Projection-Based Phase Features for Localization of a Needle Tip in 2D Curvilinear Ultrasound

Hacihaliloglu, Ilker; Beigi, Parmida; Ng, Gary C.; Rohling, Robert; Salcudean, Septimiu E.; Abolmaesumi, Purang

doi:10.1007/978-3-319-24553-9_43

Cited by 17 publications

(43 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tip of the needle is determined by defining a region of interest (ROI) in the filtered, binarized image and determining the strongest edge in the deepest blob that is located at the needle axis. Hacihaliloglu et al [ 12 ] investigated the problem of localizing the needle in B-mode images acquired using a two-dimensional (2D) curvilinear ultrasound transducer. In fact, the visibility of the needle in curvilinear B-mode images is mainly limited to a portion of the needle that is orthogonal or nearly orthogonal to the ultrasound beams [ 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

“…Hacihaliloglu et al [ 12 ] investigated the problem of localizing the needle in B-mode images acquired using a two-dimensional (2D) curvilinear ultrasound transducer. In fact, the visibility of the needle in curvilinear B-mode images is mainly limited to a portion of the needle that is orthogonal or nearly orthogonal to the ultrasound beams [ 12 , 13 ]. The method by Hacihaliloglu et al [ 12 ] aimed to localize the needle axis and tip in curvilinear B-mode images by extending the visible part of the needle, which is assumed to be located at a specific region in the ultrasound image.…”

Section: Introductionmentioning

confidence: 99%

“…In fact, the visibility of the needle in curvilinear B-mode images is mainly limited to a portion of the needle that is orthogonal or nearly orthogonal to the ultrasound beams [ 12 , 13 ]. The method by Hacihaliloglu et al [ 12 ] aimed to localize the needle axis and tip in curvilinear B-mode images by extending the visible part of the needle, which is assumed to be located at a specific region in the ultrasound image. In particular, the region that includes the visible part of the needle is processed using projection-based local phase analysis and Radon transform to obtain an initial estimation of the needle axis and identify an approximate region that surrounds the needle axis.…”

Section: Introductionmentioning

confidence: 99%

“…The needle axis is estimated based on this region using local phase analysis, Radon transform and the MLESAC algorithm. Moreover, the needle tip is estimated using statistical analysis that is similar to the analysis employed in [ 12 ]. In fact, the assumptions employed by the needle localization methods in [ 12 , 14 ], which include the assumptions about the a priori known insertion location of the needle and the assumption about the location of the visible part of the needle, might limit their application in real-life clinical procedures.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, the needle tip is estimated using statistical analysis that is similar to the analysis employed in [ 12 ]. In fact, the assumptions employed by the needle localization methods in [ 12 , 14 ], which include the assumptions about the a priori known insertion location of the needle and the assumption about the location of the visible part of the needle, might limit their application in real-life clinical procedures. In general, the performance of the needle localization methods that are based on B-mode image analysis is affected by the visibility of the needle in the B-mode ultrasound image.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Accurate Needle Localization Using Two-Dimensional Power Doppler and B-Mode Ultrasound Image Analyses: A Feasibility Study

Daoud

Shtaiyat

Zayadeen

et al. 2018

Sensors

View full text Add to dashboard Cite

Curvilinear ultrasound transducers are commonly used in various needle insertion interventions, but localizing the needle in curvilinear ultrasound images is usually challenging. In this paper, a new method is proposed to localize the needle in curvilinear ultrasound images by exciting the needle using a piezoelectric buzzer and imaging the excited needle using a curvilinear ultrasound transducer to acquire a power Doppler image and a B-mode image. The needle-induced Doppler responses that appear in the power Doppler image are analyzed to estimate the needle axis initially and identify the candidate regions that are expected to include the needle. The candidate needle regions in the B-mode image are analyzed to improve the localization of the needle axis. The needle tip is determined by analyzing the intensity variations of the power Doppler and B-mode images around the needle axis. The proposed method is employed to localize different needles that are inserted in three ex vivo animal tissue types at various insertion angles, and the results demonstrate the capability of the method to achieve automatic, reliable and accurate needle localization. Furthermore, the proposed method outperformed two existing needle localization methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Accurate Needle Localization Using Two-Dimensional Power Doppler and B-Mode Ultrasound Image Analyses: A Feasibility Study

Daoud

Shtaiyat

Zayadeen

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

Reliable and accurate needle localization in curvilinear ultrasound images using signature‐based analysis of ultrasound beamformed radio frequency signals

2020

View full text Add to dashboard Cite

PurposeUltrasound imaging is used in many minimally invasive needle insertion procedures to track the advancing needle, but localizing the needle in ultrasound images can be challenging, particularly at steep insertion angles. Previous methods have been introduced to localize the needle in ultrasound images, but the majority of these methods are based on ultrasound B‐mode image analysis that is affected by the needle visibility. To address this limitation, we propose a two‐phase, signature‐based method to achieve reliable and accurate needle localization in curvilinear ultrasound images based on the beamformed radio frequency (RF) signals that are acquired using conventional ultrasound imaging systems.MethodsIn the first phase of our proposed method, the beamformed RF signals are divided into overlapping segments and these segments are processed to extract needle‐specific features to identify the needle echoes. The features are analyzed using a support vector machine classifier to synthesize a quantitative image that highlights the needle. The quantitative image is processed using the Radon transform to achieve a reliable and accurate signature‐based estimation of the needle axis. In the second phase, the accuracy of the needle axis estimation is improved by processing the RF samples located around the signature‐based estimation of the needle axis using local phase analysis combined with the Radon transform. Moreover, a probabilistic approach is employed to identify the needle tip. The proposed method is used to localize needles with two different sizes inserted in ex vivo animal tissue specimens at various insertion angles.ResultsOur proposed method achieved reliable and accurate needle localization for an extended range of needle insertion angles with failure rates of 0% and mean angle, axis, and tip errors smaller than or equal to , 0.6 mm, and 0.7 mm, respectively. Moreover, our proposed method outperformed a recently introduced needle localization method that is based on B‐mode image analysis.ConclusionsThese results suggest the potential of employing our signature‐based method to achieve reliable and accurate needle localization during ultrasound‐guided needle insertion procedures.

show abstract

Needle detection using ultrasound B‐mode and power Doppler analyses

et al. 2022

View full text Add to dashboard Cite

Background: Ultrasound is employed in needle interventions to visualize the anatomical structures and track the needle. Nevertheless, needle detection in ultrasound images is a difficult task, specifically at steep insertion angles. Purpose: A new method is presented to enable effective needle detection using ultrasound B-mode and power Doppler analyses. Methods: A small buzzer is used to excite the needle and an ultrasound system is utilized to acquire B-mode and power Doppler images for the needle. The B-mode and power Doppler images are processed using Radon transform and local-phase analysis to initially detect the axis of the needle. The detection of the needle axis is improved by processing the power Doppler image using alpha shape analysis to define a region of interest (ROI) that contains the needle. Also, a set of feature maps is extracted from the ROI in the B-mode image. The feature maps are processed using a machine learning classifier to construct a likelihood image that visualizes the posterior needle likelihoods of the pixels. Radon transform is applied to the likelihood image to achieve an improved needle axis detection. Additionally, the region in the B-mode image surrounding the needle axis is analyzed to identify the needle tip using a custom-made probabilistic approach. Our method was utilized to detect needles inserted in ex vivo animal tissues at shallow [20 • − 40 • ), moderate [40 • − 60 • ), and steep [60 • − 85 • ] angles.Results: Our method detected the needles with failure rates equal to 0% and mean angle, axis, and tip errors less than or equal to 0.7 • , 0.6 mm, and 0.7 mm, respectively. Additionally, our method achieved favorable results compared to two recently introduced needle detection methods. Conclusions:The results indicate the potential of applying our method to achieve effective needle detection in ultrasound images.

show abstract

Projection-Based Phase Features for Localization of a Needle Tip in 2D Curvilinear Ultrasound

Cited by 17 publications

References 9 publications

Accurate Needle Localization Using Two-Dimensional Power Doppler and B-Mode Ultrasound Image Analyses: A Feasibility Study

Accurate Needle Localization Using Two-Dimensional Power Doppler and B-Mode Ultrasound Image Analyses: A Feasibility Study

Reliable and accurate needle localization in curvilinear ultrasound images using signature‐based analysis of ultrasound beamformed radio frequency signals

Needle detection using ultrasound B‐mode and power Doppler analyses

Contact Info

Product

Resources

About