Synthetic Data Generation via Generative Adversarial Networks in Healthcare: A Systematic Review of Image- and Signal-Based Studies.

Autor:	Akpinar MH; Vocational School of Technical SciencesIstanbul University-Cerrahpasa 34320 Istanbul Türkiye., Sengur A; Technology FacultyFirat University 23119 Elazig Türkiye., Salvi M; Department of Electronics and TelecommunicationsPolitecnico di Torino 10129 Turin Italy., Seoni S; Department of Electronics and TelecommunicationsPolitecnico di Torino 10129 Turin Italy., Faust O; Anglia Ruskin University Cambridge Campus CB1 1PT Cambridge U.K., Mir H; American University of Sharjah Sharjah 26666 UAE., Molinari F; Department of Electronics and TelecommunicationsPolitecnico di Torino 10129 Turin Italy., Acharya UR; University of Southern Queensland Toowoomba QLD 4300 Australia.
Jazyk:	angličtina
Zdroj:	IEEE open journal of engineering in medicine and biology [IEEE Open J Eng Med Biol] 2024 Nov 28; Vol. 6, pp. 183-192. Date of Electronic Publication: 2024 Nov 28 (Print Publication: 2025).
DOI:	10.1109/OJEMB.2024.3508472
Abstrakt:	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. Competing Interests: The authors declare that they have no conflicts of interest. (© 2024 The Authors.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu