U-Net Optimization for Hyperreflective Foci Segmentation in Retinal OCT
Diagnostics · 13.03.2026 · 16 (6) · 853
DOI: 10.3390/diagnostics16060853 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 13.03.2026. Verfasst von Pavithra Kodiyalbail Chakrapani und 6 weiteren Autor:innen. Beteiligte Einrichtung: Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Hyperreflective foci (HRF) are supportive optical coherence tomography (OCT) imaging biomarkers that have been examined for their association with disease progression and severity in various retinal disorders. The accurate identification and segmentation of these tiny structures of lipid extravasation remain complicated because of their small size, class imbalance, similarity in the reflectivity patterns with the surrounding structures and imaging artifacts. While U-Net-based models have promised exceptional results for medical image segmentation, optimal architectural settings and suitable preprocessing methods for HRF detection remain unclear.
Methods
This research assessed optimal settings for U-Net-based models for HRF segmentation by evaluating standard U-Net and attention U-Net under different preprocessing regimes. Attention U-Net employed Z-score normalization and contrast-limited adaptive histogram equalization (CLAHE) enhancement with soft dice loss. The standard U-Net was trained on OCT images with CLAHE using focal Tversky loss. A total of 435 fovea-centered OCT B scans with the corresponding, consensus-annotated HRF masks were utilized for this research.
Results
The standard U-Net outperformed attention U-Net with a dice score of 0.5207, an AUC of 0.8411, and a recall of 0.6439 on raw OCT images. The attention U-Net with preprocessing (dice: 0.5033, AUC: 0.6987, recall: 0.5391) demonstrated satisfactory performance. The results showed that the U-Net model with CLAHE and focal Tversky loss improved recall by 19.4% relative to the attention U-Net, and this corresponds roughly to a 23% relative decline in false negatives. This indicates increased sensitivity in identifying HRF regions.
Conclusions
The best-performing configuration using U-Net-based architectures for segmentation of HRFs combines the standard U-Net model with CLAHE and focal Tversky loss for handling class imbalance. This approach yields relatively higher sensitivity, indicating that the standard U-Net model delivers a simple and robust framework for automated HRF segmentation on the evaluated dataset, promising further validation in broader clinical datasets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India.
- Department of Ophthalmology, Kasturba Medical College, Manipal Academy of Higher Education, Manipal 576104, India.
- Department of Computer Science, Design and Journalism, Creighton University, Omaha, NE 68187, USA.
ORCID-Profile: Pavithra Kodiyalbail Chakrapani, Preetham Kumar, Sulatha Venkataraya Bhandary, Geetha Maiya, Shailaja Shenoy, Steven Fernandes, Prakhar Choudhary
Zitieren
APA
Kodiyalbail Chakrapani, P., Kumar, P., Bhandary, S. V., Maiya, G., Shenoy, S., Fernandes, S., & Choudhary, P. (2026). U-Net Optimization for Hyperreflective Foci Segmentation in Retinal OCT. Diagnostics, 16(6), 853. https://doi.org/10.3390/diagnostics16060853
Vancouver
Kodiyalbail Chakrapani P, Kumar P, Bhandary SV, Maiya G, Shenoy S, Fernandes S, et al. U-Net Optimization for Hyperreflective Foci Segmentation in Retinal OCT. Diagnostics. 2026;16(6):853. doi:10.3390/diagnostics16060853
BibTeX
@article{KodiyalbailChakrapani2026,
author = {Kodiyalbail Chakrapani, Pavithra and Kumar, Preetham and Bhandary, Sulatha Venkataraya and Maiya, Geetha and Shenoy, Shailaja and Fernandes, Steven and Choudhary, Prakhar},
title = {U-Net Optimization for Hyperreflective Foci Segmentation in Retinal OCT},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {6},
pages = {853},
doi = {10.3390/diagnostics16060853}
}
EUVIMED