基于深度学习的脑片图像区域划分方法

doi:10.11772/j.issn.1001-9081.2019091521

摘要/Abstract

摘要： 针对采用传统多模态配准方法进行小鼠脑片图像自动化区域划分精度差的问题，提出一种无监督多模态的脑片图像区域划分方法。首先，基于小鼠脑图谱获得脑片区域划分对应的ARA（Allen Reference Atlases）数据库中的Atlas脑图谱和Average Template脑图谱；然后，通过仿射变换预处理和PCANet-SR（Principal Component Analysis Net-based Structural Representation）网络处理将Average Template脑图谱与小鼠脑切片进行预配准及同模态转换，再根据U-net及空间变换网络实现无监督配准，并将配准变形关系作用到Atlas脑图谱上；最后，提取配准变形后的Atlas脑图谱的边缘轮廓并与原始小鼠脑切片进行融合，从而实现脑片图像的区域划分。实验结果表明，与现有PCANet-SR+B样条配准方法相比，所提方法的配准精度指标的均方根误差（RMSE）降低了1.6%，相关系数（CC）和互信息（MI）值分别提高了3.5%、0.78%；可快速实现无监督多模态的脑片图像配准任务，且使得脑片区域划分准确。

关键词: 区域划分, 配准, 空间变换网络, 无监督, 多模态

Abstract: Aiming at the problem of poor accuracy of automatic region division of mouse brain slice image using traditional multimodal registration method,an unsupervised multimodal region division method of brain slice image was proposed. Firstly,based on the mouse brain map,the Atlas brain map and the Average Template brain map in the Allen Reference Atlases (ARA) database corresponding to the brain slice region division were obtained. Then the Average Template brain map and the mouse brain slices were pre-registered and modal transformed by affine transformation preprocessing and Principal Component Analysis Net-based Structural Representation(PCANet-SR)network processing. After that,according to U-net and the spatial transformation network,the unsupervised registration was realized,and the registration deformation relationship was applied to the Atlas brain map. Finally,the edge contour of the Atlas brain map extracted by the registration deformation was merged with the original mouse brain slices in order to realize the region division of the brain slice image. Compared with the existing PCANet-SR+B spline registration method,experimental results show that the Root Mean Square Error(RMSE)of the registration accuracy index of this method reduced by 1. 6%,the Correlation Coefficient(CC)and the Mutual Information(MI)increased by 3. 5% and 0. 78% respectively. The proposed method can quickly realize the unsupervised multimodal registration task of the brain slice image,and make the brain slice regions be divided accurately.

Key words: region division, registration, spatial transformation network, nonsupervision, multimodal

中图分类号:

TP391.4

王松伟, 赵秋阳, 王宇航, 饶小平. 基于深度学习的脑片图像区域划分方法[J]. 计算机应用, 2020, 40(4): 1202-1208.

WANG Songwei, ZHAO Qiuyang, WANG Yuhang, RAO Xiaoping. Region division method of brain slice image based on deep learning[J]. Journal of Computer Applications, 2020, 40(4): 1202-1208.

参考文献

[1] 张志建, 靳森, 朱续涛, 等. 利用嗜神经病毒跨突触追踪神经网络研究进展[J]. 生命科学,2014,26(6):634-644.(ZHANG Z J, JIN S,ZHU X T,et al. Advancement in neurotropic virus-mediated trans-synaptic neural circuit tracing[J]. Chinese Bulletin of Life Science,2017,26(6):634-644.)
[2] STERNBERGER L A, HARDY P H CUCULIS, et al. The unlabeled antibody enzyme method of immunohistochemistry:preparation and properties of soluble antigen-antibody complex (horseradish peroxidase-anti-horseradish peroxidase)and its use in the identification of spirochetes[J]. Journal of Histochemistry and Cytochemistry,1970,18(5):315-333.
[3] PAXINOS G,WATSON C R R,EMSON P C. AChE-stained horizontal sections of the rat brain in stereotaxic coordinates[J]. Journal of Neuroscience Methods,1980,3(2):129-149.
[4] OSEN K K,MUGNAINI E,DAHL A L,et al. Histochemical location of AChE in the cochlear and superior olivary nuclei. A reappraisal with emphasis on the cochlear granule cell system[J]. Archives Italiennes de Biologie,1984,122(3):169-212.
[5] LINDROOS O F C. Short Nissl staining for incubated cryostat sections of the brain[J]. Biotechnic and Histochemistry,1991,66(4):208-209.
[6] KIERNAN J A, MACPHERSON C M, PRICE A, et al. A histochemical examination of the staining of kainate-induced neuronal degeneration by anionic dyes[J]. Biotechnic and Histochemistry,1998,73(5):244-254.
[7] PAXINOS G,FRANKLIN K B J. The Mouse Brain in Stereotaxic Coordinates[M]. 2nd ed. Waltham,MA:Academic Press,2001:1-59.
[8] ZHOU J,NI R. The Tree Shrew (Tupaia belangeri chinensis) Brain in Stereotaxic Coordinates[M]. Singapore:Springer,2016:399-497.
[9] PAXINOS G,WATSON C,PETRIDES M,et al. The Marmoset Brain in Stereotaxic Coordinates[M]. 4th ed. San Diego:Elsevier Academic Press,2012:1-59.
[10] BETLEY J N,STERNSON S M. Adeno-associated viral vectors for mapping, monitoring, and manipulating neural circuits[J]. Human Gene Therapy,2011,22(6):669-677.
[11] BEIER K T, SAUNDERS A, OLDENBURG I A, et al. Anterograde or retrograde transsynaptic labeling of CNS neurons with vesicular stomatitis virus vectors[J]. Proceedings of the National Academy of Sciences of the United States of America, 2011,108(37):15414-15419.
[12] TERVO D G R,HWANG B Y,VISWANATHAN S,et al. A designer AAV variant permits efficient retrograde access to projection neurons[J]. Neuron,2016,92(2):372-382.
[13] 杨丽琴, 林富春, 雷皓. 静息状态下脑功能连接的磁共振成像研究[J]. 波谱学杂志,2010,27(3):326-340. (YANG L Q,LIN F C,LEI H. Resting state functional connectivity in brain studied by fMRI approach[J]. Chinese Journal of Magnetic Resonance, 2010,27(3):326-340.)
[14] 吴瑞琪, 李博, 刘悦, 等. 光激活磁共振脑功能成像的研究现状及前景[J]. 波谱学杂志,2014,31(2):295-305.(WU R Q,LI B,LIU Y,et al. Current state and future of optogenetic functional magnetic resonance imaging[J]. Chinese Journal of Magnetic Resonance,2014,31(2):295-305.)
[15] 朱续涛, 何晓斌, 刘悦, 等. 一种简易的脑片图像的半自动区域划分及细胞计数方法[J]. 波谱学杂志,2018,35(2):133-140. (ZHU X T,HE X B,LIU Y,et al. A convenient semi-automatic method for analyzing brain sections:registration,segmentation and cell counting[J]. Chinese Journal of Magnetic Resonance, 2018,35(2):133-140.)
[16] MATTES D,HAYNOR D R,VESSELLE H,et al. Nonrigid multimodality image registration[C]//Proceedings of 2001 Conference on Medical Imaging,SPIE 4322. Bellingham,WA:SPIE,2001:1609-1620.
[17] MAES F,VANDERMEULEN D,SUETENS P. Medical image registration using mutual information[J]. Proceedings of the IEEE,2003,91(10):1699-1722.
[18] PLUIM J P W,MAINTZ J B A,VIERGEVER M A. Mutual-information-based registration of medical images:a survey[J]. IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
[19] HEINRICH M P,JENKINSON M,BHUSHAN M,et al. MIND:modality independent neighbourhood descriptor for multi-modal deformable registration[J]. Medical Image Analysis,2012,16(7):1423-1435.
[20] WACHINGER C,NAVAB N. Entropy and Laplacian images:structural representations for multi-modal registration[J]. Medical Image Analysis,2012,16(1):1-17.
[21] OKTAY O,SCHUH A,RAJCHL M,et al. Structured decision forests for multi-modal ultrasound image registration[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9350. Cham:Springer,2015:363-371.
[22] SIMONOVSKY M,GUTIÉRREZ-BECKER B,MATEUS D,et al. A deep metric for multimodal registration[C]//Proceedings of the 2016 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9902. Cham:Springer,2016:10-18.
[23] MIAO S,WANG Z J,LIAO R. A CNN regression approach for real-time 2D/3D registration[J]. IEEE Transactions on Medical Imaging,2016,35(5):1352-1363.
[24] KREBS J,MANSI T,DELINGETTE H,et al. Robust Non-rigid registration through agent-based action learning[C]//Proceedings of the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10433. Cham:Springer,2017:344-352.
[25] ROHÉ M M,DATAR M,HEIMANN T,et al. SVF-Net:learning deformable image registration using shape matching[C]//Proceedings of the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10433. Cham:Springer,2017:266-274.
[26] 刘晨, 张龙波, 王雷, 等. 基于超像素重建的多尺度B样条医学图像配准[J]. 智能计算机与应用,2019,9(1):24-27.(LIU C, ZHANG L B,WANG L,et al. Multi-scale B-spline medical image registration based on superpixel reconstruction[J]. Journal of Intelligent Computers and Applications,2019,9(1):24-27.)
[27] 高宁, 王兴元, 王秀坤. 基于多状态分层模型的有表情人脸配准[J]. 计算机工程与应用,2019,55(7):40-47. (GAO N, WANG X Y,WANG X K. Face alignment across expression based on multi state layered model[J]. Computer Engineering and Applications,2019,55(7):40-47.)
[28] GOLDOWITZ D. Allen reference atlas. A digital color brain Atlas of the C57BL/6J male mouse-by H. W. Dong[J]. Genes,Brain and Behavior,2010,9(1):128-128.
[29] BALAKRISHNAN G,ZHAO A,SABUNCU M R,et al. An unsupervised learning model for deformable medical image registration[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:9252-9260.
[30] JIA F,ZHU X,XU F. A single adaptive point mutation in Japanese encephalitis virus capsid is sufficient to render the virus as a stable vector for gene delivery[J]. Virology,2016,490:109-118.
[31] CHAN T H,JIA K,GAO S,et al. PCANet:a simple deep learning baseline for image classification[J]. IEEE Transactions on Image Processing,2015,24(12):5017-5032.
[32] LIU Y,CHENG M,HU X,et al. Richer convolutional features for edge detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:5872-5881.
[33] BUADES A,COLL B,MOREL J M. A non-local algorithm for image denoising[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2005:60-65.
[34] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham:Springer,2015:234-241.
[35] JADERBERG M,SIMONYANK,ZISSERMANA,et al. Spatial transformer networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2015:2017-2025.