Sensitivity of Image Features to Noise in Conventional and Respiratory-Gated PET/CT Images of Lung Cancer: Uncorrelated Noise Effects.
发表日期： 2016.02.26 来源： Technology in Cancer Research & Treatment, 2017, 16(5):595-608.
Oliver JA1,2, Budzevich M3, Hunt D1,2, Moros EG1,2, Latifi K1,2, Dilling TJ1, Feygelman V1,2, Zhang G1,2.
1. Department of Radiation Oncology, Moffitt Cancer Center, Tampa, FL, USA.
2. Department of Physics, University of South Florida, Tampa, FL, USA.
3. Small Animal Imaging Laboratory, Moffitt Cancer Center, Tampa, FL, USA.
噪声对图像特征的影响尚未深入研究。我们的目的是探索图像特征对图像中加入不相关噪声的影响。使用Ge-68幻影计算正电子发射断层扫描/计算机断层扫描仪的信噪比和噪声功率谱。回顾性分析31例肺癌患者的常规和呼吸门控正电子发射断层扫描/计算机断层扫描图像。通过添加等于正电子发射断层摄影图像的最大强度的2.5%，4.0%和6.0%的不同标准偏差的高斯噪声和10,20,50,80和120计算机断层摄影图像的Hounsfield单位，为每个原始图像创建多组噪声图像。从所有图像中提取图像特征，并计算原始图像和噪声图像特征值之间的百分比差异。 然后根据噪声敏感度对这些特征进行分类。轮廓相关的形状描述平均在正电子发射断层扫描的4%以下，噪声和原始图像之间计算机断层扫描的差异小于13%。灰度级区域矩阵特征对于不相关噪声最为敏感，其显示了计算机断层扫描中常规和呼吸门控图像的平均差异> 200%，正电子发射断层扫描显示90%的平均差异。 图像特征差异随着正电子发射断层扫描中的形状，强度和灰度共生矩阵特征的噪声水平的增加以及常规计算机断层扫描中的灰度共生矩阵和灰度大小区域矩阵特征而增加。因此，研究人员应注意对图像特征的噪音影响。
The effect of noise on image features has yet to be studied in depth. Our objective was to explore how significantly image features are affected by the addition of uncorrelated noise to an image. The signal-to-noise ratio and noise power spectrum were calculated for a positron emission tomography/computed tomography scanner using a Ge-68 phantom. The conventional and respiratory-gated positron emission tomography/computed tomography images of 31 patients with lung cancer were retrospectively examined. Multiple sets of noise images were created for each original image by adding Gaussian noise of varying standard deviation equal to 2.5%, 4.0%, and 6.0% of the maximum intensity for positron emission tomography images and 10, 20, 50, 80, and 120 Hounsfield units for computed tomography images. Image features were extracted from all images, and percentage differences between the original image and the noise image feature values were calculated. These features were then categorized according to the noise sensitivity. The contour-dependent shape descriptors averaged below 4% difference in positron emission tomography and below 13% difference in computed tomography between noise and original images. Gray level size zone matrix features were the most sensitive to uncorrelated noise exhibiting average differences >200% for conventional and respiratory-gated images in computed tomography and 90% in positron emission tomography. Image feature differences increased as the noise level increased for shape, intensity, and gray-level co-occurrence matrix features in positron emission tomography and for gray-level co-occurrence matrix and gray-level size zone matrix features in conventional computed tomography. Investigators should be aware of the noise effects on image features.
PET/CT, image feature analysis, image noise, lung cancer, radiomics