pyradiomics官方文档学习(3)--RadiomicsE

pyradiomics 官方文档里有几个示例文件，里面涉及了包括yaml文件设置、feature extraction、可视化等一系列影像组学常规操作，是非常好的学习资料。源码请参考：https://github.com/AIM-Harvard/pyradiomics

今天学习标题名为"PyRadiomics toolbox in Python"的这份文档。

0 加载module和函数

# Radiomics package
from radiomics import featureextractor

import six, numpy as np

1 获取图像及其掩模文件(Setting up data)

import os
import SimpleITK as sitk

from radiomics import getTestCase

imagepath_1, labelpath_1 = getTestCase('brain1')
imagepath_2, labelpath_2 = getTestCase('brain2')

image_1 = sitk.ReadImage(imagepath_1)
label_1 = sitk.ReadImage(labelpath_1)
image_2 = sitk.ReadImage(imagepath_2)
label_2 = sitk.ReadImage(labelpath_2)

2. 查看图像(Show the images)

# Display the images
%matplotlib inline
import matplotlib.pyplot as plt

plt.figure(figsize=(20,20))

# First image
plt.subplot(2,2,1)
plt.imshow(sitk.GetArrayFromImage(image_1)[12,:,:], cmap="gray")
plt.title("Brain #1")

plt.subplot(2,2,2)
plt.imshow(sitk.GetArrayFromImage(label_1)[12,:,:])        
plt.title("Segmentation #1")

# Second image
plt.subplot(2,2,3)
plt.imshow(sitk.GetArrayFromImage(image_2)[8,:,:], cmap="gray")        
plt.title("Brain #2")

plt.subplot(2,2,4)
plt.imshow(sitk.GetArrayFromImage(label_2)[8,:,:])        
plt.title("Segmentation #2")

plt.show()

rad_fig1.png

3. 提取特征值(Extract the features)

import os
# Instantiate the extractor
params = os.path.join(os.getcwd(), '..', 'examples', 'exampleSettings', 'Params.yaml')

extractor = featureextractor.RadiomicsFeatureExtractor(params)
result_1 = extractor.execute(image_1, label_1)
result_2 = extractor.execute(image_2, label_2)

4. 作图准备(Prepare for plotting)

# Make an array of the values
feature_1 = np.array([])
feature_2 = np.array([])

for key, value in six.iteritems(result_1):
    if key.startswith("original_"):                            # excluding meta-features
        feature_1 = np.append ( feature_1, result_1[key])
        feature_2 = np.append ( feature_2, result_2[key])

5. 绘图(可视化brain1和2的特征值，及其差异)

plt.figure(figsize=(20,20))
plt.subplot(3,1,1)
plt.plot(feature_1)
plt.yscale('log')
plt.title ( "Features from brain #1")
        
plt.subplot(3,1,2)
plt.plot(feature_2)
plt.yscale('log')
plt.title ( "Features from brain #1")

plt.subplot(3,1,3)
plt.plot(feature_1 - feature_2)
plt.yscale('log')
plt.title ( "Difference")
plt.show()

rad_fig2.png

Notes:不晓得为什么，没有画出和源码里一样的图。尝试在不同环境下Windows和MacOs使用pyradiomics也不奏效。