Improved V-Net Based Image Segmentation for 3D Neuron Reconstruction

Digital reconstruction (tracing) of neuron morphology in volumetric microscopy images is critical for the analysis and understanding of neuron function. However, most of the existing neuron tracing methods are not applicable in challenging datasets where the neuron structures are contaminated by noises or have discontinued segments. In this paper, we propose a segmentation method, which serves as a preprocessing step prior to applying reconstruction methods, based on deep learning to identify the location of neuronal voxels. This preprocessing step is expected to enhance the neuronal structures and reduce the impact of image noise in the data, which would result in improved reconstruction results. We train 3D fully convolutional networks (FCNs) for segmenting the neuronal microscopy images in an end-to-end manner. Specifically, the V-Net architecture, which is a 3D FCN, is improved by using anisotropic convolution kernels and changing the number of layers to fit our neuron datasets. The improved V-Net takes 3D microscopy images as the inputs and their voxel-wise segmentation maps as the outputs. Experimental results show that this network improved the neuron tracing performance significantly in many challenging datasets when using different reconstruction methods.

[1]  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).

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

[3]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[4]  Leonidas J. Guibas,et al.  Volumetric and Multi-view CNNs for Object Classification on 3D Data , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Li Cheng,et al.  Learning to Boost Filamentary Structure Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Douglas B. Ehlenberger,et al.  Rayburst sampling, an algorithm for automated three-dimensional shape analysis from laser scanning microscopy images , 2006, Nature Protocols.

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

[8]  Erik Meijering,et al.  Neuron tracing in perspective , 2010, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[9]  Vincent Lepetit,et al.  Multiscale Centerline Detection , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Hanchuan Peng,et al.  From DIADEM to BigNeuron , 2015, Neuroinformatics.

[11]  Amit K. Roy-Chowdhury,et al.  3D Neuron Tip Detection in Volumetric Microscopy Images , 2011, 2011 IEEE International Conference on Bioinformatics and Biomedicine.

[12]  Hanchuan Peng,et al.  Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images , 2017, MLMI@MICCAI.

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

[14]  Hanchuan Peng,et al.  3D neuron tip detection in volumetric microscopy images using an adaptive ray-shooting model , 2018, Pattern Recognit..

[15]  Sidong Liu,et al.  Rivulet: 3D Neuron Morphology Tracing with Iterative Back-Tracking , 2016, Neuroinformatics.

[16]  Hanchuan Peng,et al.  Automated 3D Soma Segmentation with Morphological Surface Evolution for Neuron Reconstruction , 2018, Neuroinformatics.

[17]  Shaoqun Zeng,et al.  Rapid Reconstruction of 3D Neuronal Morphology from Light Microscopy Images with Augmented Rayburst Sampling , 2013, PloS one.

[18]  Hanchuan Peng,et al.  V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets , 2010, Nature Biotechnology.

[19]  Zhi Zhou,et al.  Adaptive Image Enhancement for Tracing 3D Morphologies of Neurons and Brain Vasculatures , 2014, Neuroinformatics.

[20]  Tianming Liu,et al.  SmartTracing: self-learning-based Neuron reconstruction , 2015, Brain Informatics.

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

[22]  Hanchuan Peng,et al.  Extensible visualization and analysis for multidimensional images using Vaa3D , 2014, Nature Protocols.

[23]  Luca Maria Gambardella,et al.  Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks , 2013, MICCAI.

[24]  Sébastien Ourselin,et al.  Real-Time Segmentation of Non-rigid Surgical Tools Based on Deep Learning and Tracking , 2016, CARE@MICCAI.

[25]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Eugene W. Myers,et al.  Automatic 3D neuron tracing using all-path pruning , 2011, Bioinform..

[27]  Shuiwang Ji,et al.  Deep Learning Segmentation of Optical Microscopy Images Improves 3-D Neuron Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[28]  Hanchuan Peng,et al.  APP2: automatic tracing of 3D neuron morphology based on hierarchical pruning of a gray-weighted image distance-tree , 2013, Bioinform..