Surgical motion characterization in simulated needle insertion procedures

Matthew S. Holden, Tamas Ungi, Derek Sargent, Robert C. McGraw, Gabor Fichtinger

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

Abstract

PURPOSE: Evaluation of surgical performance in image-guided needle insertions is of emerging interest, to both promote patient safety and improve the efficiency and effectiveness of training. The purpose of this study was to determine if a Markov model-based algorithm can more accurately segment a needle-based surgical procedure into its five constituent tasks than a simple threshold-based algorithm. METHODS: Simulated needle trajectories were generated with known ground truth segmentation by a synthetic procedural data generator, with random noise added to each degree of freedom of motion. The respective learning algorithms were trained, and then tested on different procedures to determine task segmentation accuracy. In the threshold-based algorithm, a change in tasks was detected when the needle crossed a position/velocity threshold. In the Markov model-based algorithm, task segmentation was performed by identifying the sequence of Markov models most likely to have produced the series of observations. RESULTS: For amplitudes of translational noise greater than 0.01mm, the Markov model-based algorithm was significantly more accurate in task segmentation than the threshold-based algorithm (82.3% vs. 49.9%, p

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8316
DOIs
StatePublished - 2012
Externally publishedYes
EventMedical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling - San Diego, CA, United States
Duration: Feb 5 2012Feb 7 2012

Other

OtherMedical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CitySan Diego, CA
Period2/5/122/7/12

Fingerprint

needles
Needles
insertion
thresholds
ground truth
Learning algorithms
Patient Safety
random noise
learning
Noise
Trajectories
emerging
safety
education
generators
degrees of freedom
trajectories
Learning
Efficiency
evaluation

Keywords

  • Lumbar Puncture
  • Markov Models
  • Needle trajectories
  • Simulated procedures
  • Task segmentation

ASJC Scopus subject areas

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

Cite this

Holden, M. S., Ungi, T., Sargent, D., McGraw, R. C., & Fichtinger, G. (2012). Surgical motion characterization in simulated needle insertion procedures. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 8316). [83160W] https://doi.org/10.1117/12.911003

Surgical motion characterization in simulated needle insertion procedures. / Holden, Matthew S.; Ungi, Tamas; Sargent, Derek; McGraw, Robert C.; Fichtinger, Gabor.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8316 2012. 83160W.

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

Holden, MS, Ungi, T, Sargent, D, McGraw, RC & Fichtinger, G 2012, Surgical motion characterization in simulated needle insertion procedures. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 8316, 83160W, Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, CA, United States, 2/5/12. https://doi.org/10.1117/12.911003
Holden MS, Ungi T, Sargent D, McGraw RC, Fichtinger G. Surgical motion characterization in simulated needle insertion procedures. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8316. 2012. 83160W https://doi.org/10.1117/12.911003
Holden, Matthew S. ; Ungi, Tamas ; Sargent, Derek ; McGraw, Robert C. ; Fichtinger, Gabor. / Surgical motion characterization in simulated needle insertion procedures. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8316 2012.
@inproceedings{cb443cc8f94c4eb4ad7b9cbfa984f05e,
title = "Surgical motion characterization in simulated needle insertion procedures",
abstract = "PURPOSE: Evaluation of surgical performance in image-guided needle insertions is of emerging interest, to both promote patient safety and improve the efficiency and effectiveness of training. The purpose of this study was to determine if a Markov model-based algorithm can more accurately segment a needle-based surgical procedure into its five constituent tasks than a simple threshold-based algorithm. METHODS: Simulated needle trajectories were generated with known ground truth segmentation by a synthetic procedural data generator, with random noise added to each degree of freedom of motion. The respective learning algorithms were trained, and then tested on different procedures to determine task segmentation accuracy. In the threshold-based algorithm, a change in tasks was detected when the needle crossed a position/velocity threshold. In the Markov model-based algorithm, task segmentation was performed by identifying the sequence of Markov models most likely to have produced the series of observations. RESULTS: For amplitudes of translational noise greater than 0.01mm, the Markov model-based algorithm was significantly more accurate in task segmentation than the threshold-based algorithm (82.3{\%} vs. 49.9{\%}, p",
keywords = "Lumbar Puncture, Markov Models, Needle trajectories, Simulated procedures, Task segmentation",
author = "Holden, {Matthew S.} and Tamas Ungi and Derek Sargent and McGraw, {Robert C.} and Gabor Fichtinger",
year = "2012",
doi = "10.1117/12.911003",
language = "English (US)",
isbn = "9780819489654",
volume = "8316",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Surgical motion characterization in simulated needle insertion procedures

AU - Holden, Matthew S.

AU - Ungi, Tamas

AU - Sargent, Derek

AU - McGraw, Robert C.

AU - Fichtinger, Gabor

PY - 2012

Y1 - 2012

N2 - PURPOSE: Evaluation of surgical performance in image-guided needle insertions is of emerging interest, to both promote patient safety and improve the efficiency and effectiveness of training. The purpose of this study was to determine if a Markov model-based algorithm can more accurately segment a needle-based surgical procedure into its five constituent tasks than a simple threshold-based algorithm. METHODS: Simulated needle trajectories were generated with known ground truth segmentation by a synthetic procedural data generator, with random noise added to each degree of freedom of motion. The respective learning algorithms were trained, and then tested on different procedures to determine task segmentation accuracy. In the threshold-based algorithm, a change in tasks was detected when the needle crossed a position/velocity threshold. In the Markov model-based algorithm, task segmentation was performed by identifying the sequence of Markov models most likely to have produced the series of observations. RESULTS: For amplitudes of translational noise greater than 0.01mm, the Markov model-based algorithm was significantly more accurate in task segmentation than the threshold-based algorithm (82.3% vs. 49.9%, p

AB - PURPOSE: Evaluation of surgical performance in image-guided needle insertions is of emerging interest, to both promote patient safety and improve the efficiency and effectiveness of training. The purpose of this study was to determine if a Markov model-based algorithm can more accurately segment a needle-based surgical procedure into its five constituent tasks than a simple threshold-based algorithm. METHODS: Simulated needle trajectories were generated with known ground truth segmentation by a synthetic procedural data generator, with random noise added to each degree of freedom of motion. The respective learning algorithms were trained, and then tested on different procedures to determine task segmentation accuracy. In the threshold-based algorithm, a change in tasks was detected when the needle crossed a position/velocity threshold. In the Markov model-based algorithm, task segmentation was performed by identifying the sequence of Markov models most likely to have produced the series of observations. RESULTS: For amplitudes of translational noise greater than 0.01mm, the Markov model-based algorithm was significantly more accurate in task segmentation than the threshold-based algorithm (82.3% vs. 49.9%, p

KW - Lumbar Puncture

KW - Markov Models

KW - Needle trajectories

KW - Simulated procedures

KW - Task segmentation

UR - http://www.scopus.com/inward/record.url?scp=84860245298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860245298&partnerID=8YFLogxK

U2 - 10.1117/12.911003

DO - 10.1117/12.911003

M3 - Conference contribution

AN - SCOPUS:84860245298

SN - 9780819489654

VL - 8316

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -