Telementoring for Laparoscopic Surgery Training

Laparoscopic surgery is a difficult skill to learn. Many hospitals in major cities, rural areas of the Unites States, and other countries have the basic infrastructure to teach and perform laparoscopic procedures, but what they lack is expert surgeons and/or access to specialized labs. In such areas, trainees often learn on FLS type methods and then go directly to operating on humans. Tele-learning and tele-medicine can help reduce such disparities by bringing expert knowledge to locations that do not have resident experts and allowing remote access to specialized facilities. Robotics, information databases, and computer networks have reached a level where low-cost tele-mentoring and tele- learning solutions are now possible. Towards these goals, we have developed the UCLA Laparobot, a master-slave robot that can be used to for the remote training of laparoscopic surgeons. This a result of a collaboration between the Center for Advanced Surgical and Interventional Technologies (CASIT), the Department of Computer Science, and the Department of Mechanical and Aerospace Engineering at UCLA.

Video demo:

Selected publications:

  1. 1.Support Vector Machines Improve the Accuracy of Performance Evaluation of Laparoscopic Training Tasks”, Brian Allen, Vasile Nistor, Erik Dutson, Greg Carman, Catherine Lewis, Petros Faloutsos, Surgical Endoscopy, 24(1), PMID: 19533237,Springer New York, pp. 170-178, 2010.


    Despite technological advances in the tracking of surgical motions, automatic evaluation of laparoscopic skills remains remote. A new method is proposed that combines multiple discrete motion analysis metrics. This new method is compared with previously proposed metric combination methods and shown to provide greater ability for classifying novice and expert surgeons.

    Methods: For this study, 30 participants (four experts and 26 novices) performed 696 trials of three training tasks: peg transfer, pass rope, and cap needle. Instrument motions were recorded and reduced to four metrics. Three methods of combining metrics into a prediction of surgical competency (summed-ratios, z-score normalization, and support vector machine [SVM]) were compared. The comparison was based on the area under the receiver operating characteristic curve (AUC) and the predictive accuracy with a previously unseen validation data set.

    Results: For all three tasks, the SVM method was superior in terms of both AUC and predictive accuracy with the validation set. The SVM method resulted in AUCs of 0.968, 0.952, and 0.970 for the three tasks compared.

  2. 2.Laparoscopic Surgical Robot for Remote in Vivo Training”, Brian Allen, Brett Jordan, Will Pannell, Catherine Lewis, Erik Dutson, Petros Faloutsos, Advanced Robotics, special issue on Minimally Invasive and Endoscopic surgical Robot System, The Robotic Society of Japan, 2010, in press.


    he Laparobot is a tele-operated robot designed specifically for training surgeons in advanced laparoscopic techniques. The Laparobot allows a student to practice surgery on a remotely located animal. The system uses standard laparoscopic tools for both the student’s control interface and for performing the in vivo surgery, thereby providing a realistic training platform for non-robotic laparoscopic surgery. By allowing students to practice surgery remotely, animal models become more accessible and less expensive, and can replace learning on human patients. The Laparobot addresses problems inherent in designing a low-cost, tele-operated robot.