C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation

TL;DR

C-DARL is a self-supervised, contrastive diffusion adversarial learning model that improves blood vessel segmentation accuracy across various medical imaging modalities without requiring manual annotations.

Contribution

The paper introduces a novel self-supervised framework combining diffusion, adversarial, and contrastive learning for vessel segmentation, reducing reliance on manual labels.

Findings

Outperforms baseline methods in vessel segmentation accuracy.

Demonstrates robustness to noise across multiple datasets.

Effective across diverse imaging modalities.

Abstract

Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.