Loading...

Recognition of Instrument Position in Laparoscopic Images in Order to Control the Cameraman Robot

Amini Khoiy, Keyvan | 2010

371 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40680 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Farahmand, Farzam; Bagheri Shouraki, Saeed
  7. Abstract:
  8. Laparoscopic surgery is a branch of minimally invasive surgery that is implemented in the abdominal cavity. This kind of surgery is conducted using surgical instruments that are inserted into the abdomen through some small incisions created on its wall and the necessary vision is provided for the surgeon using a laparoscope lens that is inserted through the first created incision. In recent years, because of its advantages, controlling and manipulation of the lens is done using some robots instead of surgeon assistant. To facilitate the controlling procedure of these robots for the surgeon, several controlling modes such as keyboard, foot switch, and voice commands are presented. Robolens is such a surgeon assistant cameraman robot that now is under clinical use and could be manipulated using mentioned controlling modes. There is another idea that creates the feedback for intelligent control of the robot, using detected instrument position in the laparoscopic images. The purpose of this project was to add such an intelligent controlling mode to this robot, so that the surgeon could control the robot motion using one’s instrument.
    To reach this aim, several studies was done on the available object detection and instrument tracking methods and their advantages and disadvantages were determined. Finally a color based method was chosen that segments the image using the compound Value plus Saturation histogram and Hue component analysis. Then the selected method was described in detail and the final algorithm was designed. Finally, the designed algorithm was implemented in VC++ programming environment. Testing the algorithm on the real laparoscopic clips shows that, it could detect the correct instrument tip position in 97% at 20 frames per second. At last, the proposed algorithm was implied in simulated conditions on laparoscopic phantoms to control the Robolens, and it reached good results.
  9. Keywords:
  10. Image Processing ; Asistant Surgury Robot ; Laparoscopic Surgery ; Image Segmentation

 Digital Object List

 Bookmark

No TOC