English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Spinal fusion surgery requires highly accurate implantation of pedicle screwimplants, which must be conducted in critical proximity to vital structureswith a limited view of anatomy. Robotic surgery systems have been proposed toimprove placement accuracy, however, state-of-the-art systems suffer from thelimitations of open-loop approaches, as they follow traditional concepts ofpreoperative planning and intraoperative registration, without real-timerecalculation of the surgical plan. In this paper, we propose an intraoperativeplanning approach for robotic spine surgery that leverages real-timeobservation for drill path planning based on Safe Deep Reinforcement Learning(DRL). The main contributions of our method are (1) the capability to guaranteesafe actions by introducing an uncertainty-aware distance-based safety filter;and (2) the ability to compensate for incomplete intraoperative anatomicalinformation, by encoding a-priori knowledge about anatomical structures with anetwork pre-trained on high-fidelity anatomical models. Planning quality wasassessed by quantitative comparison with the gold standard (GS) drill planning.In experiments with 5 models derived from real magnetic resonance imaging (MRI)data, our approach was capable of achieving 90% bone penetration with respectto the GS while satisfying safety requirements, even under observation andmotion uncertainty. To the best of our knowledge, our approach is the firstsafe DRL approach focusing on orthopedic surgeries.

Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement