Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation
This work addresses a domain-specific problem in medical imaging for OCTA analysis, offering an incremental improvement by enabling adjustable segmentation with clear caliber and topology.
The paper tackles the challenge of microvessel segmentation in OCTA images by proposing a label adversarial learning method to bridge the gap between skeleton-level and pixel-level segmentation, achieving results that outperform manual annotations and conventional filtering effects.
You can have your cake and eat it too. Microvessel segmentation in optical coherence tomography angiography (OCTA) images remains challenging. Skeleton-level segmentation shows clear topology but without diameter information, while pixel-level segmentation shows a clear caliber but low topology. To close this gap, we propose a novel label adversarial learning (LAL) for skeleton-level to pixel-level adjustable vessel segmentation. LAL mainly consists of two designs: a label adversarial loss and an embeddable adjustment layer. The label adversarial loss establishes an adversarial relationship between the two label supervisions, while the adjustment layer adjusts the network parameters to match the different adversarial weights. Such a design can efficiently capture the variation between the two supervisions, making the segmentation continuous and tunable. This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology. Experimental results show that our results outperform manual annotations of current public datasets and conventional filtering effects. Furthermore, such a continuous process can also be used to generate an uncertainty map representing weak vessel boundaries and noise.