No abstract

No 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.

No abstract

Real-time needle segmentation and tracking is very important in image-guided surgery, biopsy, and therapy. Due to its robustness to the addition of extraneous noise, the Hough Transform is one of the most powerful line-detection techniques nowadays and has been widely used in different areas. Unfortunately, its high computation needs often prevent it from being applied in real-time applications without the help of specially designed hardware. In order to solve this problem, a variety of fast implementation algorithms have been proposed. However, none of them can be performed in a real time on an affordable computer. In this paper, we describe a fast implementation of the Hough Transform based on coarse-fine search and the determination of the optimal image resolution. Compared to conventional techniques, our approach decreases the time for needle segmentation by an order of magnitude. Experiments with agar phantom and patient breast biopsy ultrasound (US) image sequences showed that our approach can segment the biopsy needle in real time (i.e., less than 33 ms) on an affordable PC computer without the help of specially designed hardware with the angular rms error of about 1 degrees and the position rms error of about 0.5 mm.

PurposeQuantification of carotid plaques has been shown to be important for assessing as well as monitoring the progression and regression of carotid atherosclerosis. Various metrics have been proposed and methods of measurements ranging from manual tracing to automated segmentations have also been investigated. Of those metrics, quantification of carotid plaques by measuring vessel‐wall‐volume (VWV) using the segmented media‐adventitia (MAB) and lumen‐intima (LIB) boundaries has been shown to be sensitive to temporal changes in carotid plaque burden. Thus, semi‐automatic MAB and LIB segmentation methods are required to help generate VWV measurements with high accuracy and less user interaction.MethodsIn this paper, we propose a semiautomatic segmentation method based on deep learning to segment the MAB and LIB from carotid three‐dimensional ultrasound (3DUS) images. For the MAB segmentation, we convert the segmentation problem to a pixel‐by‐pixel classification problem. A dynamic convolutional neural network (Dynamic CNN) is proposed to classify the patches generated by sliding a window along the norm line of the initial contour where the CNN model is fine‐tuned dynamically in each test task. The LIB is segmented by applying a region‐of‐interest of carotid images to a U‐Net model, which allows the network to be trained end‐to‐end for pixel‐wise classification.ResultsA total of 144 3DUS images were used in this development, and a threefold cross‐validation technique was used for evaluation of the proposed algorithm. The proposed algorithm‐generated accuracy was significantly higher than the previous methods but with less user interactions. Comparing the algorithm segmentation results with manual segmentations by an expert showed that the average Dice similarity coefficients (DSC) were 96.46 ± 2.22% and 92.84 ± 4.46% for the MAB and LIB, respectively, while only an average of 34 s (vs 1.13, 2.8 and 4.4 min in previous methods) was required to segment a 3DUS image. The interobserver experiment indicated that the DSC was 96.14 ± 1.87% between algorithm‐generated MAB contours of two observers' initialization.ConclusionsOur results showed that the proposed carotid plaque segmentation method obtains high accuracy and repeatability with less user interactions, suggesting that the method could be used in clinical practice to measure VWV and monitor the progression and regression of carotid plaques.

In this article a new slice-based 3D prostate segmentation method based on a continuity constraint, implemented as an autoregressive (AR) model is described. In order to decrease the propagated segmentation error produced by the slice-based 3D segmentation method, a continuity constraint was imposed in the prostate segmentation algorithm. A 3D ultrasound image was segmented using the slice-based segmentation method. Then, a cross-sectional profile of the resulting contours was obtained by intersecting the 2D segmented contours with a coronal plane passing through the midpoint of the manually identified rotational axis, which is considered to be the approximate center of the prostate. On the coronal cross-sectional plane, these intersections form a set of radial lines directed from the center of the prostate. The lengths of these radial lines were smoothed using an AR model. Slice-based 3D segmentations were performed in the clockwise and in the anticlockwise directions, where clockwise and anticlockwise are defined with respect to the propagation directions on the coronal view. This resulted in two different segmentations for each 2D slice. For each pair of unmatched segments, in which the distance between the contour generated clockwise and that generated anticlockwise was greater than 4 mm, a method was used to select the optimal contour. Experiments performed using 3D prostate ultrasound images of nine patients demonstrated that the proposed method produced accurate 3D prostate boundaries without manual editing. The average distance between the proposed method and manual segmentation was 1.29 mm. The average intraobserver coefficient of variation (i.e., the standard deviation divided by the average volume) of the boundaries segmented by the proposed method was 1.6%. The average segmentation time of a 352 x 379 x 704 image on a Pentium IV 2.8 GHz PC was 10 s.

No abstract