Quantitative computerized analysis of diffuse lung disease in high-resolution computed tomography
Quantitative computerized analysis of diffuse lung disease in high-resolution computed tomography
复制标题
DOI：
10.1118/1.1597431
复制
发表时间：
2003-09-01
期刊：
影响因子：
3.8
通讯作者：
Doi, K
中科院分区：
文献类型：
--
作者：
Uchiyama, Y;Katsuragawa, S;Doi, K
在高分辨率计算机断层扫描（HRCT）图像上，已经开发了一种自动计算机方案来检测和表征弥漫性肺部疾病。我们的数据库包括来自105例患者的315张HRCT图像，包括六种不同类型的正常和异常切片，即磨玻璃影、网状和线状影、结节性影、蜂窝状影、肺气肿改变和实变。在315张HRCT图像中包含特定弥散模式的区域由三位放射科医生在CRT显示器上独立标记，其方式与他们在放射学报告中通常描述的方式相同。具有特定模式的区域，由三位放射科医生独立且一致地标记为相同模式，在本研究中被用作特定异常混浊的“金标准”。首先利用形态学滤波和阈值分割技术将肺从每个切片的背景中分割出来，然后用32x32矩阵将肺划分为许多连续的感兴趣区域（roi）。在每个ROI中确定的六个物理度量。包括CT值的平均值和标准差、空气密度分量、结节分量、线形分量和多房分量。人工神经网络（ann）用于区分七种不同的模式，包括正常模式和六种与弥漫性肺疾病相关的模式。这种计算机方法对每个ROI的六种异常模式的检测灵敏度为：毛玻璃性混浊99.2%(122/123)，网状和线状混浊100%(15/15)，结节性混浊88.0%(132/150)，蜂窝状混浊100%(98/98)，肺气肿变化95.8%(369/385)，实变100%（43/43）。检测正常ROI的特异性为88.1%（940/1067）。这种计算机化方法可能有助于放射科医生在HRCT图像中评估弥漫性肺部疾病。(C) 2003年美国医学物理学家协会。
An automated computerized scheme has been developed for the detection and characterization of diffuse lung diseases on high-resolution computed tomography (HRCT) images. Our database consisted of 315 HRCT images selected from 105 patients, which included normal and abnormal slices related to six different patterns, i.e., ground-glass opacities, reticular and linear opacities, nodular opacities, honeycombing, emphysematous change, and consolidation. The areas that included specific diffuse patterns in 315 HRCT images were marked by three radiologists independently on the CRT monitor in the same manner as they commonly describe in their radiologic reports. The areas with a specific pattern, which three radiologists marked independently and consistently as the same patterns, were used as "gold standard" for specific abnormal opacities in this study. The lungs were first segmented from the background in each slice by use of a morphological filter and a thresholding technique, and then divided into many contiguous regions of interest (ROIs) with a 32x32 matrix. Six physical measures which were determined in each ROI. included the mean and the standard deviation of the CT value, air density components, nodular components, line components, and multilocular components. Artificial neural networks (ANNs) were employed for distinguishing between seven different patterns which included normals and six patterns associated with diffuse lung disease. The sensitivity of this computerized method for a detection of the six abnormal patterns in each ROI was 99.2% (122/123) for ground-glass opacities, 100% (15/15) for reticular and linear opacities, 88.0% (132/150) for nodular opacities, 100% (98/98) for honeycombing, 95.8% (369/385) for emphysematous change, and 100% (43/43) for consolidation. The specificity in detecting a normal ROI was 88.1% (940/1067). This computerized method may be useful in assisting radiologists in their assessment of diffuse lung disease in HRCT images. (C) 2003 American Association of Physicists in Medicine.