Objective Evaluation of Laparoscopic Surgical Skills Using Hidden Markov Models Based on Haptic Information and Tool/Tissue Interactions

Rosen, J. and Solazzo, M. and Hannaford, B. and Sinanan, M. (2000) Objective Evaluation of Laparoscopic Surgical Skills Using Hidden Markov Models Based on Haptic Information and Tool/Tissue Interactions. American College of Surgeons Annual Meeting - Washington State Chapter.

[img] Text
CP_05.pdf

Download (234kB)
Official URL: http://brl.ee.washington.edu/BRL_Pubs/Pdfs/Rep135....

Abstract

Laparoscopic surgical skills evaluation of surgery residents is usually a subjective process, carried out in the operating room by senior surgeons. By its nature, this process is performed using fuzzy criteria.The objective of the current study was to develop and assess an objectivelaparoscopic surgical skill scale using Hidden Markov Models (HMM) basedon haptic information, tool/tissue interactions and visual taskdecomposition. Methods: Eight subjects (six residents: first year surgical residents 2xR1, third year surgical residents 2xR3, fifth year surgical residents 2xR5; and two expert laparoscopic surgeons: 2xES) performed laparoscopic cholecystectomy following a specific 7 step protocolon a pig. An instrumented laparoscopic grasper equipped with a three-axisforce/torque sensor was used to measure the forces and torques at thehand/tool interface synchronized with a video of the tool operativemaneuvers. A synthesis of frame-by-frame video analysis was used to define14 different types of tool/tissue interactions, each one associated withunique force/torque (F/T) signatures. HMMs were developed for each subjectrepresenting the surgical skills in terms of haptic information andtool tissue interactions. The statistical distance between the HMMSrepresenting residents at different levels of their training and the HMMsof expert surgeons were calculated in order to evaluate the learning curveof selected steps of laparoscopic cholecystectomy. Results: The objectivelaparoscopic surgical skill learning-curve showed significant differencesbetween all skill levels. The major differences between skill levelswere: (i) magnitudes of F/T applied, (ii) types of tool/tissue interactionsused and with the transition between them, and (iii) time intervalsspent in each tool/tissue interaction and the overall completion time.The HMM analysis showed that the greatest difference in performance wasbetween R1 and R3 and then decreased as the level of expertise increased.The objective evidence for a learning curve indicates that the surgicalresidents appear to acquire a major portion of their laparoscopic surgicalcapabilities between the first and the third years of their residency training.

Item Type: Article
Subjects: Z Other
Divisions: Department of Electrical Engineering
Depositing User: Muneaki Miyasaka
Date Deposited: 27 Jul 2015 23:07
Last Modified: 27 Jul 2015 23:07
URI: http://brl.ee.washington.edu/eprints/id/eprint/197

Actions (login required)

View Item View Item