Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach

Lin Chen, Qiang Zhang, Qiongjie Tian, Baoxin Li

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

Abstract

In recent years, surgical simulation has emerged at the forefront of new technologies for improving the education and training of surgical residents. To objectively evaluate the surgical skills of the trainees and reduce the training cost, an automated method for rating the performance of the operator is critical. However, automated evaluation of surgical skills in a video-based system, e.g., the FLS trainer box, is still a challenging task, both due to the lack of reliable visual features and the lack of analysis tools that bridge the semantic gap between the low-level visual features and the high-level surgical skills. This study attempts to find a latent space for the visual features for supporting more meaningful analysis of surgical skills. The approach employs multi-modality fusion and Canonical Correlation Analysis as the key techniques. Experiments were designed to evaluate the proposed approach. The results suggest that this is a promising direction.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
PublisherIOS Press
Pages66-70
Number of pages5
Volume184
DOIs
StatePublished - 2013

Fingerprint

Semantics
Fusion reactions
Education
Learning
Technology
Costs and Cost Analysis
Costs
Experiments
Direction compound

Keywords

  • motion analysis
  • motor skill evaluation
  • Surgical training

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Chen, L., Zhang, Q., Tian, Q., & Li, B. (2013). Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach. In Studies in Health Technology and Informatics (Vol. 184, pp. 66-70). IOS Press. https://doi.org/10.3233/978-1-61499-209-7-66

Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach. / Chen, Lin; Zhang, Qiang; Tian, Qiongjie; Li, Baoxin.

Studies in Health Technology and Informatics. Vol. 184 IOS Press, 2013. p. 66-70.

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

Chen, L, Zhang, Q, Tian, Q & Li, B 2013, Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach. in Studies in Health Technology and Informatics. vol. 184, IOS Press, pp. 66-70. https://doi.org/10.3233/978-1-61499-209-7-66
Chen L, Zhang Q, Tian Q, Li B. Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach. In Studies in Health Technology and Informatics. Vol. 184. IOS Press. 2013. p. 66-70 https://doi.org/10.3233/978-1-61499-209-7-66
Chen, Lin ; Zhang, Qiang ; Tian, Qiongjie ; Li, Baoxin. / Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach. Studies in Health Technology and Informatics. Vol. 184 IOS Press, 2013. pp. 66-70
@inproceedings{e3a5b1c445e04235816165efe94e69bb,
title = "Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach",
abstract = "In recent years, surgical simulation has emerged at the forefront of new technologies for improving the education and training of surgical residents. To objectively evaluate the surgical skills of the trainees and reduce the training cost, an automated method for rating the performance of the operator is critical. However, automated evaluation of surgical skills in a video-based system, e.g., the FLS trainer box, is still a challenging task, both due to the lack of reliable visual features and the lack of analysis tools that bridge the semantic gap between the low-level visual features and the high-level surgical skills. This study attempts to find a latent space for the visual features for supporting more meaningful analysis of surgical skills. The approach employs multi-modality fusion and Canonical Correlation Analysis as the key techniques. Experiments were designed to evaluate the proposed approach. The results suggest that this is a promising direction.",
keywords = "motion analysis, motor skill evaluation, Surgical training",
author = "Lin Chen and Qiang Zhang and Qiongjie Tian and Baoxin Li",
year = "2013",
doi = "10.3233/978-1-61499-209-7-66",
language = "English (US)",
volume = "184",
pages = "66--70",
booktitle = "Studies in Health Technology and Informatics",
publisher = "IOS Press",

}

TY - GEN

T1 - Learning skill-defining latent space in video-based analysis of surgical expertise-a multi-stream fusion approach

AU - Chen, Lin

AU - Zhang, Qiang

AU - Tian, Qiongjie

AU - Li, Baoxin

PY - 2013

Y1 - 2013

N2 - In recent years, surgical simulation has emerged at the forefront of new technologies for improving the education and training of surgical residents. To objectively evaluate the surgical skills of the trainees and reduce the training cost, an automated method for rating the performance of the operator is critical. However, automated evaluation of surgical skills in a video-based system, e.g., the FLS trainer box, is still a challenging task, both due to the lack of reliable visual features and the lack of analysis tools that bridge the semantic gap between the low-level visual features and the high-level surgical skills. This study attempts to find a latent space for the visual features for supporting more meaningful analysis of surgical skills. The approach employs multi-modality fusion and Canonical Correlation Analysis as the key techniques. Experiments were designed to evaluate the proposed approach. The results suggest that this is a promising direction.

AB - In recent years, surgical simulation has emerged at the forefront of new technologies for improving the education and training of surgical residents. To objectively evaluate the surgical skills of the trainees and reduce the training cost, an automated method for rating the performance of the operator is critical. However, automated evaluation of surgical skills in a video-based system, e.g., the FLS trainer box, is still a challenging task, both due to the lack of reliable visual features and the lack of analysis tools that bridge the semantic gap between the low-level visual features and the high-level surgical skills. This study attempts to find a latent space for the visual features for supporting more meaningful analysis of surgical skills. The approach employs multi-modality fusion and Canonical Correlation Analysis as the key techniques. Experiments were designed to evaluate the proposed approach. The results suggest that this is a promising direction.

KW - motion analysis

KW - motor skill evaluation

KW - Surgical training

UR - http://www.scopus.com/inward/record.url?scp=84879533072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879533072&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-209-7-66

DO - 10.3233/978-1-61499-209-7-66

M3 - Conference contribution

C2 - 23400132

AN - SCOPUS:84879533072

VL - 184

SP - 66

EP - 70

BT - Studies in Health Technology and Informatics

PB - IOS Press

ER -