(1) 我的问题是?
1、→使用Pyradiomics后,出现代码提示信息如下
Feature Compactness1 is deprecated, use with caution!
Feature Compactness2 is deprecated, use with caution!
Feature SphericalDisproportion is deprecated, use with caution!
parameter force2D must be set to True to enable shape2D extraction
Feature StandardDeviation is deprecated, use with caution!
GLCM is symmetrical, therefore Sum Average = 2 * Joint Average, only 1 needs to be calculated
但是看这些特征也都是有相应的值的,请问这些特征还能用于后续的筛选吗
具体设置代码如下:
settings = {}
settings[‘binWidth’] = 25 # 5 pyradiomics库提取的大部分特征是根据各种灰度直方图算的,所以binWidth指的是制作直方图和离散化图像灰度时的 bin 大小。
settings[‘sigma’] = [3, 5]
settings[‘Interpolator’] = sitk.sitkBSpline #设置用于重采样的插值方法(有多种可选)。仅适用于重采样图像
settings[‘resampledPixelSpacing’] = [1, 1, 1] # 3,3,3
settings[‘voxelArrayShift’] = 1000 # 300
settings[‘normalize’] = True
settings[‘normalizeScale’] = 1 #确定图像归一化后的比例。默认为1。
extractor = featureextractor.RadiomicsFeatureExtractor(additionInfo=True, **settings)
#extractor = featureextractor.RadiomicsFeatureExtractor()
print(‘Extraction parameters:\n\t’, extractor.settings)
#By default, only original is enabled. Optionally enable some image types:
#extractor.enableImageTypes(Original={}, LoG={}, Wavelet={})
#extractor.enableImageTypeByName(‘LoG’)
#extractor.enableImageTypeByName(‘Wavelet’)
extractor.enableAllFeatures()
extractor.enableFeaturesByName(firstorder=[‘Energy’, ‘TotalEnergy’, ‘Entropy’, ‘Minimum’, ‘10Percentile’, ‘90Percentile’, ‘Maximum’, ‘Mean’, ‘Median’, ‘InterquartileRange’, ‘Range’, ‘MeanAbsoluteDeviation’, ‘RobustMeanAbsoluteDeviation’, ‘RootMeanSquared’, ‘StandardDeviation’, ‘Skewness’, ‘Kurtosis’, ‘Variance’, ‘Uniformity’])
extractor.enableFeaturesByName(shape=[‘VoxelVolume’, ‘MeshVolume’, ‘SurfaceArea’, ‘SurfaceVolumeRatio’, ‘Compactness1’, ‘Compactness2’, ‘Sphericity’, ‘SphericalDisproportion’,‘Maximum3DDiameter’,‘Maximum2DDiameterSlice’,‘Maximum2DDiameterColumn’,‘Maximum2DDiameterRow’, ‘MajorAxisLength’, ‘MinorAxisLength’, ‘LeastAxisLength’, ‘Elongation’, ‘Flatness’])
# 上边两句我将一阶特征和形状特征中的默认禁用的特征都手动启用,为了之后特征筛选
print(‘Enabled filters:\n\t’, extractor.enabledImagetypes)
2、第二个问题,对图像进行了重采样,settings[‘normalizeScale’]这个取多大有没有说法,我是提取T1结构像的海马特征,同时这个重采样除了对图像重采样意外,是还会对mask也进行重采样吗?