Objective Laparoscopic Skills Assessments of Surgical Residents Using HiddenMarkov Models Based on Haptic Information and Tool/Tissue Interactions

Rosen, J. and Solazzo, M. and Hannaford, B. and Sinanan, M. (2001) Objective Laparoscopic Skills Assessments of Surgical Residents Using HiddenMarkov Models Based on Haptic Information and Tool/Tissue Interactions. Studies in Health Technology and Informatics - Medicine Meets Virtual Reality, 81. pp. 417-423.

[img] Text

Download (36kB)
Official URL: http://brl.ee.washington.edu/BRL_Pubs/Pdfs/Rep145....


Laparscopic surgical skills evaluation of surgery residents is usually asubjective 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 studentwas to develop and assess an objective laparoscopic surgical skill scale using HiddenMarkov Models (HMM) based on haptic information, tool/tissue interactions and visualtask decomposition. Methods: Eight subjects (six surgical trainees: first yearsurgical residents 2xR1, third year surgical residents 2xR3, fifth year surgical residents 2xR5, and two expert laparoscopic surgeons 2xES)performed laparoscopic cholecystectomyfollowing a specific 7 steps protocol on a pig. An instrumented laparoscopic grasperequipped with a three-axis force/torque sensor located at the proximal end with an additional force sensor located on the handle, was used to measure the forces and torques. The hand/tool interface force/torque data was synchronized with a video of the tool operative maneuvers. A synthesis of frame-by-frame video analysis was used todefine 14 different tyupes of tool/tissue interactions, each one associated with uniqueforce/torque (F/T) signatures. HMMs were developed for each subjectrepresenting the surgical skills by defining the various tool/tissue interactions as states andthe associated F/T signatures as observations. The statistical distance between theHMMs representing residents at different levels of their training and the HMMs ofexpert surgeons were calculated in order to generate a learning curve of selected stepsduring laparoscopic cholecystectomy. Results: Comparison of HMMs betweengroups showed significant differences between all skill levels, supporting the objective definition of a learning curve. The major differences between skill levels were: (i) magnitudes of F/T applied, (ii) types of tool/tissue interactions used and the transition between them and (iii) time intervals spent in each tool/tissue interaction and the overall completion time. The objective HMM analysis showed that the greatest difference in performance was between R1 and R3 groups and then decreased as the level ofexpertise increased, suggesting that significant laparoscopic surgical capability develops between the first and the third years of their residency training. The power of themethodology using HMM for objective surgical skill assessment arises from the fact that it compiles enormous amount of data regarding different aspects of surgical skill into a very compact model that can be translated into a single number representing the distance from expert performance. Moreover, the methodology is not limited to in-vivo condition as demonstrated in the current study. It can be extended to other modalities such as measuringperformance in surgical simulators and robotic systems.

Item Type: Article
Subjects: C Surgical Robots > C Surgical Robots(General)
C Surgical Robots > CC Preventing Tissue Damage
Divisions: Department of Electrical Engineering
Depositing User: Nava Aghdasi
Date Deposited: 12 Aug 2015 20:16
Last Modified: 12 Aug 2015 20:16
URI: http://brl.ee.washington.edu/eprints/id/eprint/252

Actions (login required)

View Item View Item