Automated catheter detection in volumetric ultrasound

Ultrasound guided catheter insertion is a common procedure in current clinical practice, but it requires a skilled ultrasound practitioner to correctly acquire the images so that the catheter and tip are well visualized. Automated detection of the catheter location in ultrasound images can help in procedural guidance as well as surveillance of catheter position post placement, especially when the ultrasound imaging is being performed by a non-sonographer. Accurate and fast localization of the catheter is a very challenging task because of the poor observability of the catheter in ultrasound images. In this paper, we present a novel algorithm for fast catheter detection in 3D ultrasound images. We begin by generating a catheter-likelihood map using a physical model of the catheter. For fast detection, we perform a greedy optimization, where the likelihood map is projected onto a single image plane using a variation on the maximum-intensity-projection approach. The highest likelihood curves on this plane then help us to determine the curved planes on which the catheter may be located. The potential catheter locations are then detected on these curved planes. We finally apply some post-processing to enable robust detection of the catheter. We illustrate the performance of our proposed method through quantitative comparisons with expert annotations as well as qualitative results on 26 images obtained from 7 subjects (of which 15 are with and 11 are without a catheter).