EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive 3D Augmentation in StyleGAN2-ADA for High-Fidelity Lung Nodule Synthesis from Limited CT Volumes

Oleksandr Fedoruk iD, Konrad Klimaszewski iD, Michał Kruk iD

Sensors · 2025

DOI: 10.3390/s25247404 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Oleksandr Fedoruk und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Technology, Warsaw University of Life Sciences, 02-776 Warsaw, Poland. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Imaging, Three-Dimensional, Lung, Lung Neoplasms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative adversarial networks (GANs) typically require large datasets for effective training, which poses challenges for volumetric medical imaging tasks where data are scarce. This study addresses this limitation by extending adaptive discriminator augmentation (ADA) for three-dimensional (3D) StyleGAN2 to improve generative performance on limited volumetric data. The proposed 3D StyleGAN2-ADA redefines all 2D operations for volumetric processing and incorporates the full set of original augmentation techniques. Experiments are conducted on the NoduleMNIST3D dataset of lung CT scans containing 590 voxel-based samples across two classes. Two augmentation pipelines are evaluated—one using color-based transformations and another employing a comprehensive set of 3D augmentations including geometric, filtering, and corruption augmentations. Performance is compared against the same network and dataset without any augmentations at all by assessing generation quality with Kernel Inception Distance (KID) and 3D Structural Similarity Index Measure (SSIM). Results show that volumetric ADA substantially improves training stability and reduces the risk of a mode collapse, even under severe data constraints. A strong augmentation strategy improves the realism of generated 3D samples and better preserves anatomical structures relative to those without data augmentation. These findings demonstrate that adaptive 3D augmentations effectively enable high-quality synthetic medical image generation from extremely limited volumetric datasets. The source code and the weights of the networks are available in the GitHub repository.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedImaging, Three-DimensionalLungLung NeoplasmsHumansAlgorithmsNeural Networks, ComputerImage Processing, Computer-Assisted

Stichwörter der Autor:innen

3D deep learningadaptive discriminator augmentation (ADA)computed tomography (CT)generative adversarial networks (GAN)lung nodulesmedical image synthesisvolumetric medical imaging

Autor:innen und Institutionen

  • Institute of Information Technology, Warsaw University of Life Sciences, 02-776 Warsaw, Poland.
  • Department of Complex Systems, National Centre for Nuclear Research, 05-400 Otwock, Poland.

ORCID-Profile: Oleksandr Fedoruk, Konrad Klimaszewski, Michał Kruk

Zitieren

APA

Fedoruk, O., Klimaszewski, K., & Kruk, M. (2025). Adaptive 3D Augmentation in StyleGAN2-ADA for High-Fidelity Lung Nodule Synthesis from Limited CT Volumes. Sensors. https://doi.org/10.3390/s25247404

Vancouver

Fedoruk O, Klimaszewski K, Kruk M. Adaptive 3D Augmentation in StyleGAN2-ADA for High-Fidelity Lung Nodule Synthesis from Limited CT Volumes. Sensors. 2025. doi:10.3390/s25247404

BibTeX
@article{Fedoruk2025,
  author = {Fedoruk, Oleksandr and Klimaszewski, Konrad and Kruk, Michał},
  title = {Adaptive 3D Augmentation in StyleGAN2-ADA for High-Fidelity Lung Nodule Synthesis from Limited CT Volumes},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25247404}
}
Kostenlos starten →