Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

ALICE - Artificial Intelligence Catheter. Towards Autonomous Closed Loop Control of Passive Endovascular Catheters Based on Deep Reinforcement Learning

Poster presented at Emerging Learning Techniques for Robotics, Workshop at the Hamlyn Symposium on Medical Robotics, 26th June 2019, London
: Karstensen, Lennart; Pusch, Tim Philipp; Siegfarth, Marius; Behr, Tobias; Hüsener, Dominik; Pätz, Torben; Strehlow, Jan

Poster urn:nbn:de:0011-n-5525220 (2.2 MByte PDF)
MD5 Fingerprint: ea23b2793d2ffa0da290849f7c5f8c92
Created on: 30.7.2019

2019, 1 Folie
Workshop "Emerging Learning Techniques for Robotics" <2019, London>
Symposium on Medical Robotics <2019, London>
Poster, Electronic Publication
Fraunhofer IPA ()
Fraunhofer MEVIS ()
deep learning; Bestärkendes Lernen; Künstliche Intelligenz; Gefäßchirurgie; Gefäßerkrankung; Kathetertechnik

Endovascular catheters are used for state of the art therapies of many widespread diseases. Navigating them can be very laborious and so far no robotic assistance exists for passive catheters. Steer-able catheters exist, but due to their large diameter they are not suitable for many interventions. We propose a closed loop control system where a deep reinforcement learning based control algorithm steers the catheter. The algorithm is provided with live data by a tracking system. Prior to the intervention the control algorithm is trained on the simulation model and by expert demonstration. Here we present the results of our experiments, where a control algorithm learns to steer a guidewire through a simplified vascular tree. Learning is performed in the simulation model and the result transferred to the test bench. Our results show that the algorithm is able to learn catheter steering. However the simulation results cannot be transferred to the test bench directly without facing a reduced accuracy due to the test bench not having perfect states like the simulation.