DENSE-INception U-net for medical image segmentation

BACKGROUND AND OBJECTIVE Convolutional neural networks (CNNs) play an important role in the field of medical image segmentation. Among many kinds of CNNs, the U-net architecture is one of the most famous fully convolutional network architectures for medical semantic segmentation tasks. Recent work shows that the U-net network can be substantially deeper thus resulting in improved performance on segmentation tasks. Though adding more layers directly into network is a popular way to make a network deeper, it may lead to gradient vanishing or redundant computation during training. METHODS A novel CNN architecture is proposed that integrates the Inception-Res module and densely connecting convolutional module into the U-net architecture. The proposed network model consists of the following parts: firstly, the Inception-Res block is designed to increase the width of the network by replacing the standard convolutional layers; secondly, the Dense-Inception block is designed to extract features and make the network more deep without additional parameters; thirdly, the down-sampling block is adopted to reduce the size of feature maps to accelerate learning and the up-sampling block is used to resize the feature maps. RESULTS The proposed model is tested on images of blood vessel segmentations from retina images, the lung segmentation of CT Data from the benchmark Kaggle datasets and the MRI scan brain tumor segmentation datasets from MICCAI BraTS 2017. The experimental results show that the proposed method can provide better performance on these two tasks compared with the state-of-the-art algorithms. The results reach an average Dice score of 0.9857 in the lung segmentation. For the blood vessel segmentation, the results reach an average Dice score of 0.9582. For the brain tumor segmentation, the results reach an average Dice score of 0.9867. CONCLUSIONS The experiments highlighted that combining the inception module with dense connections in the U-Net architecture is a promising approach for semantic medical image segmentation.

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

[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]  Laurens van der Maaten,et al.  Submanifold Sparse Convolutional Networks , 2017, ArXiv.

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[6]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[7]  Ali Mohammadzadeh,et al.  A Hybrid Multilayer Filtering Approach for Thyroid Nodule Segmentation on Ultrasound Images , 2018, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[8]  Kilian Q. Weinberger,et al.  Memory-Efficient Implementation of DenseNets , 2017, ArXiv.

[9]  A. Srinivasan,et al.  Applications of deformable models for in-dopth analysis and feature extraction from medical images—A review , 2013, Pattern Recognition and Image Analysis.

[10]  Kilian Q. Weinberger,et al.  Deep Networks with Stochastic Depth , 2016, ECCV.

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[13]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[14]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[15]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[16]  David Dagan Feng,et al.  Stacked fully convolutional networks with multi-channel learning: application to medical image segmentation , 2017, The Visual Computer.

[17]  Tianfu Wang,et al.  A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images , 2016, IEEE Transactions on Medical Imaging.

[18]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[19]  Mo Li,et al.  Exploring Deep Learning for Efficient and Reliable Mobile Sensing , 2018, IEEE Netw..

[20]  C. Paterson,et al.  Measuring retinal vessel tortuosity in 10-year-old children: validation of the Computer-Assisted Image Analysis of the Retina (CAIAR) program. , 2009, Investigative ophthalmology & visual science.

[21]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Liang Chen,et al.  DRINet for Medical Image Segmentation , 2018, IEEE Transactions on Medical Imaging.

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

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

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

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

[27]  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).

[28]  Woei-Chyn Chu,et al.  Performance measure characterization for evaluating neuroimage segmentation algorithms , 2009, NeuroImage.

[29]  P. Jaccard.  THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE.1 , 1912 .

[30]  Haihua Xu,et al.  Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

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

[32]  Bram van Ginneken,et al.  Comparative study of retinal vessel segmentation methods on a new publicly available database , 2004, SPIE Medical Imaging.

[33]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

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

[35]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[36]  Vijayan K. Asari,et al.  Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation , 2018, ArXiv.

[37]  Ke Chen,et al.  Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images , 2015, IEEE Transactions on Medical Imaging.

[38]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Bunyarit Uyyanonvara,et al.  An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation , 2012, IEEE Transactions on Biomedical Engineering.