Six DOF motion estimation for teleoperated flexible endoscopes using optical flow: A comparative study

Colorectal cancer is one of the leading causes of cancer-related deaths worldwide, although it can be effectively treated if detected early. Teleoperated flexible endoscopes are an emerging technology to promote participation in these preventive screenings. Real-time pose estimation is therefore essential to enable feedback to the robotic endoscope's control system. Vision-based endoscope localization approaches are a promising avenue, since they do not require extra sensors on board the endoscopes. In this work, we compare several state-of-the-art algorithms for computing the image motion (optical flow), which is then used with a supervised learning strategy to provide an accurate estimate of the 6 degree of freedom endoscope motion. The method is validated using a robotically actuated endoscope in a human colon simulator, and represents a preliminary effort towards testing with clinical video data.

[1]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[2]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[4]  Duncan Fyfe Gillies,et al.  Vision based navigation system for an endoscope , 1996, Image Vis. Comput..

[5]  H. Tian,et al.  Automatic segmentation algorithm for the extraction of lumen region and boundary from endoscopic images , 2006, Medical and Biological Engineering and Computing.

[6]  Antonis A. Argyros,et al.  Lumen detection for capsule endoscopy , 2008 .

[7]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[9]  Robin P Boushey,et al.  Colorectal cancer epidemiology: incidence, mortality, survival, and risk factors. , 2009, Clinics in colon and rectal surgery.

[10]  S. Misra,et al.  The use of the focus of expansion for automated steering of flexible endoscopes , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[11]  Gian Luca Mariottini,et al.  Wide-Baseline Dense Feature Matching for Endoscopic Images , 2013, PSIVT.

[12]  Pietro Valdastri,et al.  Advanced endoscopic technologies for colorectal cancer screening. , 2013, World journal of gastroenterology.

[13]  M. Socha,et al.  Data Processing Tasks in Wireless GI Endoscopy: Image-Based Capsule Localization & Navigation and Video Compression , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[15]  Jianfei Liu,et al.  A stable optic-flow based method for tracking colonoscopy images , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[16]  R. Webster,et al.  Advanced technologies for gastrointestinal endoscopy. , 2012, Annual review of biomedical engineering.

[17]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[18]  Gian Luca Mariottini,et al.  A Fast and Accurate Feature-Matching Algorithm for Minimally-Invasive Endoscopic Images , 2013, IEEE Transactions on Medical Imaging.

[19]  L. Sherwood.  Human Physiology : From Cells to Systems , 1989 .

[20]  Jianfei Liu,et al.  Towards designing an optical-flow based colonoscopy tracking algorithm: a comparative study , 2013, Medical Imaging.

[21]  P. Swain,et al.  Inspection of the human stomach using remote-controlled capsule endoscopy: a feasibility study in healthy volunteers (with videos). , 2011, Gastrointestinal endoscopy.

[22]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[23]  S. Kudo,et al.  Blinded nonrandomized comparative study of gastric examination with a magnetically guided capsule endoscope and standard videoendoscope. , 2012, Gastrointestinal endoscopy.

[24]  Itsuo Kumazawa,et al.  3D Polygon Mesh Compression with Multi Layer Feed Forward Neural Networks , 2003 .

[25]  Shankar M. Krishnan,et al.  A Novel Methodology for Extracting Colon ’ s Lumen from Colonoscopic Images , 2003 .

[26]  M. van der Voort,et al.  Design and evaluation of robotic steering of a flexible endoscope , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[27]  Pietro Valdastri,et al.  Image partitioning and illumination in image-based pose detection for teleoperated flexible endoscopes , 2013, Artif. Intell. Medicine.

[28]  Max Q.-H. Meng,et al.  A locomotion mechanism with external magnetic guidance for active capsule endoscope , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[29]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[30]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[31]  Stefano Stramigioli,et al.  Three-dimensional pose reconstruction of flexible instruments from endoscopic images , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[32]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[33]  P. Dario,et al.  Magnetic air capsule robotic system: proof of concept of a novel approach for painless colonoscopy , 2012, Surgical Endoscopy.

[34]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[35]  S. M. Krishnan,et al.  Closed-boundary extraction of large intestinal lumen , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.