Browse > Article
http://dx.doi.org/10.3837/tiis.2020.03.003

A Triple Residual Multiscale Fully Convolutional Network Model for Multimodal Infant Brain MRI Segmentation  

Chen, Yunjie (School of math and statistics, Nanjing University of Information Science & Technology)
Qin, Yuhang (School of math and statistics, Nanjing University of Information Science & Technology)
Jin, Zilong (School of computer and software, Nanjing University of Information Science & Technology)
Fan, Zhiyong (School of Automation, Nanjing University of Information Science & Technology)
Cai, Mao (School of math and statistics, Nanjing University of Information Science & Technology)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.14, no.3, 2020 , pp. 962-975 More about this Journal
Abstract
The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).
Keywords
Isointense phase; Tissue segmentation; Convolutional network; Residual multiscale block;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Ronneberger O, Fischer P, Brox T, "U-Net: Convolutional Networks for Biomedical Image Segmentation," in Proc. of MICCAI 2015. Springer International Publishing, 234-241, 2015.
2 Long J, Shelhamer E, Darrell T, "Fully convolutional networks for semantic segmentation," IEEE, 3431-3440, 2015.
3 Chen L, Bentley P, Mori K, et al., "DRINet for Medical Image Segmentation," IEEE Transactions on Medical Imaging, 2018.
4 Chen L, Bentley P, Rueckert D, "Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks," Neuroimage Clinical, 15, 633-643, 2017.   DOI
5 Huang G, Liu Z, Laurens V D M, et al., "Densely Connected Convolutional Networks," 2016.
6 He K, Zhang X, Ren S, et al., "Deep Residual Learning for Image Recognition," in Proc. of IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, vol. 1, pp. 770-778, 2016.
7 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in Proc. of CVPR, pp. 1-9, 2015.
8 Simonyan K, Zisserman A, "Very Deep Convolutional Networks for Large-Scale Image Recognition," Computer Science, 2014.
9 Princy Matlani and Manish Shrivastava, "Hybrid Deep VGG-NET Convolutional Classifier for Video Smoke Detection," CMES: Computer Modeling in Engineering & Sciences, Vol.119, No.3, pp.427-458, 2019.   DOI
10 Diakogiannis F I, Waldner, Francois, Caccetta P, et al., "ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data," 2019.
11 Badrinarayanan V, Kendall A, Cipolla R, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-1, 2017.
12 Lanlan Rui, Yabin Qin, Biyao Li and Zhipeng Gao, "Context-Based Intelligent Scheduling and Knowledge Push Algorithms for AR-Assist Communication Network Maintenance," CMES: Computer Modeling in Engineering & Sciences, Vol.118, No.2, pp.291-315, 2019.   DOI
13 Zhang J, Jin Y, Xu J, et al., "MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation," 2018.
14 Zhou Z, Siddiquee M M R, Tajbakhsh N, et al., "UNet++: A Nested U-Net Architecture for Medical Image Segmentation," 2018.
15 Zhao H, Shi J, Qi X, et al., "Pyramid Scene Parsing Network," 2016.
16 Chen L C, Papandreou G, Kokkinos I, et al., "Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs," Computer Science, 2014(4), 357-361, 2014.
17 Lin G, Milan A, Shen C, et al., "RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation," 2016.
18 G. Li, et al., "Early Diagnosis of Autism Disease by Multi-Channel Cnns," Machine Learning in Medical Imaging, pp. 303-309, 2018.
19 F. Shi, et al., "Neonatal Atlas Construction Using Sparse Representation," Human Brain Mapping, vol. 35, pp. 4663-4677, Sep 2014.   DOI
20 S. Hu, et al., "Learning-Based Deformable Image Registration for Infant MR Images in the First Year of Life," Medical Physics, vol. 44, pp. 158-170, Jan 2017.   DOI
21 F. Shi, et al., "Construction of Multi-Region-Multi-Reference Atlases for Neonatal Brain MRI Segmentation," NeuroImage, vol. 51, pp. 684-693, Jun 2010.   DOI
22 Li C, Xu C, Anderson A W, et al., "MRI Tissue Classification and Bias Field Estimation Based on Coherent Local Intensity Clustering: A Unified Energy Minimization Framework," Springer Berlin Heidelberg, 288-299, 2009.
23 S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," ICML, pp. 448-456, 2015.
24 Kazuhiko Kakuda, Tomoyuki Enomoto and Shinichiro Miura, "Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications," CMES: Computer Modeling in Engineering & Sciences, Vol.118, No.1, pp.1-14, 2019.   DOI
25 He K, Zhang X, Ren S, et al., "Identity Mappings in Deep Residual Networks," 2016.
26 L. Wang, et al., "Longitudinally Guided Level Sets for Consistent Tissue Segmentation of Neonates," Human Brain Mapping, vol. 34, pp. 956-972, Apr 2013.   DOI
27 N. Srivastava, et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," The Journal of Machine Learning Research, vol. 15, pp. 1929-1958, 2014.
28 Zamir A, Sax A, Shen W, et al., "Taskonomy: Disentangling Task Transfer Learning," 2018.
29 Hu K, Liu C, Yu X, et al., "A 2.5D Cancer Segmentation for MRI Images Based on U-Net," in Proc. of 2018 5th International Conference on Information Science and Control Engineering (ICISCE), 2018.