Artificial Intelligence, Robotics & IoT

Minimally invasive surgery (MIS) is not currently widely used by surgeons due to its cost and complex training requirement of surgeons.

As a first step toward making MIS a more accessible technology to use is to provide the surgeon with quality images inside the patient as well as the surgical tool location automatically in real time in a common reference frame. Then provide real-time suggestions of how to navigate inside the human body in order to follow the pre-operation (pre-op) path.

The objective of this paper is to build a platform to accomplish this goal. A set of three heterogeneous asynchronous sensors is proposed to help the surgeon navigate surgical tools inside the human body. The proposed system consists of a Laser Range Scanner (LRS) to emulate the CT/MRI whose image is used to generate the pre-op path by the surgeons, an Electromagnetic Tracking System (EMTS) that provides three dimensional position and orientation of the surgical tool inside the human body, and a small size camera attached to the EMTS to provide real-time images. This set of sensors provides all the necessary information needed for MIS navigation.

The sensors have a different data rate, different reference frames, and independent clocks. A prerequisite for successful navigation is to represent all the sensors data in a common reference frame. The focus of this paper is on offline calibration of the three sensors, i.e. before the surgical device is inserted in the human body. This is a pre-requisite for real-time navigation inside the human body.

The proposed off-line calibration technique was tested using experimental laboratory data. The accuracy of the calibration process was promising with an average error of 0.1081mm and 0.0872mm along the x and y directions, respectively, in the 2D camera image.

The next phases of this work will be highlighted in the presentation.