Local Structure Prediction with Convolutional Neural Networks for Multimodal Brain Tumor Segmentation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081731%3A_____%2F16%3A00507004" target="_blank" >RIV/68081731:_____/16:00507004 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-42016-5_6" target="_blank" >http://dx.doi.org/10.1007/978-3-319-42016-5_6</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-42016-5_6" target="_blank" >10.1007/978-3-319-42016-5_6</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Local Structure Prediction with Convolutional Neural Networks for Multimodal Brain Tumor Segmentation

Popis výsledku v původním jazyce

Most medical images feature a high similarity in the intensities of nearby pixels and a strong correlation of intensity profiles across different image modalities. One way of dealing with - and even exploiting - this correlation is the use of local image patches. In the same way, there is a high correlation between nearby labels in image annotation, a feature that has been used in the ´local structure predictiol´of local label patches. In the present study we test this local structure prediction approach for 3D segmentation tasks, systematically evaluating different parameters that are relevant for the dense annotation of anatomical structures. We choose convolutional neural network as learning algorithm, as it is known to be suited for dealing with correlation between features. We evaluate our approach on the public BRATS2014 data set with three multimodal segmentation tasks, being able to obtain state-of-the-art results for this brain tumor segmentation data set consisting of 254 multimodal volumes with computing time of only 13s per volume

Název v anglickém jazyce

Local Structure Prediction with Convolutional Neural Networks for Multimodal Brain Tumor Segmentation

Popis výsledku anglicky

Most medical images feature a high similarity in the intensities of nearby pixels and a strong correlation of intensity profiles across different image modalities. One way of dealing with - and even exploiting - this correlation is the use of local image patches. In the same way, there is a high correlation between nearby labels in image annotation, a feature that has been used in the ´local structure predictiol´of local label patches. In the present study we test this local structure prediction approach for 3D segmentation tasks, systematically evaluating different parameters that are relevant for the dense annotation of anatomical structures. We choose convolutional neural network as learning algorithm, as it is known to be suited for dealing with correlation between features. We evaluate our approach on the public BRATS2014 data set with three multimodal segmentation tasks, being able to obtain state-of-the-art results for this brain tumor segmentation data set consisting of 254 multimodal volumes with computing time of only 13s per volume

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

30210 - Clinical neurology

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lecture Notes in Computer Science

ISBN

978-3-319-42015-8

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

13

Strana od-do

59-71

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Munich

Datum konání akce

9. 10. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000389404000006