基于能量最小化的肾脏计算断层扫描图像分割方法  

Kidney segmentation in computed tomography sequences based on energy minimization

作　　者：张品[1] 梁艳梅[1] 常胜江[1] 范海伦[2] 

机构地区：[1]南开大学现代光学研究所,天津300071 [2]天津医科大学总医院普通外科,天津300052

出　　处：《物理学报》2013年第20期519-524,共6页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:11374167);天津市应用基础与前沿技术研究计划重点项目(批准号:09JCZDJC18300);教育部博士点基金(批准号:20090031110033)资助的课题~~

摘　　要：随着成像技术的不断发展,医学图像处理在计算机辅助诊断和病变管理中的重要作用日渐突出,而计算断层扫描序列图像的肾脏组织分割是其中的关键步骤.本文结合肾脏序列图像的连续性特征,提出了一种基于活动轮廓和图割方法的能量最小化分割模型来自动分割肾脏组织.根据相邻切片图像的形状差异与层间距之间的关系,计算出序列图像中适合图割优化能量函数的最优范围.能量函数采用测地活动轮廓模型和Chan-Vese模型的综合形式,兼顾了目标的边界和区域信息.随后,利用图割方法优化离散化的能量函数,驱使活动轮廓逐渐向目标边界靠近,直至收敛为止.对30组腹腔序列图像进行了算法测试,实验表明基于能量最小化的分割方法能够有效地提取出序列图像中的肾脏组织,其分割结果的平均Dice系数达到了93.7%.With the continuous development of medical imaging technology, medical image processing has played an increasingly prominent role in computer-aided diagnosis and disease management. Kidney segmentation in abdominal computed tomography （CT） sequences is a key step. In this paper, combining with the contextual property of renal tissues, a new energy minimization model based on active contour and graph cuts is proposed for kidney extraction in CT sequence. According to the relationship between the shape difference in adjacent slices and corresponding layer thickness, the optimal search range of the contour evolution is calculated for graph cut optimization. The energy function, combining the geodesic active contour with Chan-Vese model, takes into account the boundary and regional information. Then, graph cut methods are used to optimize the discrete energy function and drive the active contour towards object boundaries. Thirty abdominal CT sequences are used to evaluate the accuracy and effectiveness of the proposed algorithm. The experimental results reveal that this approach can extract renal tissues in CT sequences effectively and the average Dice coefficient reaches about 93.7%.

关 键 词：计算层析 肾脏分割 能量最小化 连续性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]