Brain microstructure reconstruction based on deep learning

XIE Qiwei, CHEN Xi, SHEN Lijun, LI Guoqing, MA Hongtu, HAN Hua

Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (2) : 482-491.

PDF(3709 KB)
中国科学院数学与系统科学研究院期刊网
PDF(3709 KB)
Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (2) : 482-491. DOI: 10.12011/1000-6788(2018)02-0482-10

Brain microstructure reconstruction based on deep learning

  • XIE Qiwei1,2,3, CHEN Xi3, SHEN Lijun3, LI Guoqing3, MA Hongtu3, HAN Hua3,4,5
Author information +
History +

Abstract

To research the operation mechanism of brain for realizing brain-inspired intelligence, we employ the deep learning tool system to solve the problems of automatic analysis of big data in synaptic-scale brain microstructure reconstruction. The problems include dense neurons reconstruction, single neuron tracing, key organelles detection and reconstruction. Meanwhile, we adopt the fully convolutional networks (FCN) with a candidate region proposal network (RPN) to detect mitochondria and synapses, and integrate deep SPPUnet (spatial pyramid pooling U-net) framework with multi-cut algorithm for neurons reconstruction. Preferable performance have achieved in visual and quantitative analysis. These works provide effective support for high-throughput synaptic-scale brain microstructure reconstruction for neuroscientists.

Key words

brain microstructure reconstruction / electron microscope image / deep learning / region proposal network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
XIE Qiwei , CHEN Xi , SHEN Lijun , LI Guoqing , MA Hongtu , HAN Hua. Brain microstructure reconstruction based on deep learning. Systems Engineering - Theory & Practice, 2018, 38(2): 482-491 https://doi.org/10.12011/1000-6788(2018)02-0482-10

References

[1] 黄秉宪. 脑研究的系统科学[J]. 系统工程理论与实践, 1999, 19(6):35-39.Huang B X. System science for brain research[J]. Systems Engineering-Theory & Practice, 1999, 19(6):35-39.
[2] 谢启伟, 陈曦, 沈丽君, 等. 脑微观重建系统研究[J]. 系统工程理论与实践, 2017, 37(11):3006-3017.Xie Q W, Chen X, Shen L J, et al. Micro reconstruction system for brain[J]. Systems Engineering-Theory & Practice, 2017, 37(11):3006-3017.
[3] 高德坤, 吴冲, 李永立. 一种新的混合分类器及其人脸识别的应用研究[J]. 系统工程理论与实践, 2016, 36(6):1517-1525. Gao D K, Wu C, Li Y L. A new hybrid classifier model and its application on face recognition[J]. Systems Engineering-Theory & Practice, 2016, 36(6):1517-1525.
[4] Ibrahim R, Yousri N A, Ismail M A, et al. Multi-level gene/MiRNA feature selection using deep belief nets and active learning[C]//IEEE International Conference on Engineering in Medicine and Biology Society, 2014:3957-3960.
[5] Zhang W, Li R, Deng H, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation[J]. NeuroImage, 2015, 108:214-224.
[6] Quang D, Chen Y, Xie X. DANN:A deep learning approach for annotating the pathogenicity of genetic variants[J]. Bioinformatics, 2015, 31(5):761-763.
[7] Narayanan K, Kenneth J H, Daniel Raimund B, et al. Saturated reconstruction of a volume of neocortex[J]. Cell, 2015, 162(3):648-661.
[8] Berning M, Boergens K M, Helmstaedter M. SegEM:Efficient image analysis for high-resolution connectomics[J]. Neuron, 2015, 87(6):1193-1206.
[9] Sermanet P, Eigen D, Zhang X, et al. Overfeat:Integrated recognition, localization and detection using convolutional networks[R]. Eprint Arxiv, 2013.
[10] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2014:580-587.
[11] Girshick R. Fast R-CNN[C]//IEEE International Conference on Computer Vision, 2015:1440-1448.
[12] Ren S, He K, Girshick R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6):1137-1149.
[13] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2015:3431-3440.
[14] Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2017:6230-6239.
[15] Ciresan D, Giusti A, Gambardella L M, et al. Deep neural networks segment neuronal membranes in electron microscopy images[J]. Advances in Neural Information Processing Systems, 2012, 25:2852-2860.
[16] Lee K, Zlateski A, Vishwanathan A, et al. Recursive training of 2D-3D convolutional networks for neuronal boundary detection[C]//IEEE International Conference on Neural Information Processing Systems, 2015:3573-3581.
[17] Chen H, Qi X, Cheng J Z, et al. Deep contextual networks for neuronal structure segmentation[C]//AAAI'16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016:1167-1173.
[18] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2012, 60(2):84-90.
[19] Chen X, Xie Q, Shen L, et al. Wrinkle image registration for serial microscopy sections[C]//IEEE International Conference on Signal-Image Technology & Internet-Based Systems, 2015:23-26.
[20] Roberts M, Jeong W K, Vázquezreina A, et al. Neural process reconstruction from sparse user scribbles[M]//Medical Image Computing and Computer-Assisted Intervention, 2011:621-628.
[21] Yang Y, Liu D Q, Huang W, et al. Selective synaptic remodeling of amygdalocortical connections associated with fear memory[J]. Nature Neuroscience, 2016, 19(10):1348-1355.
[22] Sun M, Zhang D, Guo H, et al. 3D-reconstruction of synapses based on EM images[C]//IEEE International Conference on Mechatronics and Automation, 2016:1959-1964.
[23] Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):583-596.
[24] Yin L, Xiao C, Xie Q, et al. An efficient method for neuronal tracking in electron microscopy images[C]//IEEE International Conference on Mechatronics and Automation, 2017:1865-1870.
[25] Jurrus E, Watanabe S, Giuly R J, et al. Semi-automated neuron boundary detection and nonbranching process segmentation in electron microscopy images[J]. Neuroinformatics, 2013, 11(1):5-29.
[26] Beier T, Hamprecht F A, Kappes J H. Fusion moves for correlation clustering[C]//IEEE International Conference on Computer Vision and Pattern Recognition, 2015:3507-3516.
[27] Rao Q, Han H, Li W, et al. Automatically segmenting and reconstructing neurons in SEM images[C]//IEEE International Conference on Mechatronics and Automation, 2016:1908-1915.
[28] Unnikrishnan R, Pantofaru C, Hebert M. Toward objective evaluation of image segmentation algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):929-944.
[29] Marina M. Comparing clusterings:An axiomatic view[C]//ICML'05 Proceedings of the 22nd International Conference on Machine, 2005:577-584.
[30] Arganda-Carreras I, Turaga S C, Berger D R, et al. 2012 ISBI challenge:Segmentation of neuronal structures in EM stacks[EB/OL]. http://brainiac2.mit.edu/isbichallenge/.
[31] Arganda-Carreras I, Turaga S C, Berger D R, et al. Crowdsourcing the creation of image segmentation algorithms for connectomics[J]. Frontiers in Neuroanatomy, 2015, 9:142.

Funding

National Natural Science Foundation of China (61673381, 61201050, 61306070, 61701497); Special Program of Beijing Municipal Science and Technology Commission (Z161100000216146); Strategic Priority Research Program of the CAS (XDB02060001); Program of Committee of Science and Technology of the Central Military Commission of the PRC (17-163-11-ZT-003-002-04); Scientific Research Instrument and Equipment Development Project of Chinese Academy of Sciences (YZ201671)
PDF(3709 KB)

471

Accesses

0

Citation

Detail
Sections
Recommended

/

〈 〉