Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.01190 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916674577367040 |
|---|---|
| author | Fhima, Jonathan Van Eijgen, Jan Beeckmans, Lennert Jacobs, Thomas Freiman, Moti Nakayama, Luis Filipe Stalmans, Ingeborg Baskin, Chaim Behar, Joachim A. |
| author_facet | Fhima, Jonathan Van Eijgen, Jan Beeckmans, Lennert Jacobs, Thomas Freiman, Moti Nakayama, Luis Filipe Stalmans, Ingeborg Baskin, Chaim Behar, Joachim A. |
| contents | Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating controllable layout-aware images. RLAD conditions image generation on multiple key layout components extracted from real images, ensuring high structural fidelity while enabling diversity in other components. Applied to retinal fundus imaging, we augmented the training datasets by synthesizing paired retinal images and vessel segmentations conditioned on extracted blood vessels from real images, while varying other layout components such as lesions and the optic disc. Experiments demonstrated that RLAD-generated data improved generalization in retinal vessel segmentation by up to 8.1%. Furthermore, we present REYIA, a comprehensive dataset comprising 586 manually segmented retinal images. To foster reproducibility and drive innovation, both our code and dataset will be made publicly accessible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01190 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling Fhima, Jonathan Van Eijgen, Jan Beeckmans, Lennert Jacobs, Thomas Freiman, Moti Nakayama, Luis Filipe Stalmans, Ingeborg Baskin, Chaim Behar, Joachim A. Computer Vision and Pattern Recognition Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating controllable layout-aware images. RLAD conditions image generation on multiple key layout components extracted from real images, ensuring high structural fidelity while enabling diversity in other components. Applied to retinal fundus imaging, we augmented the training datasets by synthesizing paired retinal images and vessel segmentations conditioned on extracted blood vessels from real images, while varying other layout components such as lesions and the optic disc. Experiments demonstrated that RLAD-generated data improved generalization in retinal vessel segmentation by up to 8.1%. Furthermore, we present REYIA, a comprehensive dataset comprising 586 manually segmented retinal images. To foster reproducibility and drive innovation, both our code and dataset will be made publicly accessible. |
| title | Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01190 |