Full Text:   <2358>

Summary:  <1777>

CLC number: 

On-line Access: 2024-08-27

Received: 2023-10-17

Revision Accepted: 2024-05-08

Crosschecked: 0000-00-00

Cited: 0

Clicked: 4455

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Xiaobing ZHANG

https://orcid.org/0000-0001-9344-2630

Shengdong NIE

https://orcid.org/0000-0001-7825-4455

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE B 2021 Vol.22 No.6 P.462-475

http://doi.org/10.1631/jzus.B2000381


3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks


Author(s):  Xiaobing ZHANG, Yin HU, Wen CHEN, Gang HUANG, Shengdong NIE

Affiliation(s):  School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; more

Corresponding email(s):   nsd4647@163.com

Key Words:  Glioma, Magnetic resonance imaging (MRI), Segmentation, Dense block, 2D convolutional neural networks (2D-CNNs)


Xiaobing ZHANG, Yin HU, Wen CHEN, Gang HUANG, Shengdong NIE. 3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks[J]. Journal of Zhejiang University Science B, 2021, 22(6): 462-475.

@article{title="3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks",
author="Xiaobing ZHANG, Yin HU, Wen CHEN, Gang HUANG, Shengdong NIE",
journal="Journal of Zhejiang University Science B",
volume="22",
number="6",
pages="462-475",
year="2021",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.B2000381"
}

%0 Journal Article
%T 3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks
%A Xiaobing ZHANG
%A Yin HU
%A Wen CHEN
%A Gang HUANG
%A Shengdong NIE
%J Journal of Zhejiang University SCIENCE B
%V 22
%N 6
%P 462-475
%@ 1673-1581
%D 2021
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.B2000381

TY - JOUR
T1 - 3D brain glioma segmentation in MRI through integrating multiple densely connected 2D convolutional neural networks
A1 - Xiaobing ZHANG
A1 - Yin HU
A1 - Wen CHEN
A1 - Gang HUANG
A1 - Shengdong NIE
J0 - Journal of Zhejiang University Science B
VL - 22
IS - 6
SP - 462
EP - 475
%@ 1673-1581
Y1 - 2021
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.B2000381


Abstract: 
To overcome the computational burden of processing three-dimensional (3D) medical scans and the lack of spatial information in two-dimensional (2D) medical scans, a novel segmentation method was proposed that integrates the segmentation results of three densely connected 2D convolutional neural networks (2D-CNNs). In order to combine the low-level features and high-level features, we added densely connected blocks in the network structure design so that the low-level features will not be missed as the network layer increases during the learning process. Further, in order to resolve the problems of the blurred boundary of the glioma edema area, we superimposed and fused the T2-weighted fluid-attenuated inversion recovery (FLAIR) modal image and the T2-weighted (T2) modal image to enhance the edema section. For the loss function of network training, we improved the cross-entropy loss function to effectively avoid network over-fitting. On the Multimodal Brain Tumor Image segmentation Challenge (BraTS) datasets, our method achieves dice similarity coefficient values of 0.84, 0.82, and 0.83 on the BraTS2018 training; 0.82, 0.85, and 0.83 on the BraTS2018 validation; and 0.81, 0.78, and 0.83 on the BraTS2013 testing in terms of whole tumors, tumor cores, and enhancing cores, respectively. Experimental results showed that the proposed method achieved promising accuracy and fast processing, demonstrating good potential for clinical medicine.

集成多个密集连接二维卷积神经网络(2D-CNNs)分割模型的脑胶质瘤三维分割

概要:为了克服处理三维医学扫描的计算负担和二维医学扫描中空间信息的不足,本文提出了一种新的脑胶质瘤分割方法,该方法将三个密集连接的二维卷积神经网络(2D-CNN)分割模型的分割结果进行融合。为了将低级特征和高级特征组合在一起,本文在网络结构设计中添加了紧密连接的模块,这样在学习过程中随着网络层数的增加,低级特征将不会被遗漏。此外,为了解决神经胶质瘤水肿区域边界模糊的问题,我们叠加并融合了液体衰减反转恢复(FLAIR)模态图像和T2模态图像以增强水肿区域。对于网络训练的损失函数,我们改进了交叉熵损失函数,有效避免了网络过度拟合。本文在多模态脑肿瘤图像分割数据集(BraTS)上进行实验验证。其中,我们的方法在BraTS2018训练集上在整个肿瘤,肿瘤核心和增强肿瘤区域的Dice系数值分别达到了0.84、0.82和0.83;在BraTS2018验证集上达到0.82、0.85和0.83;在BraTS2013测试集上达到的0.81、0.78和0.83。实验结果表明,该方法具有良好的准确性和快速的处理能力,具有良好的临床应用前景。

关键词:脑胶质瘤;磁共振成像(MRI);分割;密集连接块;二维卷积神经网络(2D-CNNs)

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]BaidU, TalbarS, RaneS, et al., 2020. A novel approach for fully automatic intra-tumor segmentation with 3D U-Net architecture for gliomas. Front Comput Neurosci, 14:10.

[2]BakasS, AkbariH, SotirasA, et al., 2017. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data, 4:170117.

[3]ChenLL, WuY, DSouzaAM, et al., 2018. MRI tumor segmentation with densely connected 3D CNN. Proceedings Volume 10574, Medical Imaging 2018: Image Processing. SPIE Medical Imaging, 2018, Houston, Texas, USA, 105741F.

[4]DvořákP, MenzeB, 2016. Local structure prediction with convolutional neural networks for multimodal brain tumor segmentation. In: Menze B, Langs G, Montillo A, et al. (Eds.), Medical Computer Vision: Algorithms for Big Data. Springer, Cham, p.59-71.

[5]GoetzM, WeberC, BinczykF, et al., 2015. DALSA: domain adaptation for supervised learning from sparsely annotated MR images. IEEE Trans Med Imaging, 35(1):184-196.

[6]GuoD, WangL, SongT, et al., 2019. Cascaded global context convolutional neural network for brain tumor segmentation. In: Crimi A, Bakas S (Eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2019. Lecture Notes in Computer Science, Vol. 11992. Springer, Cham, p.315-326.

[7]HavaeiM, DavyA, Warde-FarleyD, et al., 2017. Brain tumor segmentation with Deep Neural Networks. Med Image Anal, 35:18-31.

[8]HeKM, ZhangXY, RenSQ, et al., 2016. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, p.770-778.

[9]HuangG, LiuZ, van der MaatenL, et al., 2017. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, p.2261-2269.

[10]HussainS, AnwarSM, MajidM, 2017. Brain tumor segmentation using cascaded deep convolutional neural network. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Republic of Korea, p.1998-2001.

[11]IslamR, ImranS, AshikuzzamanM, et al., 2020. Detection and classification of brain tumor based on multilevel segmentation with convolutional neural network. J Biomed Sci Eng, 13(4):45-53.

[12]KamnitsasK, LedigC, NewcombeVFJ, et al., 2017. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal, 36:61-78.

[13]KistlerM, BonarettiS, PfahrerM, et al., 2013. The virtual skeleton database: an open access repository for biomedical research and collaboration. J Med Internet Res, 15(11):e245.

[14]KrishnaN, KhalanderMR, ShettyN, et al., 2019. Segmentation and detection of glioma using deep learning. In: Chiplunkar N, Fukao T (Eds.), Advances in Artificial Intelligence and Data Engineering. Advances in Intelligent Systems and Computing, Vol. 1133. Springer, Singapore, p.109-120.

[15]LiQN, GaoZF, WangQY, et al., 2018. Glioma segmentation with a unified algorithm in multimodal MRI images. IEEE Access, 6:9543-9553.

[16]LiYH, JiaFC, QinJ, 2016. Brain tumor segmentation from multimodal magnetic resonance images via sparse representation. Artif Intell Med, 73:1-13.

[17]McKinleyR, MeierR, WiestR, 2018. Ensembles of densely-connected CNNs with label-uncertainty for brain tumor segmentation. In: Crimi A, Bakas S, Kuijf H, et al. (Eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2018. Lecture Notes in Computer Science, Vol. 11384. Springer, Cham, p.456-465.

[18]MengqiaoW, JieY, YiC, et al., 2017. The multimodal brain tumor image segmentation based on convolutional neural networks. 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA). Springer, Cham, p.336-339.

[19]MenzeBH, JakabA, BauerS, et al., 2015. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging, 34(10):1993-2024.

[20]MohanG, SubashiniMM, 2018. MRI based medical image analysis: survey on brain tumor grade classification. Biomed Signal Proc Control, 39:139-161.

[21]NairV, HintonGE, 2010. Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, p.807-814.

[22]PanMY, ShiYH, SongZJ, 2020. Segmentation of gliomas based on a double-pathway residual convolution neural network using multi-modality information. J Med Imaging Health Informatics, 10(11):2784-2794.

[23]SimonyanK, ZissermanA, 2015. Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations. Springer, Cham, p.6.https://arxiv.org/abs/1409.1556

[24]UdupaP, VishwakarmaS, 2016. A survey of MRI segmentation techniques for brain tumor studies. Bonfring Int J Adv Image Proc, 6(3):22-27.

[25]UrbanG, BendszusM, HamprechtFA, et al., 2014. Multi-modal brain tumor segmentation using deep convolutional neural networks. Proceedings MICCAI-BRATS, Springer, Cham, p.31-35.

[26]ZhaoLY, JiaKB, 2015. Deep feature learning with discrimination mechanism for brain tumor segmentation and diagnosis. 2015 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP). Adelaide, SA, Australia, p.306-309.

[27]ZhaoXM, WuYH, SongGD, et al., 2018. A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med Image Anal, 43:98-111.

[28]ZhouCH, ChenSC, DingCX, et al., 2018. Learning contextual and attentive information for brain tumor segmentation. In: Crimi A, Bakas S, Kuijf H, et al. (Eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2018. Lecture Notes in Computer Science, Vol. 11384, Springer, Cham, p.497-507.

[29]ZhouZX, HeZS, ShiMF, et al., 2020. 3D dense connectivity network with atrous convolutional feature pyramid for brain tumor segmentation in magnetic resonance imaging of human heads. Comput Biol Med, 121:103766.

[30]ZhugeY, KrauzeAV, NingH, et al., 2017. Brain tumor segmentation using holistically nested neural networks in MRI images. Med Phys, 44(10):5234-5243.

[31]ZikicD, IoannouY, BrownM, et al., 2014. Segmentation of brain tumor tissues with convolutional neural networks. Proceedings MICCAI Workshop on Multimodal Brain Tumor Segmentation Challenge. Springer, Cham, p.36-39.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE