TY - CHAP
AU - Rüttgers, Mario
AU - Hübenthal, Fabian
AU - Tsubokura, Makoto
AU - Lintermann, Andreas
TI - Parallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning
VL - 15581
CY - Cham
PB - Springer Nature Switzerland
M1 - FZJ-2025-01673
SN - 978-3-031-85702-7 (print), 978-3-031-85703-4 (electronic)
T2 - Lecture Notes in Computer Science
SP - 79 - 96
PY - 2025
AB - Septoplasty and turbinectomy are among the most frequent but also most debated interventions in the field of rhinology. A previously developed tool enhances surgery planning by physical aspects of respiration, i.e., for the first time a reinforcement learning (RL) algorithm is combined with large-scale computational fluid dynamics (CFD) simulations to plan anti-obstructive surgery. In the current study, an improvement of the tool’s predictive capabilities is investigated for the aforementioned types of surgeries by considering two approaches: (i) training of parallel environments is executed on multiple ranks and the agents of each environment share their experience in a pre-defined interval and (ii) for some of the state-reward combinations the CFD solver is replaced by a Gaussian process regression (GPR) model for an improved computational efficiency. It is found that employing a parallel RL algorithm improves the reliability of the surgery planning tool in finding the global optimum. However, parallel training leads to a larger number of state-reward combinations that need to be computed by the CFD solver. This overhead is compensated by replacing some of the computations with the GPR algorithm, i.e., around 6% of the computations can be saved without significantly degrading the predictions’ accuracy. Nevertheless, increasing the number of state-reward combinations predicted by the GPR algorithm only works to a certain extent, since this also leads to larger errors.
T2 - Parallel Processing and Applied Mathematics 2024
CY - 8 Sep 2024 - 11 Sep 2024, Ostrava (Czech Republic)
Y2 - 8 Sep 2024 - 11 Sep 2024
M2 - Ostrava, Czech Republic
LB - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
UR - https://juser.fz-juelich.de/record/1038857
ER -