Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies
IEEE Open Journal of Engineering in Medicine and Biology · 2025 · 6 · 183-192
DOI: 10.1109/ojemb.2024.3508472 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift IEEE Open Journal of Engineering in Medicine and Biology, 2025. Verfasst von Muhammed Halil Akpinar und 7 weiteren Autor:innen. Beteiligte Einrichtung: Vocational School of Technical SciencesIstanbul University-Cerrahpasa 34320 Istanbul Türkiye. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 110 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Politecnico di Torino, CRUI-CARE initiative.
Abstract (Originalsprache)
Generative Adversarial Networks (GANs) have emerged as a powerful tool in artificial intelligence, particularly for unsupervised learning. This systematic review analyzes GAN applications in healthcare, focusing on image and signal-based studies across various clinical domains. Following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, we reviewed 72 relevant journal articles. Our findings reveal that magnetic resonance imaging (MRI) and electrocardiogram (ECG) signal acquisition techniques were most utilized, with brain studies (22%), cardiology (18%), cancer (15%), ophthalmology (12%), and lung studies (10%) being the most researched areas. We discuss key GAN architectures, including cGAN (31%) and CycleGAN (18%), along with datasets, evaluation metrics, and performance outcomes. The review highlights promising data augmentation, anonymization, and multi-task learning results. We identify current limitations, such as the lack of standardized metrics and direct comparisons, and propose future directions, including the development of no-reference metrics, immersive simulation scenarios, and enhanced interpretability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Vocational School of Technical SciencesIstanbul University-Cerrahpasa 34320 Istanbul Türkiye.
- Technology FacultyFirat University 23119 Elazig Türkiye.
- Department of Electronics and TelecommunicationsPolitecnico di Torino 10129 Turin Italy.
- Anglia Ruskin University Cambridge Campus CB1 1PT Cambridge U.K.
- American University of Sharjah Sharjah 26666 UAE.
- University of Southern Queensland Toowoomba QLD 4300 Australia.
ORCID-Profile: Muhammed Halil Akpinar, Abdulkadir Sengur, Massimo Salvi, Silvia Seoni, Hasan Mir, Filippo Molinari
Förderung
- Politecnico di Torino
- CRUI-CARE initiative
Zitieren
APA
Akpinar, M. H., Sengur, A., Salvi, M., Seoni, S., Faust, O., Mir, H., Molinari, F., & Acharya, U. R. (2025). Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies. IEEE Open Journal of Engineering in Medicine and Biology, 6, 183-192. https://doi.org/10.1109/ojemb.2024.3508472
Vancouver
Akpinar MH, Sengur A, Salvi M, Seoni S, Faust O, Mir H, et al. Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies. IEEE Open Journal of Engineering in Medicine and Biology. 2025;6:183-192. doi:10.1109/ojemb.2024.3508472
BibTeX
@article{Akpinar2025,
author = {Akpinar, Muhammed Halil and Sengur, Abdulkadir and Salvi, Massimo and Seoni, Silvia and Faust, Oliver and Mir, Hasan and Molinari, Filippo and Acharya, U Rajendra},
title = {Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies},
journal = {IEEE Open Journal of Engineering in Medicine and Biology},
year = {2025},
volume = {6},
pages = {183--192},
doi = {10.1109/ojemb.2024.3508472}
}
EUVIMED