Automatic needle segmentation in three-dimensional ultrasound images using two orthogonal two-dimensional image projections

Abstract

In this paper, we describe an algorithm to segment a needle from a three-dimensional (3D) ultrasound image by using two orthogonal two-dimensional (2D) image projections. Not only is the needle more conspicuous in a projected (volume-rendered) image, but its direction in 3D lies in the plane defined by the projection direction and the needle direction in the projected 2D image. Hence, using two such projections, the 3D vector describing the needle direction lies along the intersection of the two corresponding planes. Thus, the task of 3D needle segmentation is reduced to two 2D needle segmentations. For improved accuracy and robustness, we use orthogonal projection directions (both orthogonal to a given a priori estimate of the needle direction), and use volume cropping and Gaussian transfer functions to remove complex background from the 2D projection images. To evaluate our algorithm, we tested it with 3D ultrasound images of agar and turkey breast phantoms. Using a 500 MHz personal computer equipped with a commercial volume-rendering card, we found that our 3D needle segmentation algorithm performed in near real time (about 10 fps) with a root-mean-square accuracy in needle length and endpoint coordinates of better than 0.8 mm, and about 0.5 mm on average, for needles lengths in the 3D image from 4.0 mm to 36.7 mm.

Projection-Based Needle Segmentation in 3D Ultrasound Images

“…The cropped 3D US image is then volume rendered using ray casting along the initial projection direction with a Gaussian transfer functions described by Eq. (3) in Ref [7] and a projected 2D US image, called the first projected image, is obtained. In the first projected image, we used a 2D needle segmentation technique, such as the flood-filling-based 2D US image segmentation method [7] or the real-time Hough transform technique described in Ref.…”

“…(3) in Ref [7] and a projected 2D US image, called the first projected image, is obtained. In the first projected image, we used a 2D needle segmentation technique, such as the flood-filling-based 2D US image segmentation method [7] or the real-time Hough transform technique described in Ref. [14] to segment the needle.…”

“…First, The 3D US image containing the needle is cropped using a priori knowledge of the approximate needle direction and entrance points. [7] Then, a direction perpendicular to the approximate needle direction is chosen as the initial projection direction. The cropped 3D US image is then volume rendered using ray casting along the initial projection direction with a Gaussian transfer functions described by Eq.…”

“…[6] and [7] to develop a new 3D needle segmentation technique that is more accurate and robust, especially when a correct 2D needle segmentation in the 2D US images cannot be ensured. …”

“…In order to avoid such problems, we further developed a fast 3D needle segmentation based on using two orthogonal two-dimensional image projections in Ref. [7].…”