Hidden markov Models of Minimally Invasive Surgery

Rosen, J. and Richards, C. and Hannaford, B. and Sinanan, M. (2000) Hidden markov Models of Minimally Invasive Surgery. Studies in Health Technology and Informatics - Medicine Meets Virtual Reality, 70. pp. 279-285.

[img] Text

Download (140kB)
Official URL: http://brl.ee.washington.edu/BRL_Pubs/Pdfs/Rep134....


A crucial process in surgical education is to evaluate the level of surgical skills. For laparoscopic surgery, skill evaluation is traditionally performed subjectively by experts grading a video of a procedure performed by a student. By its nature, this process is performed using fuzzy criteria. The objective of the current study was to develop and assess a skill scale using Discrete Hidden Markov Models (DHMM). Ten surgeons (5 Novice Surgeons - NS; 5 Expert Surgeons) performed a cholecystectomy and Nissen fundoplication in a porcine model. An instrumented laparoscopic grasper equipped with a three-axis force/torque sensor was used to measure the forces/torques at the hand/tool interface synthronized with a video of the tool operative maneuvers. A synthesis of frame-by-frame video analysis and a vector quantization algorithm, defined force/torque signatures for 14 types of tool/tissue interactions. From each stop of the surgical procedures, two DHMM were developed representing the performance of 3 surgeons randomly selected from the 5 in the ES and NS groups. The data obtained by the remaining 2 surgeons in each group were used for evaluating the performance scale. The final result was a surgical performance index which represented a ratio of statistical similarity between the examined surgeon's DHMM and the DHMM of NS and ES. The difference between the performance index value, for a surgeon under study, and the NS/ES boundary, was considered to indicate the level of expertise in the surgeon'sown group. Using the index, 87.5 of the surgical procedures werecorrectly classified into the NS and ES groups. The 12.5 of the proceduresthat were misclassified were performed by the ES and classified as NS.However, in these cases the performance index values were very close tothe NS/ES boundary. Preliminary data suggest that a performance indexbased on DHMM and force/torque signatures provides an objective means ofdistinguishing NS from ES. In addition, this methodology can be furtherapplied to evaluate haptic virtual reality surgical simulators forimproving realism in surgical education.

Item Type: Article
Subjects: Z Other
Divisions: Department of Electrical Engineering
Depositing User: Muneaki Miyasaka
Date Deposited: 27 Jul 2015 23:44
Last Modified: 27 Jul 2015 23:44
URI: http://brl.ee.washington.edu/eprints/id/eprint/199

Actions (login required)

View Item View Item