基于改进BET的MRI脑组织自动提取算法  

MRI Brain Tissue Automatic Extraction Algorithm Based on Modified BET

作　　者：杨金柱 陆琳[1,2] 曹鹏 赵大哲 YANG Jin-zhu;LU Lin;CAO Peng;ZHAO Da-zhe(School of Computer Science ＆ Engineering, Northeastern University, Shenyang 110169,China;Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University, Shenyang 110169, China.)

机构地区：[1]东北大学计算机科学与工程学院,辽宁沈阳110169 [2]东北大学医学影像计算教育部重点实验室,辽宁沈阳110169

出　　处：《东北大学学报（自然科学版）》2018年第2期186-189,210,共5页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(61172002)

摘　　要：提出一种基于改进BET(brain extraction tool)的MRI脑组织自动提取算法.首先,该算法结合图像梯度信息能够估计出更为准确的脑重心(center of gravity,COG);其次,该算法构建了新的脑表面形变力,在垂直于脑表面切线的扩张力中引入了边缘力,该力很好地抑制了脑组织的边界泄漏和过度分割问题.使用本文方法对MRI脑影像进行了自动脑组织提取,实验结果表明,本文算法能够自动获得更加准确的脑组织提取结果,特别是在脑组织边缘处,本文算法与BET算法相比,提取结果更准确.Based on modified brain extraction tool（ BET）,an automatic extraction algorithm is proposed for brain MRI（ magnetic resonance imaging）. Firstly,the algorithm combining image gradient information can estimate the center of gravity（ COG） of brain more accurately; secondly,it builds a new brain surface deformation force. Edge force is introduced into the expansion force perpendicular to the tangent of brain surface,which could suppress the brain tissue leaking and over-segmentation problem. Experiments are conducted on the algorithm proposed to automatically extract brain tissue of MRI brain images,and the results show the more accurate extraction of brain tissue,especially at brain tissue edges,compared with the BET method.

关 键 词：脑组织提取 磁共振图像 脑组织提取工具 脑重心 边缘力 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]