Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (4): 1202-1208.DOI: 10.11772/j.issn.1001-9081.2019091521

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Region division method of brain slice image based on deep learning

WANG Songwei1, ZHAO Qiuyang1, WANG Yuhang1, RAO Xiaoping2   

  1. 1. College of Electrical Engineering, Zhengzhou University, Zhengzhou Henan 450000, China;
    2. Wuhan Institute of Physics and Mathematics, Chinese Academy of Sciences, Wuhan Hubei 430071, China
  • Received:2019-09-03 Revised:2019-11-08 Online:2020-04-10 Published:2019-12-02

基于深度学习的脑片图像区域划分方法

王松伟1, 赵秋阳1, 王宇航1, 饶小平2   

  1. 1. 郑州大学 电气工程学院, 郑州 450000;
    2. 中国科学院 武汉物理与数学研究所, 武汉 430071
  • 通讯作者: 王松伟
  • 作者简介:王松伟(1979-),男(回族),河南周口人,副教授,博士,CCF会员,主要研究方向:生物视觉机制研究与建模、机器视觉;赵秋阳(1995-),男,河南驻马店人,硕士研究生,主要研究方向:基于深度学习的图像配准与目标检测;王宇航(1995-),男,河南漯河人,硕士研究生,主要研究方向:基于深度学习的图像配准与目标检测;饶小平(1981-),男,湖北武汉人,助理研究员,博士,主要研究方向:神经通路示踪技术。

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

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

CLC Number: