Automatic Needle Detection and Tracking in 3D Ultrasound Using an ROI-Based RANSAC and Kalman Method

Abstract

This article proposes a robust technique for needle detection and tracking using three-dimensional ultrasound (3D US). It is difficult for radiologists to detect and follow the position of micro tools, such as biopsy needles, that are inserted in human tissues under 3D US guidance. To overcome this difficulty, we propose a method that automatically reduces the processed volume to a limited region of interest (ROI), increasing at the same time the calculation speed and the robustness of the proposed technique. First, a line filter method that enhances the contrast of the needle against the background is used to facilitate the initialization of ROI using the tubularness information of the complete US volume. Then, the random sample consensus (RANSAC) and Kalman filter (RK) algorithm is used in the ROI to detect and track the precise position of the needle. A series of numerical inhomogeneous phantoms with a needle simulated from real 3D US volumes are used to evaluate our method. The results show that the proposed method is much more robust than the RANSAC algorithm when detecting the needle, regardless of whether or not the insertion axis corresponds to an acquisition plane in the 3D US volume. The possibility of failure is also discussed in this article.

Medical Instrument Detection in 3-Dimensional Ultrasound Data Volumes

“…Therefore, it is proposed to fit a model of the instrument by means of RANdom SAmple Consecsus (RANSAC), which enables also a realtime performance on a GPU [37]. Furthermore, processing only in the region of interest and tracking over time is shown to limit the computational complexity and increase robustness in phantom data [38]. Nevertheless, arbitrary movements of the transducer and subject must be avoided for a successful tracking.…”

Assistive technology for ultrasound-guided central venous catheter placement

“…Comparison of the three methods was conducted in Ref. [70], and the results show that RANSAC is faster and more robust than the other two methods.…”

“…[63], where RANSAC was coupled with Gabor filters to produce a more accurate needle localization, and Ref. [70], where a region-of-interest based approach was implemented using a Kalman filter to reduce the amount of data to be processed and hence speed up the localization process. Although RANSAC can robustly localize the needle in an ultrasound image, one disadvantage of the method is that it does not have an upper bound on the iterations to be performed before producing an optimal solution; stopping the iterative process early may yield solutions that are not optimal.…”

Acoustically Active Catheter for Intracardiac Navigation by Color Doppler Ultrasonography

“…Other investigators (Armstrong et al, 2001; Fronheiser et al, 2008) visualized biopsy needles in color Doppler images through mechanical vibrations induced by a piezoelectric element placed at the needle base and producing a Doppler shift. A third group of approaches benefits from ultrasound signal or image filtering and enhancement, such as in automatic needle detection and tracking in 3-dimensional ultrasound images (Zhao et al, 2013). Ultrasonic needle tracking through coded excitation of the transmitted navigation signal has been proposed recently (Xia et al, 2016) and has a promise of considerably increasing the signal-to-noise ratio for needle detection in B-mode images.…”