University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung diseases are a major global health concern, with nearly 4 million deaths annually, according to the World Health Organization (WHO). Chest X-rays (CXR) are widely used as a cost-effective and efficient diagnostic tool by radiologists to detect conditions such as pneumonia, tuberculosis, COVID-19, and lung cancer. This review paper provides an overview of the current research on diagnosing lung diseases using CXR images and Artificial Intelligence (AI), without focusing on any specific disease. It examines different approaches employed by researchers to leverage CXR, an accessible diagnostic medium, for early lung disease detection. This review shortlisted 11 research papers addressing this problem through AI, exploring the datasets used and their sources. Results varied across studies: for lung cancer, Deep Convolutional Neural Network (DCNN) achieved 97.20% accuracy, while multiclass frameworks like ResNet152V2+Bi-GRU (gated reccurent unit) reached 79.78% and 93.38%, respectively. For COVID-19 detection, accuracy rates of 98% and 99.37% were achieved using EfficientNet and Parallel Convolutional Neural Network-Extreme Learning Machine (CNN-ELM). Additionally, studies on the CXR-14 dataset (14 classes) showed high accuracy, with MobileNet V2 reaching 94%. Other notable results include 73% accuracy with VDSNet, 98.05% with VGG19+CNN for three classes, and high accuracy in detecting pediatric pneumonia, lung opacity, pneumothorax, and tuberculosis.

Förderung

  • Ministry of Culture, Sports and Tourism in 2024
  • Sejong University

Zitieren

APA

Iqbal, H., Khan, A., Nepal, N., Khan, F., & Moon, Y. (2024). Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review. Electronics, 13(23), 4688. https://doi.org/10.3390/electronics13234688

Vancouver

Iqbal H, Khan A, Nepal N, Khan F, Moon Y. Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review. Electronics. 2024;13(23):4688. doi:10.3390/electronics13234688

BibTeX
@article{Iqbal2024,
  author = {Iqbal, Hammad and Khan, Arshad and Nepal, Narayan and Khan, Faheem and Moon, Yeon-Kug},
  title = {Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {23},
  pages = {4688},
  doi = {10.3390/electronics13234688}
}
Kostenlos starten →