Research on Computer-Aided Diagnosis System for Lung Cancer Detection by X-ray CT.

我们提出将X射线CT扫描仪应用于肺癌的筛查试验，并着手开发了一套计算机辅助设计系统，为实现该筛查系统的广泛应用奠定了基础。我们已经开发了一种初步的CAD算法，并将其应用于小型临床试验。在本研究活动中，我们开发了以下几个项目来提升我们的CAD算法，并将其应用到未来的实际应用中：(1)开发了一种基于物体三维结构的异常结节和正常血管的分类算法；(2)开发了适用于不同大小结节的Variable-Quoit算法；(3)开发了实时、动态的MIP算法

We proposed to apply X-ray CT scanner for screening test of lung cancer and started to develop a CAD system, which is essential to realize the widespread of this screening system. We already developed a first-step CAD algorithm and applied it to the small size clinical test. As the results we found some items to be brushed up to get more accurate classification rate.In this research activity, we developed the following items to level up our CAD algorithm, which would be applied to practical usage in future.(1) Development of a classification algorithm between abnormal nodules and normal vessels based on 3-D structure of objects.(2) Development of the variable-Quoit algorithm adaptively fitting to the various sizes of nodules.(3) Development of a real-time, dynamic MIP algorithm(4) Prototype construction of GUI system for CAD