Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees
Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees
复制标题
DOI：
10.1118/1.1528178
复制
发表时间：
2003-01-01
期刊：
影响因子：
3.8
通讯作者：
Johnson, CD
中科院分区：
文献类型：
--
作者：
Jerebko, AK;Summers, RM;Johnson, CD
由于息肉的形状和正常结肠表面的复杂性，CT结肠镜检查结肠息肉是有问题的。已发表的结果表明计算机辅助检测息肉的可行性，但需要更好的分类器来提高特异性。本文比较了神经网络和递归二叉树两种分类方法的分类结果。作为我们的起点，我们从冒号的三维重建中收集表面几何信息，然后根据选择的变量（如区域密度、高斯和平均曲率和球度）进行筛选。过滤器返回候选息肉的位置，基于先前使用检测阈值的工作，神经网络或二叉树被应用。在我们的调查中使用了39个息肉的数据集，大小从3到25毫米。对于神经网络和二叉树，我们使用十倍交叉验证来更好地估计真实错误率。采用Levenberg-Marquardt算法训练的带有一个隐藏层的反向传播神经网络获得了最好的结果：灵敏度90%，特异性95%，每次研究有16个假阳性。(C) 2003年美国医学物理学家协会。
Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study. (C) 2003 American Association of Physicists in Medicine.