Real-time Vision-based Approach for Estimating Tool-tissue Contact Force with Application to Laparoscopic Surgery

Taheri, Mohammad | 2014

737 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 48243 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Behzadipour, Saeed
  7. Abstract:
  8. Lack of force feedback during minimally invasive procedures is one of the downsides of such interventions and might result to excessive damage to surrounding tissues. The goal of the present research is to introduce a vision-based approach to estimate contact forces on soft tissues. In this approach, a model was developed in which, image of deformation of a sample soft tissue, under the jaws of laparoscopic gripper, is the input and the output is the gripper force. In this work, a FEM of soft tissue in contact with jaws of a laparoscopic tool is developed. . In the model, the effects of friction between the tool and tissue is considered which was not included in the previous studies. After that a database from different deformations of a rectangular soft tissue was generated running the FEM. Accordingly, from the geometric position of nodes of the upper surface of the soft tissue, 3 distinct geometric features from 2D deformation and 4 distinct features from 3D deformation data, were extracted. Then, two multilayer perceptron neural networks (for 2D and 3D deformation) were trained from these features and corresponding gripper force (computed from finite element simulation). Neural network results showed that contact forces of the FEM can be estimated with 95% accuracy. In order to evaluate the model, the results of some experiments from a previous study were used. In those experiments, 2D and 3D deformation of a Paraffin Gel sample was recorded under a probing force using optical measurement devices. The results showed that for deformations less than 40% of the initial size of the specimen, gripper force can be estimated with more than 14% accuracy
  9. Keywords:
  10. Finite Element Analysis ; Force Feedback ; Feature Extraction ; Multilayered Neural Network ; Soft Tissues Deformation ; Laparoscopic Surgery ; Geometric Features

 Digital Object List