EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

3D-StyleGAN2-ADA: Volumetric Synthesis of Realistic Prostate T2W MRI

Claudia Giardina iD, Verónica Vilaplana iD

Journal of Imaging · 14.03.2026 · 12 (3) · 130

DOI: 10.3390/jimaging12030130 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 14.03.2026. Verfasst von Claudia Giardina und 1 weiteren Autor:innen. Beteiligte Einrichtung: Signal Theory and Communications, Universitat Politècnica de Catalunya-BarcelonaTech (UPC), 08034 Barcelona, Spain. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FPI-Ministerio, Spain, Horizon Europe Framework Programme, Agencia Estatal de Investigación.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work investigates the extension of StyleGAN2-ADA to three-dimensional prostate T2-weighted (T2W) MRI generation. The architecture is adapted to operate on 3D anisotropic volumes, enabling stable training at a clinically relevant resolution of 256×256×24, where a baseline 3D-StyleGAN fails to converge. Quantitative evaluation using Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and generative Precision–Recall metrics demonstrates substantial improvements over a 3D-StyleGAN baseline. Specifically, FID decreased from 114.2 to 27.3, while generative Precision increased from 0.22 to 0.82, indicating markedly improved fidelity and alignment with the real data distribution. Beyond generative metrics, the synthetic volumes were evaluated through radiomic feature analysis and downstream prostate segmentation. Synthetic data augmentation resulted in segmentation performance comparable to real-data training, supporting that volumetric generation preserves anatomically relevant structures, while multivariate radiomic analyses showed strong global feature alignment between real and synthetic volumes. These findings indicate that a 3D extension of StyleGAN2-ADA enables stable high-resolution volumetric prostate MRI synthesis while preserving anatomically coherent structure and global radiomic characteristics.

Schlagwörter

Stichwörter der Autor:innen

3D-StyleGAN2-ADAMRI augmentationgenerative adversarial networkmedical image synthesisprostate MRIprostate cancer

Autor:innen und Institutionen

  • Signal Theory and Communications, Universitat Politècnica de Catalunya-BarcelonaTech (UPC), 08034 Barcelona, Spain.

ORCID-Profile: Claudia Giardina, Verónica Vilaplana

Förderung

  • FPI-Ministerio, Spain
  • Horizon Europe Framework Programme
  • Agencia Estatal de Investigación

Zitieren

APA

Giardina, C., & Vilaplana, V. (2026). 3D-StyleGAN2-ADA: Volumetric Synthesis of Realistic Prostate T2W MRI. Journal of Imaging, 12(3), 130. https://doi.org/10.3390/jimaging12030130

Vancouver

Giardina C, Vilaplana V. 3D-StyleGAN2-ADA: Volumetric Synthesis of Realistic Prostate T2W MRI. Journal of Imaging. 2026;12(3):130. doi:10.3390/jimaging12030130

BibTeX
@article{Giardina2026,
  author = {Giardina, Claudia and Vilaplana, Verónica},
  title = {3D-StyleGAN2-ADA: Volumetric Synthesis of Realistic Prostate T2W MRI},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {3},
  pages = {130},
  doi = {10.3390/jimaging12030130}
}
Kostenlos starten →