基于动态方向梯度矢量流模型的脑肿瘤图像分割  

The Direction of Gradient Vector Flow Based on the Dynamic Model of Brain Tumor Segmentation

作　　者：俞海平[1] 邬立保[1] 陈昌沉[1] 窦洪桥[1] 朱艳[1] 

机构地区：[1]南京大学医学院附属鼓楼医院放射科,江苏南京210008

出　　处：《现代生物医学进展》2012年第6期1093-1097,共5页Progress in Modern Biomedicine

摘　　要：目的:针对GVF Snake模型算法收敛容易陷入局部极小值及对初始轮廓位置敏感等缺点,提出一种动态方向梯度矢量流模型(DDGVF),使其更适合医学图像的分割。方法:利用主动轮廓模型的提取和跟踪特定区域内目标轮廓的方法,将其应用于医学图像如CT、MRI和超声图像的处理,以获取特定器官及组织的轮廓。结果:动态方向梯度矢量流场(DDGVF)能够较好地提取出脑肿瘤图像。结论:利用该方法能够较好地分割提取出脑肿瘤图像的肿瘤病变区域,为进一步对其纹理和形状等特征进行描述和分析提供了可靠的依据。Objective： Convergence of GVF Snake model for the algorithm is easy to fall into local minimum and the initial out-line of a position-sensitive and other shortcomings,propose a dynamic model of the direction of gradient vector flow（DDGVF）,make it more suitable for medical image segmentation.Method： Extraction using active contour model and track the target within a specific re-gion contour method,can be applied to medical imaging such as CT,MRI and ultrasound image processing,access to specific organs and tissues of the contour.Result： This method can extract the images of brain tumors.Conclusion： It provides a reliable basis for further study on their characteristics such as texture and shape description and analysis.

关 键 词：脑肿瘤 图像分割 动态方向梯度矢量流模 

分 类 号：R739.41[医药卫生—肿瘤] R814.42[医药卫生—临床医学]