Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation

TL;DR

This paper introduces a novel label adversarial learning framework that enables adjustable vessel segmentation in OCTA images, balancing topology and caliber information for improved accuracy and uncertainty estimation.

Contribution

The proposed LAL method uniquely combines adversarial loss and an adjustment layer to produce continuous, tunable vessel segmentation between skeleton-level and pixel-level details.

Findings

Outperforms manual annotations and conventional filtering methods.

Enables generation of uncertainty maps for weak vessel boundaries.

Achieves continuous and adjustable vessel segmentation.

Abstract

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.