Evolutionary Exploration of an Ultrasound Propagation Predictor Neural Net

article in a collection out of WoS and Scopus

English

To find an optimal treatment plan for an focused ultrasound based procedure, a multitude of computationally expensive simulations need to be evaluated, often thousands of times. Recent renaissance of machine learning technologies could provide a solution to this problem, as a recently published article presented a Physics Informed Neural Net to predict Acoustic Propagation through a human skull. The learned optimizer showed an excellent performance on the test set, and is capable of generalization well outside the training examples, including to much larger computational domains, and more complex source and sound speed distributions. The utilized UNet architecture, however, was marked by the authors as the uncertain part of the design with a real possibility to improve upon. To explore their design more deeply and to confirm their theories, we made an attempt to improve the solver by use of an evolutionary algorithm, challenging the importance of different building blocks and authors original choices and decisions regarding the architecture. Two experiments using Cartesian Genetic Programming had been ran, first to try and optimize the original nets architecture, and a second one, to study the effects of the employed multi-resolution encoding on precision of the network. Our exploitative experiments managed to find a network with approximately an order of magnitude better RMSE for the predictor, using the same validation set as the original solver. The exploration evolution process then showed the use of 4 resolution layers as valid, and provided topics for further research on the effects of the memory blocks and convolution kernel sizes.

Evolutionary Optimisation, Evolutionary Design, Ultrasound Propagation Predictor, Cartesian Genetic Programming

CHLEBÍK, J.; JAROŠ, J.

1. 1. 2026

Brno

16

https://www.fit.vut.cz/research/publication/12880/

chlebik_evostar23.pdf