Generalized Retinal Artery/Vein Segmentation via Multi-Dataset Fine-Tuning and Pathology Subgroup Analysis
Bioengineering · 30.07.2026 · 13 (8) · 882
DOI: 10.3390/bioengineering13080882 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 30.07.2026. Verfasst von Seo Gyeong Lee und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical IT Engineering, Konyang University, 158 Gwanjeodong-ro, Seo-gu, Daejeon 35365, Republic of Korea. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Daejeon RISE.
Abstract (Originalsprache)
Background
Automatic artery/vein (A/V) segmentation in color fundus photography underpins retinal biomarkers such as the arteriolar-to-venular ratio (AVR), yet single-dataset models generalize poorly across institutions and pathologies.
Methods
Using pre-trained Recursive Refinement W-Net (RRWNet) weights as initialization, eight heterogeneous datasets were jointly fine-tuned under a single set of weights for 50 epochs: five A/V-labeled (Fundus-AVSeg, LES-AV, RITE, FIREFLY-Gen, PSEUDO_AV) and three vessel-only (DRIVE, CHASE_DB1, HRF). A vessel-only loss separation strategy applied only the vessel-channel loss to vessel-only datasets, preventing A/V metric dilution; post-processing combined field-of-view masking, connected-component denoising, and morphological refinement, outputting artery, vein, and vessel masks with crossing and junction maps.
Results
Loss separation recovered validation DSC from 0.518 to 0.570 (AUC up to 0.959). On re-inference across four datasets (332 images), the single-weight model attained mean-AV DSC 0.657 ± 0.085 and AUC 0.976 ± 0.016; across normal, AMD, glaucoma, and DR subgroups, performance was statistically indistinguishable (Kruskal–Wallis, all p > 0.36), indicating consistent behavior across pathologies.
Conclusions
Within a leakage-aware internal evaluation, the single-weight model produced stable A/V segmentation across the four datasets and across pathology subgroups, indicating preliminary internal consistency rather than proven cross-domain generalization. Because the evaluation reuses data seen during training and no external or patient-level held-out set was used, robustness claims are deferred; leakage-free external validation and patient-level re-evaluation are identified as the essential next steps.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical IT Engineering, Konyang University, 158 Gwanjeodong-ro, Seo-gu, Daejeon 35365, Republic of Korea.
ORCID-Profile: Seo Gyeong Lee
Förderung
- Daejeon RISE
Zitieren
APA
Lee, S. G., & Han, J. H. (2026). Generalized Retinal Artery/Vein Segmentation via Multi-Dataset Fine-Tuning and Pathology Subgroup Analysis. Bioengineering, 13(8), 882. https://doi.org/10.3390/bioengineering13080882
Vancouver
Lee SG, Han JH. Generalized Retinal Artery/Vein Segmentation via Multi-Dataset Fine-Tuning and Pathology Subgroup Analysis. Bioengineering. 2026;13(8):882. doi:10.3390/bioengineering13080882
BibTeX
@article{Lee2026,
author = {Lee, Seo Gyeong and Han, Ju-Hyuck},
title = {Generalized Retinal Artery/Vein Segmentation via Multi-Dataset Fine-Tuning and Pathology Subgroup Analysis},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {8},
pages = {882},
doi = {10.3390/bioengineering13080882}
}
EUVIMED