Automated objective surgical skill assessment in the operating room from unstructured tool motion in septoplasty

Narges Ahmidi, Piyush Poddar, Jonathan D. Jones, S. Swaroop Vedula, Lisa Earnest Ishii, Gregory Hager, Masaru Ishii

Research output: Contribution to journalArticle

Abstract

Purpose: Previous work on surgical skill assessment using intraoperative tool motion has focused on highly structured surgical tasks such as cholecystectomy and used generic motion metrics such as time and number of movements. Other statistical methods such as hidden Markov models (HMM) and descriptive curve coding (DCC) have been successfully used to assess skill in structured activities on bench-top tasks. Methods to assess skill and provide effective feedback to trainees for unstructured surgical tasks in the operating room, such as tissue dissection in septoplasty, have yet to be developed. Methods: We proposed a method that provides a descriptive structure for septoplasty by automatically segmenting it into higher-level meaningful activities called strokes. These activities characterize the surgeon’s tool motion pattern. We constructed a spatial graph from the sequence of strokes in each procedure and used its properties to train a classifier to distinguish between expert and novice surgeons. We compared the results from our method with those from HMM, DCC, and generic metric-based approaches. Results: We showed that our method—with an average accuracy of 91 %—performs better or equal than these state-of-the-art methods, while simultaneously providing surgeons with an intuitive understanding of the procedure. Conclusions: In this study, we developed and evaluated an automated approach to objectively assess surgical skill during unstructured task of tissue dissection in nasal septoplasty.

Original languageEnglish (US)
Pages (from-to)981-991
Number of pages11
JournalInternational journal of computer assisted radiology and surgery
Volume10
Issue number6
DOIs
StatePublished - Apr 17 2015

Fingerprint

Operating rooms
Dissection
Operating Rooms
Hidden Markov models
Tissue
Statistical methods
Classifiers
Feedback
Stroke
Cholecystectomy
Nose

Keywords

  • Feature extraction
  • Feedback
  • Partially observed time series
  • Septoplasty
  • Surgical skill assessment
  • Unstructured activities

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Surgery
  • Medicine(all)

Cite this

Automated objective surgical skill assessment in the operating room from unstructured tool motion in septoplasty. / Ahmidi, Narges; Poddar, Piyush; Jones, Jonathan D.; Vedula, S. Swaroop; Ishii, Lisa Earnest; Hager, Gregory; Ishii, Masaru.

In: International journal of computer assisted radiology and surgery, Vol. 10, No. 6, 17.04.2015, p. 981-991.

Research output: Contribution to journalArticle

@article{f2636e4beeb246ccaa85c5e0ec471304,
title = "Automated objective surgical skill assessment in the operating room from unstructured tool motion in septoplasty",
abstract = "Purpose: Previous work on surgical skill assessment using intraoperative tool motion has focused on highly structured surgical tasks such as cholecystectomy and used generic motion metrics such as time and number of movements. Other statistical methods such as hidden Markov models (HMM) and descriptive curve coding (DCC) have been successfully used to assess skill in structured activities on bench-top tasks. Methods to assess skill and provide effective feedback to trainees for unstructured surgical tasks in the operating room, such as tissue dissection in septoplasty, have yet to be developed. Methods: We proposed a method that provides a descriptive structure for septoplasty by automatically segmenting it into higher-level meaningful activities called strokes. These activities characterize the surgeon’s tool motion pattern. We constructed a spatial graph from the sequence of strokes in each procedure and used its properties to train a classifier to distinguish between expert and novice surgeons. We compared the results from our method with those from HMM, DCC, and generic metric-based approaches. Results: We showed that our method—with an average accuracy of 91 {\%}—performs better or equal than these state-of-the-art methods, while simultaneously providing surgeons with an intuitive understanding of the procedure. Conclusions: In this study, we developed and evaluated an automated approach to objectively assess surgical skill during unstructured task of tissue dissection in nasal septoplasty.",
keywords = "Feature extraction, Feedback, Partially observed time series, Septoplasty, Surgical skill assessment, Unstructured activities",
author = "Narges Ahmidi and Piyush Poddar and Jones, {Jonathan D.} and Vedula, {S. Swaroop} and Ishii, {Lisa Earnest} and Gregory Hager and Masaru Ishii",
year = "2015",
month = "4",
day = "17",
doi = "10.1007/s11548-015-1194-1",
language = "English (US)",
volume = "10",
pages = "981--991",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "6",

}

TY - JOUR

T1 - Automated objective surgical skill assessment in the operating room from unstructured tool motion in septoplasty

AU - Ahmidi, Narges

AU - Poddar, Piyush

AU - Jones, Jonathan D.

AU - Vedula, S. Swaroop

AU - Ishii, Lisa Earnest

AU - Hager, Gregory

AU - Ishii, Masaru

PY - 2015/4/17

Y1 - 2015/4/17

N2 - Purpose: Previous work on surgical skill assessment using intraoperative tool motion has focused on highly structured surgical tasks such as cholecystectomy and used generic motion metrics such as time and number of movements. Other statistical methods such as hidden Markov models (HMM) and descriptive curve coding (DCC) have been successfully used to assess skill in structured activities on bench-top tasks. Methods to assess skill and provide effective feedback to trainees for unstructured surgical tasks in the operating room, such as tissue dissection in septoplasty, have yet to be developed. Methods: We proposed a method that provides a descriptive structure for septoplasty by automatically segmenting it into higher-level meaningful activities called strokes. These activities characterize the surgeon’s tool motion pattern. We constructed a spatial graph from the sequence of strokes in each procedure and used its properties to train a classifier to distinguish between expert and novice surgeons. We compared the results from our method with those from HMM, DCC, and generic metric-based approaches. Results: We showed that our method—with an average accuracy of 91 %—performs better or equal than these state-of-the-art methods, while simultaneously providing surgeons with an intuitive understanding of the procedure. Conclusions: In this study, we developed and evaluated an automated approach to objectively assess surgical skill during unstructured task of tissue dissection in nasal septoplasty.

AB - Purpose: Previous work on surgical skill assessment using intraoperative tool motion has focused on highly structured surgical tasks such as cholecystectomy and used generic motion metrics such as time and number of movements. Other statistical methods such as hidden Markov models (HMM) and descriptive curve coding (DCC) have been successfully used to assess skill in structured activities on bench-top tasks. Methods to assess skill and provide effective feedback to trainees for unstructured surgical tasks in the operating room, such as tissue dissection in septoplasty, have yet to be developed. Methods: We proposed a method that provides a descriptive structure for septoplasty by automatically segmenting it into higher-level meaningful activities called strokes. These activities characterize the surgeon’s tool motion pattern. We constructed a spatial graph from the sequence of strokes in each procedure and used its properties to train a classifier to distinguish between expert and novice surgeons. We compared the results from our method with those from HMM, DCC, and generic metric-based approaches. Results: We showed that our method—with an average accuracy of 91 %—performs better or equal than these state-of-the-art methods, while simultaneously providing surgeons with an intuitive understanding of the procedure. Conclusions: In this study, we developed and evaluated an automated approach to objectively assess surgical skill during unstructured task of tissue dissection in nasal septoplasty.

KW - Feature extraction

KW - Feedback

KW - Partially observed time series

KW - Septoplasty

KW - Surgical skill assessment

KW - Unstructured activities

UR - http://www.scopus.com/inward/record.url?scp=84930083244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930083244&partnerID=8YFLogxK

U2 - 10.1007/s11548-015-1194-1

DO - 10.1007/s11548-015-1194-1

M3 - Article

C2 - 25895080

AN - SCOPUS:84930083244

VL - 10

SP - 981

EP - 991

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 6

ER -