Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours
Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours
复制标题
DOI：
10.1118/1.2207129
复制
发表时间：
2006-07-01
期刊：
影响因子：
3.8
通讯作者：
Zhou, Chuan
中科院分区：
文献类型：
--
作者：
Way, Ted W.;Hadjiiski, Lubomir M.;Zhou, Chuan
我们正在开发一种计算机辅助诊断（CAD）系统，用于对CT扫描发现的恶性和良性肺结节进行分类。一个完全自动化的系统被设计为分割结节从其周围的结构化背景中的局部体积的利益（VOI），并提取图像特征进行分类。图像分割采用三维活动轮廓（AC）方法。本研究使用了来自58名患者的96个肺结节（44个恶性，52个良性）的数据集。3D AC模型基于二维AC，添加了三个新的能量分量以利用3D信息：（1）3D梯度，其引导活动轮廓寻找对象表面，（2）3D曲率，其在z方向上施加平滑度约束，以及（3）掩模能量，其惩罚生长超过胸膜或胸壁的轮廓。在三维AC模型中，通过单纯形优化方法来搜索最佳能量权重。从分割的结节中提取形态和灰度特征。橡皮筋拉直变换（RBST）被施加到周围的结节体素的外壳。从RBST图像中提取基于游程统计的纹理特征。采用二次单纯形优化方法选择最有效的特征，设计了一种逐步特征选择的线性判别分析分类器。采用Leave-one-case-out方法对CAD系统进行了训练和测试。该系统实现了0.83 +/- 0.04的受试者工作特性曲线下的测试面积（A（z））。我们的初步研究结果表明，使用三维AC模型和三维纹理特征周围的结节是一个很有前途的方法与CAD肺结节的分割和分类。用我们的数据集训练的3D AC模型的分割性能用肺部图像数据库联盟（LIDC）中的23个结节进行了评价。通过3D AC模型分割的肺结节体积通常大于LIDC放射科医生使用结节边界的视觉判断所概述的体积。(C)2006年美国医学物理学家协会。
We are developing a computer-aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three-dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two-dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface, (2) 3D curvature, which imposes a smoothness constraint in the z direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray-level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run-length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave-one-case-out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve (A(z)) of 0.83 +/- 0.04. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries. (C) 2006 American Association of Physicists in Medicine.