Real-time needle tip localization in 2D ultrasound images for robotic biopsies

Kaya, Mert; Senel, Enes; Ahmad, Awais; Orhan, Orcun; Bebek, Özkan

doi:10.1109/icar.2015.7251432

Cited by 22 publications

(27 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…N is the total number of pixels in the I(w(x;p)) or T (x), and δ(a) is the dirac delta function. In the second stage, the marginal distribution of T (x); P T , is calculated using obtained the joint probability values in (10).…”

Section: B Visual Tracking Using Scvmentioning

confidence: 99%

“…During real-time needle tracking, the needle localization algorithm can fail, or misalignment can occur between the US image plane and the needle. In these instances, the Kalman filter cannot track the needle tip accurately [10].…”

Section: Introductionmentioning

confidence: 99%

“…Gabor filtered needle pixels were automatically binarized and the needle tip was estimated using a probability mapping method [9]. The needle tip estimation noise was smoothened with the Kalman filter and the needle localization algorithm was accelerated using bin packing method [10]. Also, the needle axis and its tip were localized in real-time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual tracking of biopsy needles in 2D ultrasound images

Kaya

Senel

Ahmad

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Due to copyright restrictions, the access to the full text of this article is only available via subscription.Ultrasound (US) is one the most commonly used medical imaging techniques in percutaneous needle procedures. However, US images are inherently noisy and contain excessive number of artifacts. Hence, it is not easy to track the needle tip in the US images during the needle insertions. At this point, image based visual tracking techniques can be used for needle tip tracking. This paper presents a method for visual tracking of biopsy needles in 2D US images using sum of squared differences and sum of conditional variances. Second order Gauss-Newton optimization is used to decrease processing time and make the tracking more robust. The needle template images used in the method are updated with a strategy to prevent needle loss and detection failures during tracking. The paper also explains how to identify needle losses during tracking and how to recover the needle position without using a needle localization algorithm. We demonstrate the precision of the visual needle tip tracking method with experiments under challenging tracking conditions.TÜBİTA

show abstract

Section: B Visual Tracking Using Scvmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual tracking of biopsy needles in 2D ultrasound images

Kaya

Senel

Ahmad

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to be autonomous, the system must be able to interact with its environment and behave accordingly. In our case, the needle must reach a target tissue that is a dynamic environment due to constantly changing position [19].…”

Section: Motion Compensationmentioning

confidence: 99%

“…The feedback of both the needle tip and the target from the US imaging is available, also shown in Figure 4. The image processing algorithm developed in [19,25] is used to get the position of both the needle tip and the moving target in real time. The error between the position of the target and the needle tip is sent to the OBR controller via the UDP connection as discussed in Section 3.…”

Section: Pd Controllermentioning

confidence: 99%

Ozyegin Biopsy Robot: System integration architecture and motion compensation of a moving target

Ahmad¹,

Bebek²

2018

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper presents the complete system architecture of a robotic biopsy system for real-time operations.The system has individual functional blocks working simultaneously including a 5 DoF parallel robot, ultrasound (US) imaging machine, two robotic manipulators, and a motion capturing system. Details of the real-time functionality of the robotic system components working with spatial and computational synchronization are presented. This paper also deals with a scenario in which the target tissue is moving due to the breathing of the patient. The motion of the needle tip and the target is tracked using US images as feedback. Two types of control laws for target tracking are discussed:traditional feedback control and an optimal control method. Motion compensation is demonstrated by tracking a moving target with the needle tip motion with an RMS error of 0.25 mm.

show abstract

Medical instrument detection in ultrasound: a review

Yang

Shan²,

Kolen³

et al. 2022

Artif Intell Rev

View full text Add to dashboard Cite

Medical instrument detection is essential for computer-assisted interventions, since it facilitates clinicians to find instruments efficiently with a better interpretation, thereby improving clinical outcomes. This article reviews image-based medical instrument detection methods for ultrasound-guided (US-guided) operations. Literature is selected based on an exhaustive search in different sources, including Google Scholar, PubMed, and Scopus. We first discuss the key clinical applications of medical instrument detection in the US, including delivering regional anesthesia, biopsy taking, prostate brachytherapy, and catheterization. Then, we present a comprehensive review of instrument detection methodologies, including non-machine-learning and machine-learning methods. The conventional non-machine-learning methods were extensively studied before the era of machine learning methods. The principal issues and potential research directions for future studies are summarized for the computer-assisted intervention community. In conclusion, although promising results have been obtained by the current (non-) machine learning methods for different clinical applications, thorough clinical validations are still required.

show abstract

Real-time needle tip localization in 2D ultrasound images for robotic biopsies

Cited by 22 publications

References 17 publications

Visual tracking of biopsy needles in 2D ultrasound images

Visual tracking of biopsy needles in 2D ultrasound images

Ozyegin Biopsy Robot: System integration architecture and motion compensation of a moving target

Medical instrument detection in ultrasound: a review

Contact Info

Product

Resources

About