中文摘要：

肺区分割是计算机辅助诊断肺癌的前提。当肿块与胸壁粘连时，由于两者的计算机断层成像（CT）值接近，基于局部低级特征的传统分割方法不能得到正确结果；而且由于肿块体积大，造成了肺区内正常组织的大面积缺失，故以往含胸壁粘连型肺结节（直径小于3cm）的肺区分割方法不再适用，需要采用能结合先验形状和低级特征的主动形状模型（ASM）来分割含胸壁粘连型肺肿块的肺区。但传统ASM的搜索步骤是一种基于最小二乘的优化方法，该方法对异常标记点敏感，会使轮廓更新到正常肺组织和肿块的过渡区域而不是真正的肺边缘。针对这一问题，提出了改进的ASM算法：首先基于距离特征识别异常标记点，然后赋予异常标记点和正常标记点不同的搜索函数。搜索过程在设定的包围核（VOI）内进行。用所提出的ASM方法分割30个含胸壁粘连型肿块的肺区，与金标准的重叠度为93．6％。实验结果表明针对含胸壁粘连型肿块的肺区分割问题，改进的ASM算法能得到较好的分割结果，并且算法的运行时间是在临床可接受的范围内。

英文摘要：

Lung segmentation is the premise of the computer aided diagnosis of lung cancer. The traditional segmenta- tion method based on local low-level features can not get the correct result when a tumor is connected with pleura due to their similar computed tomography （CT） values. Moreover, because the big size of tumor leads to the loss of a large part of lung area, the traditional segmentation methods of lung with iuxta-pleural nodule whose diameter is less than 3 cm are not suitable. Acitve shape model （ASM） combined with prior shape and low level features might be appropriate. But the search steps in conventional ASM is an optimization method based on the least square, which is sensitive to outlier marker points, and it makes profile update to the transition area of normal lung tissue and tumor rather than a true lung contour. To solve the problem, we proposed an improved ASM algorithm. Firstly, we identi- fied these outlier marker points by distance, and then gave the different searching functions to the abnormal and nor- mal marker points. And the search processing should be limited in volume of interesting （VOI）. We selected 30 lung images with juxta-pleural tumors, and got the overlap rate with the gold standard as 93.6%. The experimental results showed that the improved ASM could get good segmentation results for the lungs with juxta-pleural tumors, and the running time of the algorithm could be tolerated in clinical.