Episode Classification for the Analysis of Tissue/Instrument Interaction with Multiple Visual Cues

The assessment of surgical skills for Minimally Invasive Surgery (MIS) has traditionally been conducted with visual observation and objective scoring. This paper presents a practical framework for the detection of instrument/tissue interaction from MIS video sequences by incorporating multiple visual cues. The proposed technique investigates the characteristics of four major events involved in MIS procedures including idle, retraction, cauterisation and suturing. Constant instrument tracking is maintained and multiple visual cues related to shape, deformation, changes in light reflection and other low level images featured are combined in a Bayesian framework to achieve an overall frame-by-frame classification accuracy of 77% and episode classification accuracy of 85%.

[1]  Jeffrey D. Smith,et al.  Finite element methods for real-time haptic feedback of soft-tissue models in virtual reality simulators , 2001, Proceedings IEEE Virtual Reality 2001.

[2]  Jean-Claude Latombe,et al.  Real-time simulation of deformable objects: tools and application , 2001, Proceedings Computer Animation 2001. Fourteenth Conference on Computer Animation (Cat. No.01TH8596).

[3]  Gerrit Voss,et al.  Enhanced training environment for minimally invasive surgery , 2001, Proceedings Tenth IEEE International Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises. WET ICE 2001.

[4]  Cameron N. Riviere,et al.  An Active Hand-Held Instrument for Enhanced Microsurgical Accuracy , 2000, MICCAI.

[5]  I. Brown,et al.  Engineering design of a virtual reality simulator for gynaecological endoscopy , 2001, The Seventh Australian and New Zealand Intelligent Information Systems Conference, 2001.

[6]  Ara Darzi,et al.  Simulation and skills assessment , 2001, Proceedings International Workshop on Medical Imaging and Augmented Reality.

[7]  Blake Hannaford,et al.  The BlueDRAGON - a system for measuring the kinematics and dynamics of minimally invasive surgical tools in-vivo , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[8]  Mubarak Shah,et al.  Shape from shading using linear approximation , 1994, Image Vis. Comput..

[9]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[10]  R. Satava,et al.  Virtual reality as a metric for the assessment of laparoscopic psychomotor skills , 2002, Surgical Endoscopy And Other Interventional Techniques.

[11]  Michael J. Black,et al.  Recognizing temporal trajectories using the condensation algorithm , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.