Conditions for reliable grip force and jaw angle estimation of da Vinci surgical tools

Trevor K. Stephens, John J. O’Neill, Nathan J. Kong, Mark V. Mazzeo, Jack E. Norfleet, Rob Sweet, Timothy M Kowalewski

Research output: Contribution to journalArticle

Abstract

Purpose: This work presents an estimation technique as well as corresponding conditions which are necessary to produce an accurate estimate of grip force and jaw angle on a da Vinci surgical tool using back-end sensors alone. Methods: This work utilizes an artificial neural network as the regression estimator on a dataset acquired from custom hardware on the proximal and distal ends. Through a series of experiments, we test the effect of estimation accuracy due to change in operating frequency, using the opposite jaw, and using different tools. A case study is then presented comparing our estimation technique with direct measurements of material response curves on two synthetic tissue surrogates. Results: We establish the following criteria as necessary to produce an accurate estimate: operate within training frequency bounds, use the same side jaw, and use the same tool. Under these criteria, an average root mean square error of 1.04 mN m in grip force and 0.17 degrees in jaw angle is achieved. Additionally, applying these criteria in the case study resulted in direct measurements which fell within the 95% confidence bands of our estimation technique. Conclusion: Our estimation technique, along with important training criteria, is presented herein to further improve the literature pertaining to grip force estimation. We propose the training criteria to begin establishing bounds on the applicability of estimation techniques used for grip force estimation for eventual translation into clinical practice.

Original languageEnglish (US)
Pages (from-to)117-127
Number of pages11
JournalInternational Journal of Computer Assisted Radiology and Surgery
Volume14
Issue number1
DOIs
StatePublished - Jan 17 2019

Fingerprint

Hand Strength
Jaw
Mean square error
Tissue
Neural networks
Hardware
Sensors

Keywords

  • Artificial neural network
  • Grip force estimation
  • Surgical robotics

PubMed: MeSH publication types

  • Journal Article

Cite this

Conditions for reliable grip force and jaw angle estimation of da Vinci surgical tools. / Stephens, Trevor K.; O’Neill, John J.; Kong, Nathan J.; Mazzeo, Mark V.; Norfleet, Jack E.; Sweet, Rob; Kowalewski, Timothy M.

In: International Journal of Computer Assisted Radiology and Surgery, Vol. 14, No. 1, 17.01.2019, p. 117-127.

Research output: Contribution to journalArticle

Stephens, Trevor K. ; O’Neill, John J. ; Kong, Nathan J. ; Mazzeo, Mark V. ; Norfleet, Jack E. ; Sweet, Rob ; Kowalewski, Timothy M. / Conditions for reliable grip force and jaw angle estimation of da Vinci surgical tools. In: International Journal of Computer Assisted Radiology and Surgery. 2019 ; Vol. 14, No. 1. pp. 117-127.
@article{711686dd5b3c4caa95823df967cb06a2,
title = "Conditions for reliable grip force and jaw angle estimation of da Vinci surgical tools",
abstract = "Purpose: This work presents an estimation technique as well as corresponding conditions which are necessary to produce an accurate estimate of grip force and jaw angle on a da Vinci surgical tool using back-end sensors alone. Methods: This work utilizes an artificial neural network as the regression estimator on a dataset acquired from custom hardware on the proximal and distal ends. Through a series of experiments, we test the effect of estimation accuracy due to change in operating frequency, using the opposite jaw, and using different tools. A case study is then presented comparing our estimation technique with direct measurements of material response curves on two synthetic tissue surrogates. Results: We establish the following criteria as necessary to produce an accurate estimate: operate within training frequency bounds, use the same side jaw, and use the same tool. Under these criteria, an average root mean square error of 1.04 mN m in grip force and 0.17 degrees in jaw angle is achieved. Additionally, applying these criteria in the case study resulted in direct measurements which fell within the 95{\%} confidence bands of our estimation technique. Conclusion: Our estimation technique, along with important training criteria, is presented herein to further improve the literature pertaining to grip force estimation. We propose the training criteria to begin establishing bounds on the applicability of estimation techniques used for grip force estimation for eventual translation into clinical practice.",
keywords = "Artificial neural network, Grip force estimation, Surgical robotics",
author = "Stephens, {Trevor K.} and O’Neill, {John J.} and Kong, {Nathan J.} and Mazzeo, {Mark V.} and Norfleet, {Jack E.} and Rob Sweet and Kowalewski, {Timothy M}",
year = "2019",
month = "1",
day = "17",
doi = "10.1007/s11548-018-1866-8",
language = "English (US)",
volume = "14",
pages = "117--127",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Conditions for reliable grip force and jaw angle estimation of da Vinci surgical tools

AU - Stephens, Trevor K.

AU - O’Neill, John J.

AU - Kong, Nathan J.

AU - Mazzeo, Mark V.

AU - Norfleet, Jack E.

AU - Sweet, Rob

AU - Kowalewski, Timothy M

PY - 2019/1/17

Y1 - 2019/1/17

N2 - Purpose: This work presents an estimation technique as well as corresponding conditions which are necessary to produce an accurate estimate of grip force and jaw angle on a da Vinci surgical tool using back-end sensors alone. Methods: This work utilizes an artificial neural network as the regression estimator on a dataset acquired from custom hardware on the proximal and distal ends. Through a series of experiments, we test the effect of estimation accuracy due to change in operating frequency, using the opposite jaw, and using different tools. A case study is then presented comparing our estimation technique with direct measurements of material response curves on two synthetic tissue surrogates. Results: We establish the following criteria as necessary to produce an accurate estimate: operate within training frequency bounds, use the same side jaw, and use the same tool. Under these criteria, an average root mean square error of 1.04 mN m in grip force and 0.17 degrees in jaw angle is achieved. Additionally, applying these criteria in the case study resulted in direct measurements which fell within the 95% confidence bands of our estimation technique. Conclusion: Our estimation technique, along with important training criteria, is presented herein to further improve the literature pertaining to grip force estimation. We propose the training criteria to begin establishing bounds on the applicability of estimation techniques used for grip force estimation for eventual translation into clinical practice.

AB - Purpose: This work presents an estimation technique as well as corresponding conditions which are necessary to produce an accurate estimate of grip force and jaw angle on a da Vinci surgical tool using back-end sensors alone. Methods: This work utilizes an artificial neural network as the regression estimator on a dataset acquired from custom hardware on the proximal and distal ends. Through a series of experiments, we test the effect of estimation accuracy due to change in operating frequency, using the opposite jaw, and using different tools. A case study is then presented comparing our estimation technique with direct measurements of material response curves on two synthetic tissue surrogates. Results: We establish the following criteria as necessary to produce an accurate estimate: operate within training frequency bounds, use the same side jaw, and use the same tool. Under these criteria, an average root mean square error of 1.04 mN m in grip force and 0.17 degrees in jaw angle is achieved. Additionally, applying these criteria in the case study resulted in direct measurements which fell within the 95% confidence bands of our estimation technique. Conclusion: Our estimation technique, along with important training criteria, is presented herein to further improve the literature pertaining to grip force estimation. We propose the training criteria to begin establishing bounds on the applicability of estimation techniques used for grip force estimation for eventual translation into clinical practice.

KW - Artificial neural network

KW - Grip force estimation

KW - Surgical robotics

UR - http://www.scopus.com/inward/record.url?scp=85054565322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054565322&partnerID=8YFLogxK

U2 - 10.1007/s11548-018-1866-8

DO - 10.1007/s11548-018-1866-8

M3 - Article

VL - 14

SP - 117

EP - 127

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 1

ER -