Computational Modeling Approaches For Task Analysis In Robotic-Assisted Surgery

COMPUTATIONAL MODELING APPROACHES FOR TASK ANALYSIS INROBOTIC-ASSISTED SURGERYbyMAHTAB JAHANBANI FARDMay 2016Advisor: Dr. R. Darin Ellis Major: Industrial Engineering Degree: Doctor of Philosophy Surgery is continuously subject to technological innovations including the introduction ofrobotic surgical devices. The ultimate goal is to program the surgical robot to perform certaindifficult or complex surgical tasks in an autonomous manner. The feasibility of currentrobotic surgery systems to record quantitative motion and video data motivates developingdescriptive mathematical models to recognize, classify and analyze surgical tasks. Recentadvances in machine learning research for uncovering concealed patterns in huge data sets,like kinematic and video data, offer a possibility to better understand surgical proceduresfrom a system point of view. This dissertation focuses on bridging the gap between these twolines of the research by developing computational models for task analysis in robotic-assistedsurgery.The key step for advance study in robotic-assisted surgery and autonomous skill assess-ment is to develop techniques that are capable of recognizing fundamental surgical tasksintelligently. Surgical tasks and at a more granular level, surgical gestures, need to be quan-tified to make them amenable for further study. To answer to this query, we introduce anew framework, namely DTW-kNN, to recognize and classify three important surgical tasksincluding suturing, needle passing and knot tying based on kinematic data captured usingda Vinci robotic surgery system. Our proposed method needs minimum preprocessing that