Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions

T. De Silva, A. Uneri, X. Zhang, M. Ketcha, R. Han, M. Jacobson, N. Sheth, S. Vogt, G. Kleinszig, A. Belzberg, D. M. Sciubba, J. H. Siewerdsen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Introduction: Ultrasound (US) is a promising low-cost, real-Time, portable imaging modality suitable for guidance in spine pain procedures. However, suboptimal image quality and US artifacts confound visualization of deep bony anatomy and have limited its widespread use. Real-Time fusion of US images with pre-procedure MRI could provide valuable assistance to guide needle targeting in 3D. To achieve this goal, we propose a fast, entirely image-based 3D-2D rigid registration framework that operates without external hardware tracking and can estimate US probe pose relative to patient position in real-Time. Method: Registration of 2D US (slice) images is performed via the initialization obtained from a fast dictionary search that determines probe pose within a predefined set of pose configurations. 2D slices are extracted from a static 3D US (volume) image to construct a feature dictionary representing different probe poses. Haar features are computed in a fourlevel pyramid that transforms 2D image intensities to a 1D feature vector, which are in turn matched to the 2D target image. 3D-2D registration was performed with the Haar-based initialization with normalized cross-correlation as the metric and Powell's method as the optimizer. Reduction to 1D feature vectors presents the potential for major gains in speed compared to registration of the 3D and 2D images directly. The method was validated in experiments conducted in a lumbar spine phantom and a cadaver specimen with known translations imparted by a computerized motion stage. Results: The Haar feature matching method demonstrated initialization accuracy (mean ± std) = (1.9 ± 1.4) mm and (2.1 ± 1.2) mm in phantom and cadaver studies, respectively. The overall registration accuracy was (2.0 ± 1.3) mm and (1.7 ± 0.9) mm, and the initialization was a necessary and important step in the registration process. Conclusions: The proposed image-based registration method demonstrated promising results for compensating motion of the US probe. This image-based solution could be an important step toward an entirely image-based, real-Time registration method of 2D US to 3D US and pre-procedure MRI, eliminating hardware-based tracking systems in a manner more suitable to clinical workflow.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
PublisherSPIE
Volume10576
ISBN (Electronic)9781510616417
DOIs
StatePublished - Jan 1 2018
EventMedical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling - Houston, United States
Duration: Feb 12 2018Feb 15 2018

Other

OtherMedical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CityHouston
Period2/12/182/15/18

Fingerprint

Ultrasonics
Glossaries
dictionaries
Cadaver
spine
probes
Magnetic resonance imaging
Spine
hardware
Hardware
Workflow
pain
Needles
Artifacts
Image quality
anatomy
Anatomy
pyramids
Fusion reactions
needles

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

De Silva, T., Uneri, A., Zhang, X., Ketcha, M., Han, R., Jacobson, M., ... Siewerdsen, J. H. (2018). Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions. In Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling (Vol. 10576). [105760E] SPIE. https://doi.org/10.1117/12.2293710

Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions. / De Silva, T.; Uneri, A.; Zhang, X.; Ketcha, M.; Han, R.; Jacobson, M.; Sheth, N.; Vogt, S.; Kleinszig, G.; Belzberg, A.; Sciubba, D. M.; Siewerdsen, J. H.

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. Vol. 10576 SPIE, 2018. 105760E.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

De Silva, T, Uneri, A, Zhang, X, Ketcha, M, Han, R, Jacobson, M, Sheth, N, Vogt, S, Kleinszig, G, Belzberg, A, Sciubba, DM & Siewerdsen, JH 2018, Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions. in Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. vol. 10576, 105760E, SPIE, Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling, Houston, United States, 2/12/18. https://doi.org/10.1117/12.2293710
De Silva T, Uneri A, Zhang X, Ketcha M, Han R, Jacobson M et al. Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions. In Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. Vol. 10576. SPIE. 2018. 105760E https://doi.org/10.1117/12.2293710
De Silva, T. ; Uneri, A. ; Zhang, X. ; Ketcha, M. ; Han, R. ; Jacobson, M. ; Sheth, N. ; Vogt, S. ; Kleinszig, G. ; Belzberg, A. ; Sciubba, D. M. ; Siewerdsen, J. H. / Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions. Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling. Vol. 10576 SPIE, 2018.
@inproceedings{aabaa1ed9d124007b3ccb83bc4603336,
title = "Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions",
abstract = "Introduction: Ultrasound (US) is a promising low-cost, real-Time, portable imaging modality suitable for guidance in spine pain procedures. However, suboptimal image quality and US artifacts confound visualization of deep bony anatomy and have limited its widespread use. Real-Time fusion of US images with pre-procedure MRI could provide valuable assistance to guide needle targeting in 3D. To achieve this goal, we propose a fast, entirely image-based 3D-2D rigid registration framework that operates without external hardware tracking and can estimate US probe pose relative to patient position in real-Time. Method: Registration of 2D US (slice) images is performed via the initialization obtained from a fast dictionary search that determines probe pose within a predefined set of pose configurations. 2D slices are extracted from a static 3D US (volume) image to construct a feature dictionary representing different probe poses. Haar features are computed in a fourlevel pyramid that transforms 2D image intensities to a 1D feature vector, which are in turn matched to the 2D target image. 3D-2D registration was performed with the Haar-based initialization with normalized cross-correlation as the metric and Powell's method as the optimizer. Reduction to 1D feature vectors presents the potential for major gains in speed compared to registration of the 3D and 2D images directly. The method was validated in experiments conducted in a lumbar spine phantom and a cadaver specimen with known translations imparted by a computerized motion stage. Results: The Haar feature matching method demonstrated initialization accuracy (mean ± std) = (1.9 ± 1.4) mm and (2.1 ± 1.2) mm in phantom and cadaver studies, respectively. The overall registration accuracy was (2.0 ± 1.3) mm and (1.7 ± 0.9) mm, and the initialization was a necessary and important step in the registration process. Conclusions: The proposed image-based registration method demonstrated promising results for compensating motion of the US probe. This image-based solution could be an important step toward an entirely image-based, real-Time registration method of 2D US to 3D US and pre-procedure MRI, eliminating hardware-based tracking systems in a manner more suitable to clinical workflow.",
author = "{De Silva}, T. and A. Uneri and X. Zhang and M. Ketcha and R. Han and M. Jacobson and N. Sheth and S. Vogt and G. Kleinszig and A. Belzberg and Sciubba, {D. M.} and Siewerdsen, {J. H.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2293710",
language = "English (US)",
volume = "10576",
booktitle = "Medical Imaging 2018",
publisher = "SPIE",

}

TY - GEN

T1 - Real-Time image-based 3D-2D registration for ultrasound-guided spinal interventions

AU - De Silva, T.

AU - Uneri, A.

AU - Zhang, X.

AU - Ketcha, M.

AU - Han, R.

AU - Jacobson, M.

AU - Sheth, N.

AU - Vogt, S.

AU - Kleinszig, G.

AU - Belzberg, A.

AU - Sciubba, D. M.

AU - Siewerdsen, J. H.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Introduction: Ultrasound (US) is a promising low-cost, real-Time, portable imaging modality suitable for guidance in spine pain procedures. However, suboptimal image quality and US artifacts confound visualization of deep bony anatomy and have limited its widespread use. Real-Time fusion of US images with pre-procedure MRI could provide valuable assistance to guide needle targeting in 3D. To achieve this goal, we propose a fast, entirely image-based 3D-2D rigid registration framework that operates without external hardware tracking and can estimate US probe pose relative to patient position in real-Time. Method: Registration of 2D US (slice) images is performed via the initialization obtained from a fast dictionary search that determines probe pose within a predefined set of pose configurations. 2D slices are extracted from a static 3D US (volume) image to construct a feature dictionary representing different probe poses. Haar features are computed in a fourlevel pyramid that transforms 2D image intensities to a 1D feature vector, which are in turn matched to the 2D target image. 3D-2D registration was performed with the Haar-based initialization with normalized cross-correlation as the metric and Powell's method as the optimizer. Reduction to 1D feature vectors presents the potential for major gains in speed compared to registration of the 3D and 2D images directly. The method was validated in experiments conducted in a lumbar spine phantom and a cadaver specimen with known translations imparted by a computerized motion stage. Results: The Haar feature matching method demonstrated initialization accuracy (mean ± std) = (1.9 ± 1.4) mm and (2.1 ± 1.2) mm in phantom and cadaver studies, respectively. The overall registration accuracy was (2.0 ± 1.3) mm and (1.7 ± 0.9) mm, and the initialization was a necessary and important step in the registration process. Conclusions: The proposed image-based registration method demonstrated promising results for compensating motion of the US probe. This image-based solution could be an important step toward an entirely image-based, real-Time registration method of 2D US to 3D US and pre-procedure MRI, eliminating hardware-based tracking systems in a manner more suitable to clinical workflow.

AB - Introduction: Ultrasound (US) is a promising low-cost, real-Time, portable imaging modality suitable for guidance in spine pain procedures. However, suboptimal image quality and US artifacts confound visualization of deep bony anatomy and have limited its widespread use. Real-Time fusion of US images with pre-procedure MRI could provide valuable assistance to guide needle targeting in 3D. To achieve this goal, we propose a fast, entirely image-based 3D-2D rigid registration framework that operates without external hardware tracking and can estimate US probe pose relative to patient position in real-Time. Method: Registration of 2D US (slice) images is performed via the initialization obtained from a fast dictionary search that determines probe pose within a predefined set of pose configurations. 2D slices are extracted from a static 3D US (volume) image to construct a feature dictionary representing different probe poses. Haar features are computed in a fourlevel pyramid that transforms 2D image intensities to a 1D feature vector, which are in turn matched to the 2D target image. 3D-2D registration was performed with the Haar-based initialization with normalized cross-correlation as the metric and Powell's method as the optimizer. Reduction to 1D feature vectors presents the potential for major gains in speed compared to registration of the 3D and 2D images directly. The method was validated in experiments conducted in a lumbar spine phantom and a cadaver specimen with known translations imparted by a computerized motion stage. Results: The Haar feature matching method demonstrated initialization accuracy (mean ± std) = (1.9 ± 1.4) mm and (2.1 ± 1.2) mm in phantom and cadaver studies, respectively. The overall registration accuracy was (2.0 ± 1.3) mm and (1.7 ± 0.9) mm, and the initialization was a necessary and important step in the registration process. Conclusions: The proposed image-based registration method demonstrated promising results for compensating motion of the US probe. This image-based solution could be an important step toward an entirely image-based, real-Time registration method of 2D US to 3D US and pre-procedure MRI, eliminating hardware-based tracking systems in a manner more suitable to clinical workflow.

UR - http://www.scopus.com/inward/record.url?scp=85050673473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050673473&partnerID=8YFLogxK

U2 - 10.1117/12.2293710

DO - 10.1117/12.2293710

M3 - Conference contribution

AN - SCOPUS:85050673473

VL - 10576

BT - Medical Imaging 2018

PB - SPIE

ER -