Fast Vessel Segmentation and Tracking in Ultra High-Frequency Ultrasound Images

TL;DR

This paper presents a fast, GPU-based method for real-time segmentation and tracking of deformable vessels in ultra high-frequency ultrasound images, enabling detailed vessel analysis in medical diagnostics.

Contribution

It introduces the first rapid algorithm for vessel segmentation and tracking in 2D UHFUS images, combining local phase analysis, level set, and EKF, validated on diverse datasets.

Findings

First to rapidly segment and track vessels in 2D UHFUS images.

Achieves highest speed and accuracy in 2D HFUS images.

Validated on 40 datasets including hand vessels.

Abstract

Ultra High Frequency Ultrasound (UHFUS) enables the visualization of highly deformable small and medium vessels in the hand. Intricate vessel-based measurements, such as intimal wall thickness and vessel wall compliance, require sub-millimeter vessel tracking between B-scans. Our fast GPU-based approach combines the advantages of local phase analysis, a distance-regularized level set, and an Extended Kalman Filter (EKF), to rapidly segment and track the deforming vessel contour. We validated on 35 UHFUS sequences of vessels in the hand, and we show the transferability of the approach to 5 more diverse datasets acquired by a traditional High Frequency Ultrasound (HFUS) machine. To the best of our knowledge, this is the first algorithm capable of rapidly segmenting and tracking deformable vessel contours in 2D UHFUS images. It is also the fastest and most accurate system for 2D HFUS images.