Non-Invasive Patient Registration Based on 3D Feature Points of Vein

Non-Invasive Patient Registration Based on 3D Feature Points of Vein
Computer Assisted Surgery System; Registration; Non-invasive patient registration
Issue Date
ICCAS(International Conference on Control, Automation and System)
We proposed a new registration method based on veins. This method uses a stereo vision system and infrared light source to noninvasively extract the feature points of veins. The feature points are extracted from a 3D medical image in advance. Then, these same vein feature points are intraoperatively found in infrared stereo images. These two groups of points are then used for the proposed registration method. The results of a fundamental experiment confirmed the feasibility of the proposed method and its potential application to numerous objects. However, the registration accuracy needs to be improved to make the proposed method more useful. Our future research plans include increasing the resolution of the stereo images, improving the near infrared light source, and improving the image processing procedure to reduce the registration error. In addition, we need to improve the experimental environment. For instance, 3D vein models are preferred over 2D vein models. We also need to use a material such as a gel, which is more similar to skin, instead of a mixture of water and dye. Ultimately, we need to perform experiments in human. Lastly, although the target position error is supposed to increase with an increase in depth, we need to confirm the target position error.
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
RIS (EndNote)
XLS (Excel)


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.