EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Refining Retinal Vessel Segmentation with Conditional Diffusion Models: A Controlled Evaluation on LU-Net+RA Probability Maps

Babak Bayanian, Hanieh Naderi, Chinthaka Dinesh

Journal of Imaging · 06.11.2026 · 12 (11) · 558

DOI: 10.3390/jimaging12110558 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 06.11.2026. Verfasst von Babak Bayanian und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinal vessel segmentation remains difficult along thin, low-contrast branches. We evaluate a conditional diffusion refiner for probability maps from a lightweight U-Net with reverse attention (LU-Net+RA). A frozen mask autoencoder produces a spatially downsampled multi-channel grid; a global RGB embedding conditions denoising diffusion implicit model (DDIM) updates, followed by frozen decoding. The refiner adds 527,233 parameters to the 1,946,961-parameter backbone. Matched evaluation on CHASE-DB1, DRIVE and HRF uses five training seeds and five sampling seeds. Refined mean Dice was 0.746, 0.790 and 0.666, against coarse values of 0.811, 0.792 and 0.732. Exploratory paired intervals exclude zero in the negative direction. Conditioning variants changed Dice by less than 0.0002. Deterministic encoded-grid refinement and autoencoder fine-tuning narrowed the gap but exceeded the baseline only on DRIVE; spatial residual refinement changed Dice by −0.0001, +0.0058 and +0.0074. Matched out-of-fold training did not establish absence of input shift. Increasing DDIM updates from 50 to 100 doubled refinement time with negligible observed Dice change. An earlier single-run result was not reproduced. Under this controlled protocol, diffusion refinement did not improve LU-Net+RA.

Zitieren

APA

Bayanian, B., Naderi, H., & Dinesh, C. (2026). Refining Retinal Vessel Segmentation with Conditional Diffusion Models: A Controlled Evaluation on LU-Net+RA Probability Maps. Journal of Imaging, 12(11), 558. https://doi.org/10.3390/jimaging12110558

Vancouver

Bayanian B, Naderi H, Dinesh C. Refining Retinal Vessel Segmentation with Conditional Diffusion Models: A Controlled Evaluation on LU-Net+RA Probability Maps. Journal of Imaging. 2026;12(11):558. doi:10.3390/jimaging12110558

BibTeX
@article{Bayanian2026,
  author = {Bayanian, Babak and Naderi, Hanieh and Dinesh, Chinthaka},
  title = {Refining Retinal Vessel Segmentation with Conditional Diffusion Models: A Controlled Evaluation on LU-Net+RA Probability Maps},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {11},
  pages = {558},
  doi = {10.3390/jimaging12110558}
}
Kostenlos starten →