Autonomous navigation of a magnetic colonoscope using force sensing and a heuristic search algorithm

Abstract

This paper presents an autonomous navigation system for cost-effective magnetic-assisted colonoscopy, employing force-based sensors, an actuator, a proportional–integrator controller and a real-time heuristic searching method. The force sensing system uses load cells installed between the robotic arm and external permanent magnets to derive attractive force data as the basis for real-time surgical safety monitoring and tracking information to navigate the disposable magnetic colonoscope. The average tracking accuracy on magnetic field navigator (MFN) platform in x-axis and y-axis are 1.14 ± 0.59 mm and 1.61 ± 0.45 mm, respectively, presented in mean error ± standard deviation. The average detectable radius of the tracking system is 15 cm. Three simulations of path planning algorithms are presented and the learning real-time A* (LRTA*) algorithm with our proposed directional heuristic evaluation design has the best performance. It takes 75 steps to complete the traveling in unknown synthetic colon map. By integrating the force-based sensing technology and LRTA* path planning algorithm, the average time required to complete autonomous navigation of a highly realistic colonoscopy training model on the MFN platform is 15 min 38 s and the intubation rate is 83.33%. All autonomous navigation experiments are completed without intervention by the operator.

Fundamentals of Bowel Cancer for Biomedical Engineers

“…Aside the invention of robotic endoscopy systems, the study of robotic engineering systems and artificial intelligence has also led to the development of autonomous control system for endoscopy procedures. 46 , 78 , 149 Compared to the manually controlled endoscopes, autonomous endoscopes have been found to be more effective in terms of improved patient safety, shorter travel time and higher diagnostic rate, see e.g., References 46 , 78 , and 153 .…”

Automatic hands-free visualization of a six degrees of freedom agent within a complex anatomical space

“…This study uses robot kinematics variables as state inputs; however, navigation through the straight segments was slow, and navigation through bends proved awkward due to the robot's size. Several studies have focused on magnetic guided endoscopes [15,31,36], where external actuating magnetic fields generated by electromagnetic coils or permanent magnets control the motion of the magnetic tip. In [31], navigation by following simple predefined trajectories is presented; hence extending this method to complex non-linear trajectories is challenging.…”

“…In [31], navigation by following simple predefined trajectories is presented; hence extending this method to complex non-linear trajectories is challenging. Heuristic path planning algorithms are used in [36] to generate a feasible path in a colon map. This approach employs force-based realtime sensing to guide navigation.…”

“…This is especially true for the navigation phase, which could be one of the most time-consuming step of a routine colonoscopy procedure [15]. Indeed, autonomous navigation would allow the endoscopists to focus on the clinical aspect of the procedure rather than the manual control of endoscope, potentially improving the overall procedure outcome and reducing the training time [36]. During the navigation phase, the clinician mainly uses visual feedback from the camera placed on the tip of the endoscope to advance through the lumen [156].…”

“…According to [15], the features required to perform this task are the same as level 1, as the user remains in continuous control. [15]) -the colonoscope is steered autonomously trough the lumen, thanks to computer vision techniques [27] or other methods [36]. The control strategy generated by the robotic system could be overridden by the operator which needs to constantly supervise the motion of the robot and approve its decision [15,26,37].…”