A CADe system for nodule detection in thoracic CT images based on artificial neural network
A CADe system for nodule detection in thoracic CT images based on artificial neural network
复制标题
基于人工神经网络的胸部CT图像结节检测CADe系统
DOI：
10.1007/s11432-016-9008-0
复制
发表时间：
2017-07-01
影响因子：
8.8
通讯作者：
Hao, Aimin
中科院分区：
文献类型：
--
作者：
Liu, Xinglong;Hou, Fei;Hao, Aimin
肺癌是2015年美国癌症相关死亡的主要原因。根据先前的研究，肺结节的早期发现无疑会增加肺癌的五年生存率。在本文中，我们提出了一种新的评级方法的基础上的几何和统计特征提取初始结节候选人和人工神经网络方法检测肺结节。新方法完全基于相邻体素的3D分布，而不是用户指定的功能。在最初的候选检测，我们结合联合收割机有组织的区域属性计算的连接组件分析与相应的体素值分布的统计分析，以减少误报，同时保留真正的结节。然后，我们设计了多个人工神经网络（ANN），从不同类型的结节的大量体素邻居采样训练，并使用3D评分方法组织输出，以识别最终结节。在LIDC-IDRI数据集中的107个CT病例（252个结节）上的实验表明，我们的新方法实现了89.4%的灵敏度，同时将假阳性减少到每例2.0。实验结果表明，该系统对临床肺结节的诊断有很大的帮助。
Lung cancer has been the leading cause of cancer-related deaths in 2015 in United States. Early detection of lung nodules will undoubtedly increase the five-year survival rate for lung cancer according to prior studies. In this paper, we propose a novel rating method based on geometrical and statistical features to extract initial nodule candidates and an artificial neural network approach to the detection of lung nodules. The novel method is solely based on 3D distribution of neighboring voxels instead of user-specified features. During initial candidates detection, we combine organized region properties calculated from connected component analysis with corresponding voxel value distributions from statistical analysis to reduce false positives while retaining true nodules. Then we devise multiple artificial neural networks (ANNs) trained from massive voxel neighbor sampling of different types of nodules and organize the outputs using a 3D scoring method to identify final nodules. The experiments on 107 CT cases with 252 nodules in LIDC-IDRI data sets have shown that our new method achieves sensitivity of 89.4% while reducing the false positives to 2.0 per case. Our comprehensive experiments have demonstrated our system would be of great assistance for diagnosis of lung nodules in clinical treatments.