EUVIMEDEUVIMED entdecken
Crossref

BronchoGAN: anatomically consistent and domain-agnostic image-to-image translation for video bronchoscopy

Ahmad Soliman, Ron Keuth, Marian Himstedt

International Journal of Computer Assisted Radiology and Surgery · 2025

DOI: 10.1007/s11548-025-03450-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Ahmad Soliman und 2 weiteren Autor:innen. Beteiligte Einrichtung: Medical Informatics, University of Lübeck, Ratzeburger Allee 160, 23562, Lübeck, Germany. Hauptthemen laut MEDLINE: Bronchoscopy, Bronchi, Image Processing, Computer-Assisted. Die Arbeit nennt 34 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The limited availability of bronchoscopy images makes image synthesis particularly interesting for training deep learning models. Robust image translation across different domains-virtual bronchoscopy, phantom as well as in vivo and ex vivo image data-is pivotal for clinical applications.

Methods

This paper proposes BronchoGAN introducing anatomical constraints for image-to-image translation being integrated into a conditional GAN. In particular, we force bronchial orifices to match across input and output images. We further propose to use foundation model-generated depth images as intermediate representation ensuring robustness across a variety of input domains establishing models with substantially less reliance on individual training datasets. Moreover, our intermediate depth image representation allows to easily construct paired image data for training.

Results

Our experiments showed that input images from different domains (e.g., virtual bronchoscopy, phantoms) can be successfully translated to images mimicking realistic human airway appearance. We demonstrated that anatomical settings (i.e., bronchial orifices) can be robustly preserved with our approach which is shown qualitatively and quantitatively by means of improved FID, SSIM and dice coefficients scores. Our anatomical constraints enabled an improvement in the Dice coefficient of up to 0.43 for synthetic images.

Conclusion

Through foundation models for intermediate depth representations and bronchial orifice segmentation integrated as anatomical constraints into conditional GANs, we are able to robustly translate images from different bronchoscopy input domains. BronchoGAN allows to incorporate public CT scan data (virtual bronchoscopy) in order to generate large-scale bronchoscopy image datasets with realistic appearance. BronchoGAN enables to bridge the gap of missing public bronchoscopy images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BronchoscopyBronchiImage Processing, Computer-AssistedHumansPhantoms, ImagingDeep Learning

Stichwörter der Autor:innen

Depth estimationImage-guided navigationSegmentationVideo bronchoscopy

Autor:innen und Institutionen

  • Medical Informatics, University of Lübeck, Ratzeburger Allee 160, 23562, Lübeck, Germany.
  • Faculty of Electrical Engineering and Computer Science, University of Technology Lübeck, Mönkhofer Weg 239, 23909, Lübeck, Germany. marian.himstedt@th-luebeck.de.

Zitieren

APA

Soliman, A., Keuth, R., & Himstedt, M. (2025). BronchoGAN: anatomically consistent and domain-agnostic image-to-image translation for video bronchoscopy. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03450-w

Vancouver

Soliman A, Keuth R, Himstedt M. BronchoGAN: anatomically consistent and domain-agnostic image-to-image translation for video bronchoscopy. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03450-w

BibTeX
@article{Soliman2025,
  author = {Soliman, Ahmad and Keuth, Ron and Himstedt, Marian},
  title = {BronchoGAN: anatomically consistent and domain-agnostic image-to-image translation for video bronchoscopy},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2025},
  doi = {10.1007/s11548-025-03450-w}
}
Kostenlos starten →