Cargando…
A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery
Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-wei...
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5630188/ https://www.ncbi.nlm.nih.gov/pubmed/28985229 http://dx.doi.org/10.1371/journal.pone.0185844 |
_version_ | 1783269177894633472 |
---|---|
author | Liu, Yan Stojadinovic, Strahinja Hrycushko, Brian Wardak, Zabi Lau, Steven Lu, Weiguo Yan, Yulong Jiang, Steve B. Zhen, Xin Timmerman, Robert Nedzi, Lucien Gu, Xuejun |
author_facet | Liu, Yan Stojadinovic, Strahinja Hrycushko, Brian Wardak, Zabi Lau, Steven Lu, Weiguo Yan, Yulong Jiang, Steve B. Zhen, Xin Timmerman, Robert Nedzi, Lucien Gu, Xuejun |
author_sort | Liu, Yan |
collection | PubMed |
description | Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases. |
format | Online Article Text |
id | pubmed-5630188 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-56301882017-10-20 A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery Liu, Yan Stojadinovic, Strahinja Hrycushko, Brian Wardak, Zabi Lau, Steven Lu, Weiguo Yan, Yulong Jiang, Steve B. Zhen, Xin Timmerman, Robert Nedzi, Lucien Gu, Xuejun PLoS One Research Article Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases. Public Library of Science 2017-10-06 /pmc/articles/PMC5630188/ /pubmed/28985229 http://dx.doi.org/10.1371/journal.pone.0185844 Text en https://creativecommons.org/publicdomain/zero/1.0/ This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 (https://creativecommons.org/publicdomain/zero/1.0/) public domain dedication. |
spellingShingle | Research Article Liu, Yan Stojadinovic, Strahinja Hrycushko, Brian Wardak, Zabi Lau, Steven Lu, Weiguo Yan, Yulong Jiang, Steve B. Zhen, Xin Timmerman, Robert Nedzi, Lucien Gu, Xuejun A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title | A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title_full | A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title_fullStr | A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title_full_unstemmed | A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title_short | A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
title_sort | deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5630188/ https://www.ncbi.nlm.nih.gov/pubmed/28985229 http://dx.doi.org/10.1371/journal.pone.0185844 |
work_keys_str_mv | AT liuyan adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT stojadinovicstrahinja adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT hrycushkobrian adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT wardakzabi adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT lausteven adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT luweiguo adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT yanyulong adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT jiangsteveb adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT zhenxin adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT timmermanrobert adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT nedzilucien adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT guxuejun adeepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT liuyan deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT stojadinovicstrahinja deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT hrycushkobrian deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT wardakzabi deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT lausteven deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT luweiguo deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT yanyulong deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT jiangsteveb deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT zhenxin deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT timmermanrobert deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT nedzilucien deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery AT guxuejun deepconvolutionalneuralnetworkbasedautomaticdelineationstrategyformultiplebrainmetastasesstereotacticradiosurgery |