EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Privacy-Preserving Synthetic Mammograms: A Generative Model Approach to Privacy-Preserving Breast Imaging Datasets

Damir Shodiev, Egor Ushakov, Arsenii Litvinov, Yury Markin

Informatics · 18.10.2025 · 12 (4) · 112

DOI: 10.3390/informatics12040112 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatics, online erschienen am 18.10.2025. Verfasst von Damir Shodiev und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Economic Development of the Russian Federation, Ivannikov Institute for System Programming of the Russian Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Significant progress has been made in the field of machine learning, enabling the development of methods for automatic interpretation of medical images that provide high-quality diagnostics. However, most of these methods require access to confidential data, making them difficult to apply under strict privacy requirements. Existing privacy-preserving approaches, such as federated learning and dataset distillation, have limitations related to data access, visual interpretability, etc.

Methods

This study explores the use of generative models to create synthetic medical data that preserves the statistical properties of the original data while ensuring privacy. The research is carried out on the VinDr-Mammo dataset of digital mammography images. A conditional generative method using Latent Diffusion Models (LDMs) is proposed with conditioning on diagnostic labels and lesion information. Diagnostic utility and privacy robustness are assessed via cancer classification tasks and re-identification tasks using Siamese neural networks and membership inference.

Results

The generated synthetic data achieved a Fréchet Inception Distance (FID) of 5.8, preserving diagnostic features. A model trained solely on synthetic data achieved comparable performance to one trained on real data (ROC-AUC: 0.77 vs. 0.82). Visual assessments showed that synthetic images are indistinguishable from real ones. Privacy evaluations demonstrated a low re-identification risk (e.g., mAP@R = 0.0051 on the test set), confirming the effectiveness of the privacy-preserving approach.

Conclusions

The study demonstrates that privacy-preserving generative models can produce synthetic medical images with sufficient quality for diagnostic task while significantly reducing the risk of patient re-identification. This approach enables secure data sharing and model training in privacy-sensitive domains such as medical imaging.

Förderung

  • Ministry of Economic Development of the Russian Federation
  • Ivannikov Institute for System Programming of the Russian Academy of Sciences

Zitieren

APA

Shodiev, D., Ushakov, E., Litvinov, A., & Markin, Y. (2025). Privacy-Preserving Synthetic Mammograms: A Generative Model Approach to Privacy-Preserving Breast Imaging Datasets. Informatics, 12(4), 112. https://doi.org/10.3390/informatics12040112

Vancouver

Shodiev D, Ushakov E, Litvinov A, Markin Y. Privacy-Preserving Synthetic Mammograms: A Generative Model Approach to Privacy-Preserving Breast Imaging Datasets. Informatics. 2025;12(4):112. doi:10.3390/informatics12040112

BibTeX
@article{Shodiev2025,
  author = {Shodiev, Damir and Ushakov, Egor and Litvinov, Arsenii and Markin, Yury},
  title = {Privacy-Preserving Synthetic Mammograms: A Generative Model Approach to Privacy-Preserving Breast Imaging Datasets},
  journal = {Informatics},
  year = {2025},
  volume = {12},
  number = {4},
  pages = {112},
  doi = {10.3390/informatics12040112}
}
Kostenlos starten →