Autonomous guidewire navigation in a two dimensional vascular phantom

Karstensen L, Behr T, Pusch TP, Mathis-Ullrich F, Stallkamp J (2020)

Publication Type: Journal article

Publication year: 2020

Journal

Current Directions in Biomedical Engineering De Gruyter

Book Volume: 6

Article Number: 20200007

Journal Issue: 1

DOI: 10.1515/cdbme-2020-0007

Abstract

The treatment of cerebro- and cardiovascular diseases requires complex and challenging navigation of a catheter. Previous attempts to automate catheter navigation lack the ability to be generalizable. Methods of Deep Reinforcement Learning show promising results and may be the key to automate catheter navigation through the tortuous vascular tree. This work investigates Deep Reinforcement Learning for guidewire manipulation in a complex and rigid vascular model in 2D. The neural network trained by Deep Deterministic Policy Gradients with Hindsight Experience Replay performs well on the low-level control task, however the high-level control of the path planning must be improved further.

Authors with CRIS profile

Lennart Karstensen
Franziska Mathis-Ullrich

Involved external institutions

Fraunhofer-Institut für Produktionstechnik und Automatisierung (IPA) DE Germany (DE) Karlsruhe Institute of Technology (KIT) DE Germany (DE)

How to cite

APA:

Karstensen, L., Behr, T., Pusch, T.P., Mathis-Ullrich, F., & Stallkamp, J. (2020). Autonomous guidewire navigation in a two dimensional vascular phantom. Current Directions in Biomedical Engineering, 6(1). https://doi.org/10.1515/cdbme-2020-0007

MLA:

Karstensen, Lennart, et al. "Autonomous guidewire navigation in a two dimensional vascular phantom." Current Directions in Biomedical Engineering 6.1 (2020).

BibTeX: Download