Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter.
Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter.
复制标题
使用定向高斯衍生物过滤器对标准和移动胸部X光片进行肺部分割。
DOI：
10.1186/s12938-015-0014-8
复制
发表时间：
2015-03-04
影响因子：
3.9
通讯作者：
Ahmad Fauzi MF
中科院分区：
文献类型：
--
作者：
Wan Ahmad WS;Zaki WM;Ahmad Fauzi MF
无监督肺分割方法是开发基于内容的医学图像检索系统（CBMIRS）的必要步骤之一。本研究的目的是使用全自动无监督方法，为标准胸片和移动胸片的肺分割提供一个强大的解决方案。该方法基于7个方向的有向高斯导数滤波，结合模糊c均值（FCM）聚类和阈值分割对肺区域进行细化。此外，还提出了一种自动生成每个高斯响应阈值的新算法。该算法应用于来自公共JSRT数据集和我们来自合作医院的私人数据集的PA和AP胸片。引入两个预处理模块对不同机器的图像进行标准化处理。与先前在JSRT数据集上的文献中发现的工作进行比较表明，我们的方法给出了相当好的结果。我们还将我们的算法与其他无监督方法进行了比较，以提供对所有数据集性能的公平比较度量。公共JSRT数据集中肺分割的性能指标（准确度、F-score、精密度、灵敏度和特异性）除重叠指标为0.87外均在0.90以上。所有测量的标准差都很低，在0.01到0.06之间。私有图像数据库的重叠度量为0.81（来自标准机器的图像）和0.69（来自两台移动机器的图像）。该算法完全自动化且速度快，对于512 × 512像素的分辨率，平均执行时间为12.5 s。我们提出的方法是全自动的，无监督的，不需要训练或学习阶段，可以使用标准机器和两个不同的移动机器来分割肺部。所提出的预处理模块对于标准化移动机器的x光片非常有用。该算法为CBMIRS的应用提供了良好的性能指标，鲁棒性好，速度快。
Unsupervised lung segmentation method is one of the mandatory processes in order to develop a Content Based Medical Image Retrieval System (CBMIRS) of CXR. The purpose of the study is to present a robust solution for lung segmentation of standard and mobile chest radiographs using fully automated unsupervised method. The novel method is based on oriented Gaussian derivatives filter with seven orientations, combined with Fuzzy C-Means (FCM) clustering and thresholding to refine the lung region. In addition, a new algorithm to automatically generate a threshold value for each Gaussian response is also proposed. The algorithms are applied to both PA and AP chest radiographs from both public JSRT dataset and our private datasets from collaborative hospital. Two pre-processing blocks are introduced to standardize the images from different machines. Comparisons with the previous works found in the literature on JSRT dataset shows that our method gives a reasonably good result. We also compare our algorithm with other unsupervised methods to provide fairly comparative measures on the performances for all datasets. Performance measures (accuracy, F-score, precision, sensitivity and specificity) for the segmentation of lung in public JSRT dataset are above 0.90 except for the overlap measure is 0.87. The standard deviations for all measures are very low, from 0.01 to 0.06. The overlap measure for the private image database is 0.81 (images from standard machine) and 0.69 (images from two mobile machines). The algorithm is fully automated and fast, with the average execution time of 12.5 s for 512 by 512 pixels resolution. Our proposed method is fully automated, unsupervised, with no training or learning stage is necessary to segment the lungs taken using both a standard machine and two different mobile machines. The proposed pre-processing blocks are significantly useful to standardize the radiographs from mobile machines. The algorithm gives good performance measures, robust, and fast for the application of the CBMIRS.
登录
查看更多内容
影响因子：
10.6
作者：
Lassen, Bianca;van Rikxoort, Eva M.;Kuhnigk, Jan-Martin
通讯作者：
Kuhnigk, Jan-Martin
影响因子：
10.6
作者：
Candemir, Sema;Jaeger, Stefan;McDonald, Clement J.
通讯作者：
McDonald, Clement J.
CT 胸部图像中的自动肺裂检测和肺叶分割。
影响因子：
3.9
作者：
Qi S;van Triest HJ;Yue Y;Xu M;Kang Y
通讯作者：
Kang Y
影响因子：
10.6
作者：
Pham, DL;Prince, JL
通讯作者：
Prince, JL
DOI：
10.1109/tsmcb.2011.2124455
发表时间：
2011-10-01
影响因子：
--
作者：
Chen, Long;Chen, C. L. Philip;Lu, Mingzhu
通讯作者：
Lu, Mingzhu