Cargando…

Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images

In this work, we propose a novel cascaded V-Nets method to segment brain tumor substructures in multimodal brain magnetic resonance imaging. Although V-Net has been successfully used in many segmentation tasks, we demonstrate that its performance could be further enhanced by using a cascaded structu...

Descripción completa

Detalles Bibliográficos
Autores principales: Hua, Rui, Huo, Quan, Gao, Yaozong, Sui, He, Zhang, Bing, Sun, Yu, Mo, Zhanhao, Shi, Feng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7033427/
https://www.ncbi.nlm.nih.gov/pubmed/32116623
http://dx.doi.org/10.3389/fncom.2020.00009
_version_ 1783499664624975872
author Hua, Rui
Huo, Quan
Gao, Yaozong
Sui, He
Zhang, Bing
Sun, Yu
Mo, Zhanhao
Shi, Feng
author_facet Hua, Rui
Huo, Quan
Gao, Yaozong
Sui, He
Zhang, Bing
Sun, Yu
Mo, Zhanhao
Shi, Feng
author_sort Hua, Rui
collection PubMed
description In this work, we propose a novel cascaded V-Nets method to segment brain tumor substructures in multimodal brain magnetic resonance imaging. Although V-Net has been successfully used in many segmentation tasks, we demonstrate that its performance could be further enhanced by using a cascaded structure and ensemble strategy. Briefly, our baseline V-Net consists of four levels with encoding and decoding paths and intra- and inter-path skip connections. Focal loss is chosen to improve performance on hard samples as well as balance the positive and negative samples. We further propose three preprocessing pipelines for multimodal magnetic resonance images to train different models. By ensembling the segmentation probability maps obtained from these models, segmentation result is further improved. In other hand, we propose to segment the whole tumor first, and then divide it into tumor necrosis, edema, and enhancing tumor. Experimental results on BraTS 2018 online validation set achieve average Dice scores of 0.9048, 0.8364, and 0.7748 for whole tumor, tumor core and enhancing tumor, respectively. The corresponding values for BraTS 2018 online testing set are 0.8761, 0.7953, and 0.7364, respectively. We also evaluate the proposed method in two additional data sets from local hospitals comprising of 28 and 28 subjects, and the best results are 0.8635, 0.8036, and 0.7217, respectively. We further make a prediction of patient overall survival by ensembling multiple classifiers for long, mid and short groups, and achieve accuracy of 0.519, mean square error of 367240 and Spearman correlation coefficient of 0.168 for BraTS 2018 online testing set.
format Online
Article
Text
id pubmed-7033427
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-70334272020-02-28 Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images Hua, Rui Huo, Quan Gao, Yaozong Sui, He Zhang, Bing Sun, Yu Mo, Zhanhao Shi, Feng Front Comput Neurosci Neuroscience In this work, we propose a novel cascaded V-Nets method to segment brain tumor substructures in multimodal brain magnetic resonance imaging. Although V-Net has been successfully used in many segmentation tasks, we demonstrate that its performance could be further enhanced by using a cascaded structure and ensemble strategy. Briefly, our baseline V-Net consists of four levels with encoding and decoding paths and intra- and inter-path skip connections. Focal loss is chosen to improve performance on hard samples as well as balance the positive and negative samples. We further propose three preprocessing pipelines for multimodal magnetic resonance images to train different models. By ensembling the segmentation probability maps obtained from these models, segmentation result is further improved. In other hand, we propose to segment the whole tumor first, and then divide it into tumor necrosis, edema, and enhancing tumor. Experimental results on BraTS 2018 online validation set achieve average Dice scores of 0.9048, 0.8364, and 0.7748 for whole tumor, tumor core and enhancing tumor, respectively. The corresponding values for BraTS 2018 online testing set are 0.8761, 0.7953, and 0.7364, respectively. We also evaluate the proposed method in two additional data sets from local hospitals comprising of 28 and 28 subjects, and the best results are 0.8635, 0.8036, and 0.7217, respectively. We further make a prediction of patient overall survival by ensembling multiple classifiers for long, mid and short groups, and achieve accuracy of 0.519, mean square error of 367240 and Spearman correlation coefficient of 0.168 for BraTS 2018 online testing set. Frontiers Media S.A. 2020-02-14 /pmc/articles/PMC7033427/ /pubmed/32116623 http://dx.doi.org/10.3389/fncom.2020.00009 Text en Copyright © 2020 Hua, Huo, Gao, Sui, Zhang, Sun, Mo and Shi. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Hua, Rui
Huo, Quan
Gao, Yaozong
Sui, He
Zhang, Bing
Sun, Yu
Mo, Zhanhao
Shi, Feng
Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title_full Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title_fullStr Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title_full_unstemmed Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title_short Segmenting Brain Tumor Using Cascaded V-Nets in Multimodal MR Images
title_sort segmenting brain tumor using cascaded v-nets in multimodal mr images
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7033427/
https://www.ncbi.nlm.nih.gov/pubmed/32116623
http://dx.doi.org/10.3389/fncom.2020.00009
work_keys_str_mv AT huarui segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT huoquan segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT gaoyaozong segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT suihe segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT zhangbing segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT sunyu segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT mozhanhao segmentingbraintumorusingcascadedvnetsinmultimodalmrimages
AT shifeng segmentingbraintumorusingcascadedvnetsinmultimodalmrimages