Accelerated Design of HIFU Treatment Plans Using Island-Based Evolutionary Strategy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU135501" target="_blank" >RIV/00216305:26230/20:PU135501 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-43722-0_30" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-43722-0_30</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-43722-0_30" target="_blank" >10.1007/978-3-030-43722-0_30</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Accelerated Design of HIFU Treatment Plans Using Island-Based Evolutionary Strategy

Popis výsledku v původním jazyce

High Intensity Focused Ultrasound (HIFU) is an emerging technique for non-invasive cancer treatment where malignant tissue is destroyed by thermal ablation. Such a treatment consists of a series of short sonications destroying small volumes of tissue. High-quality treatment plans allow to precisely target malignant tissue and protect surrounding healthy tissue. Recently, we developed an evolutionary strategy to design such HIFU treatment plans using patient-specific material properties and a realistic thermal model. Unfortunately, the execution time was prohibitive for routine use. Here, we present an optimized evolutionary strategy based on island model parallelization and a revised fitness function implementation. The proposed improvements allow to develop a good treatment plan 4 times faster and with 5% higher success rate.

Název v anglickém jazyce

Accelerated Design of HIFU Treatment Plans Using Island-Based Evolutionary Strategy

Popis výsledku anglicky

High Intensity Focused Ultrasound (HIFU) is an emerging technique for non-invasive cancer treatment where malignant tissue is destroyed by thermal ablation. Such a treatment consists of a series of short sonications destroying small volumes of tissue. High-quality treatment plans allow to precisely target malignant tissue and protect surrounding healthy tissue. Recently, we developed an evolutionary strategy to design such HIFU treatment plans using patient-specific material properties and a realistic thermal model. Unfortunately, the execution time was prohibitive for routine use. Here, we present an optimized evolutionary strategy based on island model parallelization and a revised fitness function implementation. The proposed improvements allow to develop a good treatment plan 4 times faster and with 5% higher success rate.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Applications of Evolutionary Computation

ISBN

978-3-030-43721-3

ISSN

—

e-ISSN

—

Počet stran výsledku

16

Strana od-do

463-478

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Seville

Datum konání akce

15. 4. 2020

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

000896394100030