Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces VAMAE, a vessel-aware masked autoencoder framework for self-supervised pretraining on OCTA images. It uses anatomically informed masking based on vesselness and skeleton cues to emphasize vessel-rich regions, and reconstructs multiple complementary targets to capture appearance, structure, and topology. Experiments on the OCTA-500 benchmark for vessel segmentation show that VAMAE outperforms standard masked autoencoding, especially with limited labels.
By intelligently masking and reconstructing OCTA images, VAMAE learns vascular geometry so well it beats standard masked autoencoders, especially when labeled data is scarce.
Optical coherence tomography angiography (OCTA) provides non-invasive visualization of retinal microvasculature, but learning robust representations remains challenging due to sparse vessel structures and strong topological constraints. Many existing self-supervised learning approaches, including masked autoencoders, are primarily designed for dense natural images and rely on uniform masking and pixel-level reconstruction, which may inadequately capture vascular geometry. We propose VAMAE, a vessel-aware masked autoencoding framework for self-supervised pretraining on OCTA images. The approach incorporates anatomically informed masking that emphasizes vessel-rich regions using vesselness and skeleton-based cues, encouraging the model to focus on vascular connectivity and branching patterns. In addition, the pretraining objective includes reconstructing multiple complementary targets, enabling the model to capture appearance, structural, and topological information. We evaluate the proposed pretraining strategy on the OCTA-500 benchmark for several vessel segmentation tasks under varying levels of supervision. The results indicate that vessel-aware masking and multi-target reconstruction provide consistent improvements over standard masked autoencoding baselines, particularly in limited-label settings, suggesting the potential of geometry-aware self-supervised learning for OCTA analysis.