Surgical motion analysis using discriminative interpretable patterns

Germain Forestier, François Petitjean, Pavel Senin, Fabien Despinoy, Arnaud Huaulmé, Hassan Ismail Fawaz, Jonathan Weber, Lhassane Idoumghar, Pierre Alain Muller, Pierre Jannin

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Abstract

Objective: The analysis of surgical motion has received a growing interest with the development of devices allowing their automatic capture. In this context, the use of advanced surgical training systems makes an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. Material and method: In this paper, we present an approach for the discovery and ranking of discriminative and interpretable patterns of surgical practice from recordings of surgical motions. A pattern is defined as a series of actions or events in the kinematic data that together are distinctive of a specific gesture or skill level. Our approach is based on the decomposition of continuous kinematic data into a set of overlapping gestures represented by strings (bag of words) for which we compute comparative numerical statistic (tf-idf) enabling the discriminative gesture discovery via its relative occurrence frequency. Results: We carried out experiments on three surgical motion datasets. The results show that the patterns identified by the proposed method can be used to accurately classify individual gestures, skill levels and surgical interfaces. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Conclusions: The proposed approach is an interesting addition to existing learning tools for surgery as it provides a way to obtain a feedback on which parts of an exercise have been used to classify the attempt as correct or incorrect.

Original languageEnglish
Pages (from-to)3-11
Number of pages9
JournalArtificial Intelligence in Medicine
Volume91
DOIs
Publication statusPublished - Sep 2018

Keywords

  • Dynamic time warping
  • Surgery
  • Surgical process modelling
  • Temporal analysis

Cite this

Forestier, Germain ; Petitjean, François ; Senin, Pavel ; Despinoy, Fabien ; Huaulmé, Arnaud ; Fawaz, Hassan Ismail ; Weber, Jonathan ; Idoumghar, Lhassane ; Muller, Pierre Alain ; Jannin, Pierre. / Surgical motion analysis using discriminative interpretable patterns. In: Artificial Intelligence in Medicine. 2018 ; Vol. 91. pp. 3-11.
@article{c57d5580c2c54b0f900e4a200fdac4ce,
title = "Surgical motion analysis using discriminative interpretable patterns",
abstract = "Objective: The analysis of surgical motion has received a growing interest with the development of devices allowing their automatic capture. In this context, the use of advanced surgical training systems makes an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. Material and method: In this paper, we present an approach for the discovery and ranking of discriminative and interpretable patterns of surgical practice from recordings of surgical motions. A pattern is defined as a series of actions or events in the kinematic data that together are distinctive of a specific gesture or skill level. Our approach is based on the decomposition of continuous kinematic data into a set of overlapping gestures represented by strings (bag of words) for which we compute comparative numerical statistic (tf-idf) enabling the discriminative gesture discovery via its relative occurrence frequency. Results: We carried out experiments on three surgical motion datasets. The results show that the patterns identified by the proposed method can be used to accurately classify individual gestures, skill levels and surgical interfaces. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Conclusions: The proposed approach is an interesting addition to existing learning tools for surgery as it provides a way to obtain a feedback on which parts of an exercise have been used to classify the attempt as correct or incorrect.",
keywords = "Dynamic time warping, Surgery, Surgical process modelling, Temporal analysis",
author = "Germain Forestier and Fran{\cc}ois Petitjean and Pavel Senin and Fabien Despinoy and Arnaud Huaulm{\'e} and Fawaz, {Hassan Ismail} and Jonathan Weber and Lhassane Idoumghar and Muller, {Pierre Alain} and Pierre Jannin",
year = "2018",
month = "9",
doi = "10.1016/j.artmed.2018.08.002",
language = "English",
volume = "91",
pages = "3--11",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

Forestier, G, Petitjean, F, Senin, P, Despinoy, F, Huaulmé, A, Fawaz, HI, Weber, J, Idoumghar, L, Muller, PA & Jannin, P 2018, 'Surgical motion analysis using discriminative interpretable patterns', Artificial Intelligence in Medicine, vol. 91, pp. 3-11. https://doi.org/10.1016/j.artmed.2018.08.002

Surgical motion analysis using discriminative interpretable patterns. / Forestier, Germain; Petitjean, François; Senin, Pavel; Despinoy, Fabien; Huaulmé, Arnaud; Fawaz, Hassan Ismail; Weber, Jonathan; Idoumghar, Lhassane; Muller, Pierre Alain; Jannin, Pierre.

In: Artificial Intelligence in Medicine, Vol. 91, 09.2018, p. 3-11.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Surgical motion analysis using discriminative interpretable patterns

AU - Forestier, Germain

AU - Petitjean, François

AU - Senin, Pavel

AU - Despinoy, Fabien

AU - Huaulmé, Arnaud

AU - Fawaz, Hassan Ismail

AU - Weber, Jonathan

AU - Idoumghar, Lhassane

AU - Muller, Pierre Alain

AU - Jannin, Pierre

PY - 2018/9

Y1 - 2018/9

N2 - Objective: The analysis of surgical motion has received a growing interest with the development of devices allowing their automatic capture. In this context, the use of advanced surgical training systems makes an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. Material and method: In this paper, we present an approach for the discovery and ranking of discriminative and interpretable patterns of surgical practice from recordings of surgical motions. A pattern is defined as a series of actions or events in the kinematic data that together are distinctive of a specific gesture or skill level. Our approach is based on the decomposition of continuous kinematic data into a set of overlapping gestures represented by strings (bag of words) for which we compute comparative numerical statistic (tf-idf) enabling the discriminative gesture discovery via its relative occurrence frequency. Results: We carried out experiments on three surgical motion datasets. The results show that the patterns identified by the proposed method can be used to accurately classify individual gestures, skill levels and surgical interfaces. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Conclusions: The proposed approach is an interesting addition to existing learning tools for surgery as it provides a way to obtain a feedback on which parts of an exercise have been used to classify the attempt as correct or incorrect.

AB - Objective: The analysis of surgical motion has received a growing interest with the development of devices allowing their automatic capture. In this context, the use of advanced surgical training systems makes an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. Material and method: In this paper, we present an approach for the discovery and ranking of discriminative and interpretable patterns of surgical practice from recordings of surgical motions. A pattern is defined as a series of actions or events in the kinematic data that together are distinctive of a specific gesture or skill level. Our approach is based on the decomposition of continuous kinematic data into a set of overlapping gestures represented by strings (bag of words) for which we compute comparative numerical statistic (tf-idf) enabling the discriminative gesture discovery via its relative occurrence frequency. Results: We carried out experiments on three surgical motion datasets. The results show that the patterns identified by the proposed method can be used to accurately classify individual gestures, skill levels and surgical interfaces. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Conclusions: The proposed approach is an interesting addition to existing learning tools for surgery as it provides a way to obtain a feedback on which parts of an exercise have been used to classify the attempt as correct or incorrect.

KW - Dynamic time warping

KW - Surgery

KW - Surgical process modelling

KW - Temporal analysis

UR - http://www.scopus.com/inward/record.url?scp=85052759152&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2018.08.002

DO - 10.1016/j.artmed.2018.08.002

M3 - Article

C2 - 30172445

AN - SCOPUS:85052759152

VL - 91

SP - 3

EP - 11

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -