Autonomous guidewire navigation in a two dimensional vascular phantom

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.

Challenges of Implementing Artificial Intelligence in Interventional Radiology

“…[9][10][11][17][18][19][20][21] The proof-of-concept use cases published in this space can be loosely grouped into the following categories: workflow optimization (e.g., scheduling), 22 periprocedural imaging, treatment planning, 23 patient outcome and complication prediction, [24][25][26][27][28][29] intraprocedural support, [30][31][32] intraprocedural safety, 33,34 and intraprocedural guidance. 10,[35][36][37][38] While still in the early stages, each of these examples holds great potential and can be plausibly incorporated into IR practice in the near future.…”

Robotik im Operationssaal – (Ko‑)Operieren mit Kollege Roboter

“…B. eine autonome Kameraführung zu schaffen, die aus eigenen Erfahrungen lernt und somit ihr Verhalten für zukünftige Eingriffe optimiert [ 2 ]. Dabei beschränkt sich die Forschung nicht nur auf starre Instrumentation, wie die autonome Steuerung von flexiblen Kathetern [ 8 ] oder ein Koloskoproboter, der sich aufgrund erlernter Rotationsbewegungen durch das Kolon bewegt [ 23 ], zeigen. Bei lernenden Systemen stellt die Verarbeitung von Sensordaten, z.…”

A Simulation Framework for Magnetic Continuum Robots

“…The introduction of the Simulation Open Framework Architecture (SOFA) [21] and its BeamAdapter plugin [22] constitutes a promising option to simulate m-CRs and their interaction forces with complex and soft anatomies. This framework has already been successfully used for the automatic control of guidewires in neurovascular applications [23], [24], the design of patient-specific catheters in coronary angiography [9], and the development of training simulators for endovascular procedures [25], [26]. Though, these efforts are limited to applications using conventional, non-magnetically guided instruments.…”