Ultrasound segmentation based on statistical unit-root test of B-scan radial intensity profiles

Abstract

Delineation of the perimeter of hollow structures, such as veins and arteries, from ultrasound images is an important step in US-based medical interventions. A simple and efficient approach is proposed for edge detection in ultrasound images. The technique examines the radial edge profiles for unit root based on the Dickey-Fuller test. The existence of the unit root is a sign of a trend, and hence nonstationarity, in the statistics of the edge profile. The method is applied to simulated data and clinical images of human arteries and veins. The outcomes are validated based on the average of the Hausdorff distance between the automatically derived vessel contours and vessel contours marked by five experts. The proposed edge detection method provides accurate segmentations (average Hausdorff distance from expert segmentation of 1.5 mm in vessel images. and 0.4 mm in simulated data).