Journal
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
Volume 64, Issue 9, Pages 2025-2041Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TBME.2016.2647680
Keywords
Activity recognition; benchmark robotic dataset; kinematics and video; surgical motion
Categories
Funding
- NIH [1R01-DE025265]
- NSF [0534359, IIS-0748338, OIA 0941362, CSN 0931805, DGE-1232825]
- Sloan Foundation
- NSF Graduate Research Fellowship Program
- Talentia Fellowship Program of the Andalusian Regional Ministry of Economy, Innovation and Science
- European Research Council grant VideoWorld
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [0534359] Funding Source: National Science Foundation
Ask authors/readers for more resources
Objective: State-of-the-art techniques for surgical data analysis report promising results for automated skill assessment and action recognition. The contributions of many of these techniques, however, are limited to studyspecific data and validation metrics, making assessment of progress across the field extremely challenging. Methods: In this paper, we address two major problems for surgical data analysis: First, lack of uniform-shared datasets and benchmarks, and second, lack of consistent validation processes. We address the former by presenting the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), a public dataset that we have created to support comparative research benchmarking. JIGSAWS contains synchronized video and kinematic data from multiple performances of robotic surgical tasks by operators of varying skill. We address the latter by presenting a well-documented evaluation methodology and reporting results for six techniques for automated segmentation and classification of time-series data on JIGSAWS. These techniques comprise four temporal approaches for joint segmentation and classification: hidden Markov model, sparse hidden Markov model (HMM), Markov semi-Markov conditional random field, and skip-chain conditional random field; and two feature-based ones that aim to classify fixed segments: bag of spatiotemporal features and linear dynamical systems. Results: Most methods recognize gesture activities with approximately 80% overall accuracy under both leave-one-super-trial-out and leaveone- user-out cross-validation settings. Conclusion: Current methods show promising results on this shared dataset, but room for significant progress remains, particularly for consistent prediction of gesture activities across different surgeons. Significance: The results reported in this paper provide the first systematic and uniform evaluation of surgical activity recognition techniques on the benchmark database.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available