Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields.

Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach (e.g., U-net), which predicts the probability of being target object or background for each voxel. One problem of those methods is lacking of topology guarantee for segmented objects, and usually post processing is needed to infer the boundary surface of the object. In this paper, a novel model based on 3-D convolutional neural networks (CNNs) and Conditional Random Fields (CRFs) is proposed to tackle the surface segmentation problem with end-to-end training. To the best of our knowledge, this is the first study to apply a 3-D neural network with a CRFs model for direct surface segmentation. Experiments carried out on NCI-ISBI 2013 MR prostate dataset and Medical Segmentation Decathlon Spleen dataset demonstrated promising segmentation results.

[1]  Xiaodong Wu,et al.  Automated 3-D Intraretinal Layer Segmentation of Macular Spectral-Domain Optical Coherence Tomography Images , 2009, IEEE Transactions on Medical Imaging.

[2]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[3]  Lok Ming Lui,et al.  FLASH: Fast Landmark Aligned Spherical Harmonic Parameterization for Genus-0 Closed Brain Surfaces , 2015, SIAM J. Imaging Sci..

[4]  Xiaodong Wu,et al.  Optimal Net Surface Problems with Applications , 2002, ICALP.

[5]  Dongmei Zhang,et al.  Harmonic maps and their applications in surface matching , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

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

[7]  Xiaodong Wu,et al.  Simultaneous Multiple Surface Segmentation Using Deep Learning , 2017, DLMIA/ML-CDS@MICCAI.

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

[9]  Milan Sonka,et al.  Electric Field Theory Motivated Graph Construction for Optimal Medical Image Segmentation , 2009, GbRPR.

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

[11]  Zhiqiang Tian,et al.  PSNet: prostate segmentation on MRI based on a convolutional neural network , 2018, Journal of medical imaging.

[12]  Junjie Bai,et al.  Optimal Multiple Surface Segmentation With Shape and Context Priors , 2013, IEEE Transactions on Medical Imaging.

[13]  Yi Yang,et al.  Attention to Scale: Scale-Aware Semantic Image Segmentation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Xiaodong Wu,et al.  Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Florian Jung,et al.  Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challenge , 2014, Medical Image Anal..

[16]  Leixin Zhou,et al.  Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images , 2018, Biomedical optics express.

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

[18]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[19]  Martha Elizabeth Shenton,et al.  A 3D interactive multi-object segmentation tool using local robust statistics driven active contours , 2012, Medical Image Anal..

[20]  Xiaodong Wu,et al.  LOGISMOS—Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces: Cartilage Segmentation in the Knee Joint , 2010, IEEE Transactions on Medical Imaging.

[21]  Heng Huang,et al.  3D Global Convolutional Adversarial Network\\ for Prostate MR Volume Segmentation , 2018, ArXiv.

[22]  Roberto Cipolla,et al.  Convolutional CRFs for Semantic Segmentation , 2018, BMVC.

[23]  Jianru Xue,et al.  A supervoxel‐based segmentation method for prostate MR images , 2017, Medical physics.

[24]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[25]  Vibhav Vineet,et al.  Conditional Random Fields as Recurrent Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  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).

[27]  Milan Sonka,et al.  LOGISMOS-B: Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces for the Brain , 2014, IEEE Transactions on Medical Imaging.

[28]  Xiaodong Wu,et al.  Intraretinal Layer Segmentation of Macular Optical Coherence Tomography Images Using Optimal 3-D Graph Search , 2008, IEEE Transactions on Medical Imaging.