EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Synthetic Lung Ultrasound Data Generation Using Autoencoder With Generative Adversarial Network

Noreen Fatima, Federico Mento, Sajjad Afrakhteh, Tiziano Perrone, Andrea Smargiassi, Riccardo Inchingolo, Libertario Demi

IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · 2025

DOI: 10.1109/tuffc.2025.3555447 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2025. Verfasst von Noreen Fatima und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Lung, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union, Ministero dell'Universit? e della Ricerca.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Class imbalance is a significant challenge in medical image analysis, particularly in lung ultrasound (LUS), where severe patterns are often underrepresented. Traditional oversampling techniques, which simply duplicate original data, have limited effectiveness in addressing this issue. To overcome these limitations, this study introduces a novel supervised autoencoder generative adversarial network (SA-GAN) for data augmentation, leveraging advanced generative artificial intelligence (AI) to create high-quality synthetic samples for minority classes. In addition, the traditional data augmentation technique is used for comparison. The SA-GAN incorporates an autoencoder to develop a conditional latent space, effectively addressing weight clipping issues and ensuring higher quality synthetic data. The generated samples are evaluated using similarity metrics and expert analysis to validate their utility. Furthermore, state-of-the-art neural networks are used for multiclass classification, and their performance is compared when trained with GAN-based augmentation versus traditional data augmentation techniques. These contributions enhance the robustness and reliability of AI models in mitigating class imbalance in LUS analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LungNeural Networks, ComputerImage Processing, Computer-AssistedUltrasonographyHumansAlgorithmsGenerative Adversarial NetworksAutoencoder

Förderung

  • European Union
  • Ministero dell'Universit? e della Ricerca

Zitieren

APA

Fatima, N., Mento, F., Afrakhteh, S., Perrone, T., Smargiassi, A., Inchingolo, R., & Demi, L. (2025). Synthetic Lung Ultrasound Data Generation Using Autoencoder With Generative Adversarial Network. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. https://doi.org/10.1109/tuffc.2025.3555447

Vancouver

Fatima N, Mento F, Afrakhteh S, Perrone T, Smargiassi A, Inchingolo R, et al. Synthetic Lung Ultrasound Data Generation Using Autoencoder With Generative Adversarial Network. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2025. doi:10.1109/tuffc.2025.3555447

BibTeX
@article{Fatima2025,
  author = {Fatima, Noreen and Mento, Federico and Afrakhteh, Sajjad and Perrone, Tiziano and Smargiassi, Andrea and Inchingolo, Riccardo and Demi, Libertario},
  title = {Synthetic Lung Ultrasound Data Generation Using Autoencoder With Generative Adversarial Network},
  journal = {IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
  year = {2025},
  doi = {10.1109/tuffc.2025.3555447}
}
Kostenlos starten →