基于三维纹理特征仿真和脑图谱的小鼠脑磁共振显微成像分割算法  

Mouse Brain MRM Segmentation Algorithm Based on 3D Texture Feature Simulation and Anatomical Atlas

作　　者：付振荣[1] 林岚[1] 王婧璇 邬雪涛 顾克楠 吴水才[1] FU Zhenrong;LIN Lan;WANG Jingxuan;WU Xuetao;GU Kenan;WU Shuicai(College of Life Science and Bioengineering,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学生命科学与生物工程学院,北京100124

出　　处：《中国医疗设备》2018年第3期22-26,44,共6页China Medical Devices

基　　金：国家科技支撑计划课题(2015BAI02B03);北京市自然科学基金资助项目(7143171);北京市教委科技计划一般项目(KM201810005033)

摘　　要：近年来,随着脑科学研究的不断深入,基于小鼠磁共振显微成像(Magnetic Resonance Microscopy,MRM)的神经影像研究已逐渐成为该领域的研究热点。目前,小鼠脑MRM感兴趣区的分割主要还是依靠手工划分,耗时耗力。小鼠MRM脑图像的自动分割对小鼠MRM的自动分析具有重大的意义。本研究中提出了一种基于小鼠脑图谱的MRM脑图像的三维纹理合成算法,并且利用该方法对小鼠MRM的感兴趣区进行了分割。结果表明,该算法可用于小鼠脑MRM图像自动分割。In recent years,with the deepening of brain science research,mouse magnetic resonance microscopy(MRM)for neuroimaging research has gradually become a main research interest.At present,the parcellation of the mouse MRM brain image is mainly in dependent on manual segmentation,which is time-consuming and labor-intensive.The automated segmentation of mouse MRM brain image is of great significance for the study of mouse MRM.In this paper,we proposed a three-dimensional texture synthesis algorithm of mouse MRM brain image.The method was used to segment the region of interest of mouse MRM.The results showed that this algorithm could be used for automated segmentation of mouse MRM brain images.

关 键 词：磁共振显微成像 小鼠大脑 三维纹理仿真 脑图像分割 

分 类 号：R445.2[医药卫生—影像医学与核医学]