Skip-connected 3D DenseNet for volumetric infant brain MRI segmentation

Abstract Automatic 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI) is still less accurate owing to the low intensity contrast among tissues. To tackle the problem, we introduce an accurate segmentation method for volumetric infant brain MRI built upon a densely connected network that achieves state-of-the-art accuracy. Specifically, we carefully design a fully convolutional densely connected network with skip connections such that the information from different levels of dense blocks can be directly combined to achieve highly accurate segmentation results. The proposed network, called 3D-SkipDenseSeg, exploits the advantage of the recently DenseNet for classification task and extends this to segment the 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI). Experimental results demonstrate a competitive performance with regard to both segmentation accuracy and parameter efficiency of the proposed method over the existing methods; namely, the proposed 3D-SkipDenseSeg achieved the best dice similarity coefficient (DSC) of 90.37 ± 1.38% (WM), 92.27 ± 0.81% (GM), and 95.79 ± 0.54% (CSF) among the 21 participating teams in the 6-month infant brain dataset (iSeg-2017) and required only 10–30% of the parameters compared to similar deep learning-based methods.

[1]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[2]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jose Dolz,et al.  3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study , 2016, NeuroImage.

[4]  Jürgen Schmidhuber,et al.  Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation , 2015, NIPS.

[5]  Dinggang Shen,et al.  Construction of multi-region-multi-reference atlases for neonatal brain MRI segmentation , 2010, NeuroImage.

[6]  Shuiwang Ji,et al.  Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation , 2017, IEEE Transactions on Medical Imaging.

[7]  Hao Chen,et al.  VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images , 2017, NeuroImage.

[8]  Carlos Alberto Silva,et al.  Automatic brain tissue segmentation in MR images using Random Forests and Conditional Random Fields , 2016, Journal of Neuroscience Methods.

[9]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Hao Chen,et al.  Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images , 2017, AAAI.

[11]  Dinggang Shen,et al.  Neonatal brain image segmentation in longitudinal MRI studies , 2010, NeuroImage.

[12]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Gang Li,et al.  Benchmark on Automatic Six-Month-Old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge , 2019, IEEE Transactions on Medical Imaging.

[14]  Hao Chen,et al.  Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Amir Alansary,et al.  MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans , 2015, Comput. Intell. Neurosci..

[17]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[18]  Max A. Viergever,et al.  Automatic Segmentation of MR Brain Images With a Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[19]  Shuiwang Ji,et al.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation , 2015, NeuroImage.

[20]  Yaozong Gao,et al.  LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images , 2015, NeuroImage.

[21]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[22]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[24]  Jing Yuan,et al.  HyperDense-Net: A hyper-densely connected CNN for multi-modal image semantic segmentation , 2017, ArXiv.

[25]  Yaozong Gao,et al.  Segmentation of neonatal brain MR images using patch-driven level sets , 2014, NeuroImage.

[26]  P. Cattin,et al.  Multi-dimensional Gated Recurrent Units for the Segmentation of Biomedical 3D-Data , 2016, LABELS/DLMIA@MICCAI.

[27]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[28]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[31]  Daniel Rueckert,et al.  A dynamic 4D probabilistic atlas of the developing brain , 2011, NeuroImage.

[32]  Sébastien Ourselin,et al.  AdaPT: An adaptive preterm segmentation algorithm for neonatal brain MRI , 2013, NeuroImage.

[33]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[34]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[35]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Dinggang Shen,et al.  Automatic segmentation of neonatal images using convex optimization and coupled level sets , 2011, NeuroImage.

[37]  Daniel Rueckert,et al.  Magnetic resonance imaging of the newborn brain: Manual segmentation of labelled atlases in term-born and preterm infants , 2012, NeuroImage.

[38]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Hao Chen,et al.  Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets , 2017, MICCAI.

[40]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[41]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[42]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[43]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[44]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[45]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[46]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).