A Domain-Adapted Machine Learning Approach for Visual Evaluation and Interpretation of Robot-Assisted Surgery Skills

• Author(s) / Creator(s)

  • Abed Soleymani
  • Xingyu Li
  • Mahdi Tavakoli

• In this study, we present an intuitive machine learningbased
  approach to evaluate and interpret surgical skills level of a
  participant working with robotic platforms. The proposed method is
  domain-adapted, i.e., jointly utilizes an end-to-end learning approach
  for smoothness detection and domain knowledge-based metrics such
  as fluidity and economy of motion for extracting skills-related features
  within a given trajectory. An advantage of our approach compared
  to similar stochastic or deep learning models is its intuitive and
  transparent manner for extraction and visualization of skills-related
  features within the data. We illustrate the performance of our
  proposed method on trials of the JIGSAWS data set as well as our
  own experimental data gathered from Phantom Premium 1.5A
  Haptic Device. This approach utilized t-SNE technique and provides
  visualized low-dimensional representation for different trials that
  highlights nuanced information within the executive task and returns
  unusual or faulty trials as outliers far away from their normal skill
  or participant clusters. This information regarding the input trajectory
  can be used for evaluation and education applications such as learning
  curve analysis in surgical assessment and training programs.

• Date created

  2022-01-01

• Subjects / Keywords

  • Machine Learning, Surgical Skills Evaluation, Ensemble Models, Contrastive Principal Component Analysis (cPCA), t-distributed Stochastic Neighbor Embedding (t-SNE)

• Type of Item

  Article (Published)

• DOI

  https://doi.org/10.7939/r3-m2x2-8b41

• License

  Attribution-NonCommercial 4.0 International