Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Deep Reinforcement Learning for the Navigation of Neurovascular Catheters

: Behr, Tobias; Pusch, Tim Philipp; Siegfarth, Marius; Hüsener, Dominik; Mörschel, Tobias; Karstensen, Lennart

Volltext urn:nbn:de:0011-n-5651165 (526 KByte PDF)
MD5 Fingerprint: b395271d60be85d0fc3d5f4a9934fe20
(CC) by
Erstellt am: 15.11.2019

Current directions in biomedical engineering 5 (2019), Nr.1, S.5-8
ISSN: 2364-5504
Zeitschriftenaufsatz, Elektronische Publikation
Fraunhofer IPA ()
deep learning; Bestärkendes Lernen; Herzinfarkt; Medizintechnik; Katheter

Endovascular catheters are necessary for state-of-the-art treatments of life-threatening and time-critical diseases like strokes and heart attacks. Navigating them through the vascular tree is a highly challenging task. We present our preliminary results for the autonomous control of a guidewire through a vessel phantom with the help of Deep Reinforcement Learning. We trained Deep-Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG) agents on a simulated vessel phantom and evaluated the training performance. We also investigated the effect of the two enhancements Hindsight Experience Replay (HER) and Human Demonstration (HD) on the training speed of our agents. The results show that the agents are capable of learning to navigate a guidewire from a random start point in the vessel phantom to a random goal. This is achieved with an average success rate of 86.5% for DQN and 89.6% for DDPG. The use of HER and HD significantly increases the training speed. The results are promising and future research should address more complex vessel phantoms and the use of a combination of guidewire and catheter.