Recurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch - Takeaways - MDSpire

Recurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch

  • By

  • Lennart Karstensen

  • Jacqueline Ritter

  • Johannes Hatzl

  • Floris Ernst

  • Jens Langejürgen

  • Christian Uhl

  • Franziska Mathis-Ullrich

  • May 28, 2023

  • 0 min

Share

  • 1

    Endovascular interventions involve navigating a guidewire and catheter to treat vascular diseases like heart attacks and strokes.

  • 2

    Autonomous navigation systems can reduce surgeon radiation exposure and cognitive strain during endovascular procedures.

  • 3

    Learning-based controllers using neural networks face challenges in generalizing to unique patient vascular geometries.

  • 4

    This study utilizes recurrent neural networks to enhance the autonomous navigation of guidewires in varying aortic arch geometries.

  • 5

    The controller's performance is evaluated in randomized aortic arch models without prior geometry information during training.

Original Source(s)

Recurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch

  • by Lennart Karstensen, Jacqueline Ritter, Johannes Hatzl, Floris Ernst, Jens Langejürgen, Christian Uhl, Franziska Mathis-Ullrich

  • May 28, 2023

Related Content

Adaptive sensitivity-fisher regularization for heterogeneous transfer learning of vascular segmentation in laparoscopic videos

Automatic robotic doppler sonography of leg arteries

Amputation Rates Rose in Opioid-Related Hospitalizations

National inpatient analysis found steeper increases in amputations during opioid-related hospitalizations, particularly in the Northeast and West.