Multi-scale tubular structure detection in ultrasound imaging.

We propose a novel, physics-based method for detecting multi-scale tubular features in ultrasound images. The detector is based on a Hessian-matrix eigenvalue method, but unlike previous work, our detector is guided by an optimal model of vessel-like structures with respect to the ultrasound-image formation process. Our method provides a voxel-wise probability map, along with estimates of the radii and orientations of the detected tubes. These results can then be used for further processing, including segmentation and enhanced volume visualization. Most Hessian-based algorithms, including the well-known Frangi filter, were developed for CTA or MRA; they implicitly assume symmetry about the vessel centerline. This is not consistent with ultrasound data. We overcome this limitation by introducing a novel filter that allows multi-scale estimation both with respect to the vessel's centerline and with respect to the vessel's border. We use manually-segmented ultrasound imagery from 35 patients to show that our method is superior to standard Hessian-based methods. We evaluate the performance of the proposed methods based on the sensitivity and specificity like measures, and finally demonstrate further applicability of our method to vascular ultrasound images of the carotid artery, as well as ultrasound data for abdominal aortic aneurysms.

Frangi goes US: multiscale tubular structure detection adapted to 3D ultrasound.

We propose a Hessian matrix based multiscale tubular structure detection (TSD) algorithm adapted to 3D B-mode vascular US images. The algorithm is designed to highlight blood vessel centerline points and yield an estimate of the cross-section radius at each centerline point. It can be combined with a simple centerline extraction scheme, yielding precise, fast and fully automatic lumen segmentation initializations. TSD algorithms designed with CTA and MRA datasets in mind, e.g., the Frangi filter, are not capable of reliably distinguishing centerline points from other points in vascular US datasets, since some assumptions underlying these algorithms are not reasonable for US datasets. The algorithm we propose, does not have these shortcomings and performs significantly better on vascular US datasets. We propose a statistic to evaluate how well a TSD algorithm is able to distinguish centerline points from other points. Based on this statistic, we compare the Frangi Filter to various versions of our new algorithm, on 11 3D US carotid datasets.