VWV-SSL: Carotid vessel-wall-volume segmentation via sequence structural similarity and augmentation consistency-based self-supervised learning.
Authors
Abstract
Vessel wall volume (VWV) is a critical three dimensional ultrasound metric used to assess the progression and regression of carotid atherosclerosis. Ac curate measurement of VWV requires the segmentation of the media-adventitia boundary (MAB) and the lumen intima boundary (LIB) of the carotid arteries. Although deep learning methods can automatically segment the MAB and LIB and quantify VWV, they rely heavily on a large dataset with annotated images for training, which is time consuming and labor-intensive. Self-supervised learning (SSL) provides a possible solution to this challenge. However, existing SSL methods do not consider the similarities in the image sequences of 3D ultrasound. This paper proposes a novel SSL algorithm, named VWV-SSL, for 3D carotid ultrasound (3DUS) image segmentation to generate VWV measurement. VWV-SSL utilizes the sequence structural similarity and strong-weak augmented feature consistency of carotid ultrasound images to conduct the self-supervised task, which enables the networks to better learn the feature presentations of the vessel in the self-supervised task training. We applied VWV-SSL on the widely used 3D U-Net and evaluated it on 1158 3D US (579 of the common carotid artery and 579 of the bifurcation) from250subjects.Comparedtobaselinenetworks,our SSL method showed a significant improvement in segmentation performance when trained on a small number of labeled images (n = 15, 45 and 75 subjects). Moreover, the performance of VWV-SSL was superior to that of state-of-art SSL algorithms. These results indicate that our method can improve the performance of 3D U-Net when trained on a small number of labeled images, suggesting that VWV SSL could be applied in clinical practice to monitor the progression of atherosclerosis.