基于自适应体窗结构分析的肺结节检测方法.PDFVIP

J South Med Univ, 2014, 34(6): 759-765 doi 10.3969/j.issn. 1673-4254.2014.06.02 ·759 · 技术方法 基于自适应体窗结构分析的肺结节检测方法基于自适应体窗结构分析的肺结节检测方法 1 1 1 2 1 1 王 凯 ，张 煜 ，刘哲星 ，林炳权 ，吴志强 ，曹 蕾 1 2 南方医科大学 生物医学工程学院，南方医院影像中心，广东 广州 510515 摘要：基于三维Hessian 矩阵的肺结节检测方法具有很高的敏感性，却很难避免血管交叉区域产生假阳性。本文提出了一种基 于自适应体窗结构分析的方法，首先利用体素的Hessian 矩阵特征值设计结构系数分析其灰度分布特征；然后根据结构系数构 建三维自适应体窗分析组织的局部结构特征；最后使用判别函数检测出结节。通过对17套真实肺部CT 图像序列进行实验，结 果表明本方法可以检测出不同大小和类型的30个结节，并有效减少了血管交叉区域产生的假阳性。结合自适应体窗的Hessian 矩阵检测方法可以提高检测效率，减轻医生工作量，为肺结节后续的分割和治疗提供有力的支持。 关键词：肺结节检测；Hessian 矩阵；结构系数；自适应体窗；结构分析 Structural analysis based on adaptive window for pulmonary nodule detection 1 1 1 2 1 1 WANG Kai , ZHANG Yu , LIU Zhexing , LIN Bingquan , WU Zhiqiang , CAO Lei 1 2 School of Biomedical Engineering, Diagnostic Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China Abstract: Radiographic detection of pulmonary nodules based on three-dimensional Hessian matrix is highly sensitive but frequently produces false positive results in areas where blood vessels intersect. We propose a novel approach to pulmonary nodule detection using Hessian matrix-based adaptive window structure analysis, in which the structure coefficients is used to differentiate a voxel that belongs to a nodule or vascular structures, followed by construction of the 3D adaptive window to analyze the local structure characteristics; the nodules were then detected using the discrimination function. The experimental results on pulmonary CT images from 17 patients showed a 100% detection sensitivity for nodules of varying sizes and types, with also significantly reduced false positive results generated by the vessel junctions. This approach provides valuable ass