Publication Details
Distributed Evolutionary Design of HIFU Treatment Plans
Evolutionary strategy, Island model, Farmer-Workers model, HIFU, Treatment
planning, k-Wave
High-Intensity Focused Ultrasound (HIFU) is a modern technique for non-invasive,
non-ionising cancer treatment where malignant tissue is destroyed by thermal
ablation. To perform such treatment, a plan consisting of a series of short
sonications must be created. In recent years, a realistic thermal model using
patient-specific materials was introduced. Thanks to this, an evolutionary
strategy was employed to design such HIFU treatment plans. However, despite the
improvements, the execution time of such a model was too prohibitive to allow
routine use. In this paper, we present a new round of optimizations aimed at
improving the performance of the thermal model and the evolutionary strategy. The
experiments carried out in other works using an evolutionary strategy based on
the island model are repeated with up to 4 times decrease in total computation
time. This enables new experiments using a much higher number of sonications are
introduced and evaluated. Lastly, a new real-life inspired benchmark is presented
and the experiments repeated.
@misc{BUT175775,
author="Jakub {Chlebík} and Jiří {Jaroš}",
title="Distributed Evolutionary Design of HIFU Treatment Plans",
booktitle="GECCO 2021 Companion - Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion",
year="2021",
pages="297--298",
publisher="Association for Computing Machinery",
address="Lille",
doi="10.1145/3449726.3459550",
isbn="978-1-4503-8351-6",
url="https://dl.acm.org/doi/10.1145/3449726.3459550",
note="presentation, poster"
}