Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14654 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908840237203456 |
|---|---|
| author | Dubosc, Marius Fischer, Yann Auray, Zacharie Boutry, Nicolas Carlinet, Edwin Atlan, Michael Geraud, Thierry |
| author_facet | Dubosc, Marius Fischer, Yann Auray, Zacharie Boutry, Nicolas Carlinet, Edwin Atlan, Michael Geraud, Thierry |
| contents | Doppler holography is an emerging retinal imaging technique that captures the dynamic behavior of blood flow with high temporal resolution, enabling quantitative assessment of retinal hemodynamics. This requires accurate segmentation of retinal arteries and veins, but traditional segmentation methods focus solely on spatial information and overlook the temporal richness of holographic data. In this work, we propose a simple yet effective approach for artery-vein segmentation in temporal Doppler holograms using standard segmentation architectures. By incorporating features derived from a dedicated pulse analysis pipeline, our method allows conventional U-Nets to exploit temporal dynamics and achieve performance comparable to more complex attention- or iteration-based models. These findings demonstrate that time-resolved preprocessing can unlock the full potential of deep learning for Doppler holography, opening new perspectives for quantitative exploration of retinal hemodynamics. The dataset is publicly available at https://huggingface.co/datasets/DigitalHolography/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14654 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving segmentation of retinal arteries and veins using cardiac signal in doppler holograms Dubosc, Marius Fischer, Yann Auray, Zacharie Boutry, Nicolas Carlinet, Edwin Atlan, Michael Geraud, Thierry Computer Vision and Pattern Recognition Artificial Intelligence Doppler holography is an emerging retinal imaging technique that captures the dynamic behavior of blood flow with high temporal resolution, enabling quantitative assessment of retinal hemodynamics. This requires accurate segmentation of retinal arteries and veins, but traditional segmentation methods focus solely on spatial information and overlook the temporal richness of holographic data. In this work, we propose a simple yet effective approach for artery-vein segmentation in temporal Doppler holograms using standard segmentation architectures. By incorporating features derived from a dedicated pulse analysis pipeline, our method allows conventional U-Nets to exploit temporal dynamics and achieve performance comparable to more complex attention- or iteration-based models. These findings demonstrate that time-resolved preprocessing can unlock the full potential of deep learning for Doppler holography, opening new perspectives for quantitative exploration of retinal hemodynamics. The dataset is publicly available at https://huggingface.co/datasets/DigitalHolography/ |
| title | Improving segmentation of retinal arteries and veins using cardiac signal in doppler holograms |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.14654 |