摘要
脑部肿瘤精确分割和三维重建的研究对脑部肿瘤疾病的诊断具有重要意义.提出一种全自动的脑肿瘤分割方法,该方法首先利用人脑结构信息的对称性,通过区域生长法实现脑肿瘤的粗略分割,然后将粗分割区域作为初始水平集轮廓,利用改进的测地线活动轮廓(geodesic active contours, GAC)模型进一步精确分割.经实验分析可知,该模型具有良好的分割灰度不均匀的弱边缘能力.最后对分割出的脑部肿瘤序列图像进行面绘制重建及其可视化,以此为脑肿瘤研究提供更多维度的信息.
Analysis on the accurate segmentation and 3D reconstruction of brain tumors are important for the diagnosis of brain tumor diseases.This paper presents an automatic segmentation method for brain tumors.According to the symmetry of human brain structure information,a rough segmentation of brain tumor can firstly be realized by region growing method,and then taken as the initial level set contour for the further accurate segmentation by means of geodesic active contour(GAC)model.Experimental analysis shows that the model has good weak-edge ability on segmenting uneven gray scale.Finally,surface rendering,reconstruction and visualization of the segmented brain tumor sequence images are carried out to provide more dimensional information for brain tumor research.
作者
侯东奥
鲁宇明
汪宇玲
刘武
HOU Dong-ao;LU Yu-ming;WANG Yu-ling;LIU Wu(College of Aeronautical Manufacturing Engineering,Nanchang Hangkong University,Nanchang 330063,China;School of Information Engineering,East China University of Technology,Nanchang 330013,China;School of Medicine,Yale University,Connecticut 06511,United States)
出处
《应用科学学报》
CAS
CSCD
北大核心
2018年第5期808-818,共11页
Journal of Applied Sciences
基金
国家自然科学基金(No.61866025)
江西省教育厅科技项目(No.GJJ170572)资助
关键词
脑肿瘤
区域生长法
测地线活动轮廓模型
面绘制
brain tumor
region growing method
geodesic active contour(GAC)model,surface rendering