Discovering discriminative and interpretable patterns for surgical motion analysis

Germain Forestier, François Petitjean, Pavel Senin, Fabien Despinoy, Pierre Jannin

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    8 Citations (Scopus)

    Abstract

    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 make an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. In this paper, we present a novel 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 discretization of the continuous kinematic data into strings which are then processed to form bags of words. This step allows us to apply discriminative pattern mining technique based on the word occurrence frequency. We show that the patterns identified by the proposed technique can be used to accurately classify individual gestures and skill levels. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Experimental evaluation performed on the publicly available JIGSAWS dataset shows that the proposed approach successfully classifies gestures and skill levels.

    Original languageEnglish
    Title of host publicationArtificial Intelligence in Medicine
    Subtitle of host publication16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings
    EditorsAnnette ten Teije, John H. Holmes, Christian Popow, Lucia Sacchi
    Place of PublicationCham, Switzerland
    PublisherSpringer
    Pages136-145
    Number of pages10
    ISBN (Electronic)9783319597584
    ISBN (Print)9783319597577
    DOIs
    Publication statusPublished - 2017
    EventArtificial Intelligence in Medicine in Europe 2017 - Vienna, Austria
    Duration: 21 Jun 201724 Jun 2017
    Conference number: 16th
    http://aime17.aimedicine.info/home.html

    Publication series

    NameLecture Notes in Artificial Intelligence
    PublisherSpringer
    Volume10259
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    ConferenceArtificial Intelligence in Medicine in Europe 2017
    Abbreviated titleAIME 2017
    CountryAustria
    CityVienna
    Period21/06/1724/06/17
    Internet address

    Keywords

    • Pattern mining
    • Skill assessment
    • Surgical motion analysis

    Cite this

    Forestier, G., Petitjean, F., Senin, P., Despinoy, F., & Jannin, P. (2017). Discovering discriminative and interpretable patterns for surgical motion analysis. In A. T. Teije, J. H. Holmes, C. Popow, & L. Sacchi (Eds.), Artificial Intelligence in Medicine : 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings (pp. 136-145). (Lecture Notes in Artificial Intelligence; Vol. 10259 ). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-59758-4_15
    Forestier, Germain ; Petitjean, François ; Senin, Pavel ; Despinoy, Fabien ; Jannin, Pierre. / Discovering discriminative and interpretable patterns for surgical motion analysis. Artificial Intelligence in Medicine : 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings. editor / Annette ten Teije ; John H. Holmes ; Christian Popow ; Lucia Sacchi. Cham, Switzerland : Springer, 2017. pp. 136-145 (Lecture Notes in Artificial Intelligence).
    @inproceedings{67df23409b4348afa18a78bc558630d4,
    title = "Discovering discriminative and interpretable patterns for surgical motion analysis",
    abstract = "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 make an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. In this paper, we present a novel 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 discretization of the continuous kinematic data into strings which are then processed to form bags of words. This step allows us to apply discriminative pattern mining technique based on the word occurrence frequency. We show that the patterns identified by the proposed technique can be used to accurately classify individual gestures and skill levels. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Experimental evaluation performed on the publicly available JIGSAWS dataset shows that the proposed approach successfully classifies gestures and skill levels.",
    keywords = "Pattern mining, Skill assessment, Surgical motion analysis",
    author = "Germain Forestier and Fran{\cc}ois Petitjean and Pavel Senin and Fabien Despinoy and Pierre Jannin",
    year = "2017",
    doi = "10.1007/978-3-319-59758-4_15",
    language = "English",
    isbn = "9783319597577",
    series = "Lecture Notes in Artificial Intelligence",
    publisher = "Springer",
    pages = "136--145",
    editor = "Teije, {Annette ten } and Holmes, {John H. } and Popow, {Christian } and Sacchi, {Lucia }",
    booktitle = "Artificial Intelligence in Medicine",

    }

    Forestier, G, Petitjean, F, Senin, P, Despinoy, F & Jannin, P 2017, Discovering discriminative and interpretable patterns for surgical motion analysis. in AT Teije, JH Holmes, C Popow & L Sacchi (eds), Artificial Intelligence in Medicine : 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings. Lecture Notes in Artificial Intelligence, vol. 10259 , Springer, Cham, Switzerland, pp. 136-145, Artificial Intelligence in Medicine in Europe 2017, Vienna, Austria, 21/06/17. https://doi.org/10.1007/978-3-319-59758-4_15

    Discovering discriminative and interpretable patterns for surgical motion analysis. / Forestier, Germain; Petitjean, François; Senin, Pavel; Despinoy, Fabien; Jannin, Pierre.

    Artificial Intelligence in Medicine : 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings. ed. / Annette ten Teije; John H. Holmes; Christian Popow; Lucia Sacchi. Cham, Switzerland : Springer, 2017. p. 136-145 (Lecture Notes in Artificial Intelligence; Vol. 10259 ).

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    TY - GEN

    T1 - Discovering discriminative and interpretable patterns for surgical motion analysis

    AU - Forestier, Germain

    AU - Petitjean, François

    AU - Senin, Pavel

    AU - Despinoy, Fabien

    AU - Jannin, Pierre

    PY - 2017

    Y1 - 2017

    N2 - 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 make an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. In this paper, we present a novel 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 discretization of the continuous kinematic data into strings which are then processed to form bags of words. This step allows us to apply discriminative pattern mining technique based on the word occurrence frequency. We show that the patterns identified by the proposed technique can be used to accurately classify individual gestures and skill levels. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Experimental evaluation performed on the publicly available JIGSAWS dataset shows that the proposed approach successfully classifies gestures and skill levels.

    AB - 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 make an automated assessment of surgical trainee possible. Automatic and quantitative evaluation of surgical skills is a very important step in improving surgical patient care. In this paper, we present a novel 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 discretization of the continuous kinematic data into strings which are then processed to form bags of words. This step allows us to apply discriminative pattern mining technique based on the word occurrence frequency. We show that the patterns identified by the proposed technique can be used to accurately classify individual gestures and skill levels. We also present how the patterns provide a detailed feedback on the trainee skill assessment. Experimental evaluation performed on the publicly available JIGSAWS dataset shows that the proposed approach successfully classifies gestures and skill levels.

    KW - Pattern mining

    KW - Skill assessment

    KW - Surgical motion analysis

    UR - http://www.scopus.com/inward/record.url?scp=85021649175&partnerID=8YFLogxK

    U2 - 10.1007/978-3-319-59758-4_15

    DO - 10.1007/978-3-319-59758-4_15

    M3 - Conference Paper

    AN - SCOPUS:85021649175

    SN - 9783319597577

    T3 - Lecture Notes in Artificial Intelligence

    SP - 136

    EP - 145

    BT - Artificial Intelligence in Medicine

    A2 - Teije, Annette ten

    A2 - Holmes, John H.

    A2 - Popow, Christian

    A2 - Sacchi, Lucia

    PB - Springer

    CY - Cham, Switzerland

    ER -

    Forestier G, Petitjean F, Senin P, Despinoy F, Jannin P. Discovering discriminative and interpretable patterns for surgical motion analysis. In Teije AT, Holmes JH, Popow C, Sacchi L, editors, Artificial Intelligence in Medicine : 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21–24, 2017, Proceedings. Cham, Switzerland: Springer. 2017. p. 136-145. (Lecture Notes in Artificial Intelligence). https://doi.org/10.1007/978-3-319-59758-4_15