本筆記來(lái)源于B站Up主: 有Li 的影像組學(xué)系列教學(xué)視頻
本節(jié)(35)主要介紹: 2D超聲影像組學(xué)的特征提取
視頻中李博士情境再現(xiàn)了小白研究者可能碰到的各種技術(shù)難題跨蟹，并演示了解決這些問(wèn)題的思路。
-
將
dicom格式的2D 超聲圖像轉(zhuǎn)為壓縮的nifti格式橘沥，將其命名為test.nii.gz; 勾畫ROI后同樣保存為壓縮的nifti格式窗轩，命名為mask.nii.gz
Fig1.jpg 嘗試提取影像學(xué)特征：
import radiomics
from radiomics import featureextractor
imageFile = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/test.nii.gz"
maskFile = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/mask.nii.gz"
extractor = featureextractor.RadiomicsFeatureExtractor()
featureVector = extractor.execute(imageFile, maskFile)
#print(featureVector.items())
for featureName in featureVector.keys():
print("%s: %s" % (featureName, featureVector[featureName]))
出現(xiàn)了如下報(bào)錯(cuò)信息：
sitk::ERROR: Pixel type: vector of 8-bit unsigned integer is not supported in 3D byN3itk6simple26LabelStatisticsImageFilterE
- 按照提示，有可能是數(shù)據(jù)格式的問(wèn)題座咆∑沸眨回到源代碼，修改文件相應(yīng)的格式箫措，將其命名為
test1.nii.gz
import SimpleITK as sitk
import numpy as np
folderPath = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/"
reader = sitk.ImageSeriesReader()
dicom_names = reader.GetGDCMSeriesFileNames(folderPath)
reader.SetFileNames(dicom_names)
image = reader.Execute()
image_arr = sitk.GetArrayFromImage(image) # Note: order:z, y, x !!
size = image.GetSize()
origin = image.GetOrigin() #order: x, y, z
spacing = image.GetSpacing() #order:x, y, z
direction = image.GetDirection()
#print(spacing)
pixelType = sitk.sitkInt8 #注意這里是Int8
image_new = sitk.Image(size,pixelType)
#image_arr_new = image_arr[:,:,::-1] #鏡像翻轉(zhuǎn)操作
image_arr_new = image_arr
#print(image_arr_new.shape)
image_new = sitk.GetImageFromArray(image_arr_new)
image_new.SetDirection(direction)
image_new.SetSpacing(spacing)
image_new.SetOrigin(origin)
sitk.WriteImage(image_new,folderPath + "test1.nii.gz")
- 將步驟[2]中的
test.nii.gz替換為test1.nii.gz,再次執(zhí)行該步驟
此時(shí)又出現(xiàn)了報(bào)錯(cuò)信息：
sitk::ERROR: Input "labelImage" for "LabelStatisticsImageFilter" has dimension of 3 which does not match the primary input's dimension of 2!
- 執(zhí)行
print(image_arr_new.shape)后顯示為：
(1, 900, 1600, 3)
Notes: 這里涉及python讀入nifti文件的格式問(wèn)題，其順序?yàn)?z,y,x(對(duì)應(yīng)這里的1,900,1600); 這里的3為不同的slice
- 探索這個(gè)“3”代表的意義：將每一個(gè)slice導(dǎo)出來(lái)衬潦，通過(guò)對(duì)比發(fā)現(xiàn)其中的端倪斤蔓。執(zhí)行代碼：
image_arr_new = image_arr[:,:,:,0]
#image_arr_new = image_arr[:,:,:,1]
#image_arr_new = image_arr[:,:,:,2]
#print(image_arr_new.shape)
image_new = sitk.GetImageFromArray(image_arr_new)
image_new.SetDirection(direction)
image_new.SetSpacing(spacing)
image_new.SetOrigin(origin)
sitk.WriteImage(image_new,folderPath + "test-slice0.nii.gz")
#sitk.WriteImage(image_new,folderPath + "test-slice1.nii.gz")
#sitk.WriteImage(image_new,folderPath + "test-slice2.nii.gz")
- 將
test-slice0.nii.gz，test-slice1.nii.gz镀岛，test-slice2.nii.gz在軟件中打開弦牡，查看它們之間的差異(肉眼似乎看不出啥區(qū)別) - 使用寫代碼的方法來(lái)探索
test-slice0.nii.gz，test-slice1.nii.gz漂羊，test-slice2.nii.gz之間的差異(視頻里李博士演示了對(duì)比前二者)
import SimpleITK as sitk
import numpy as np
slicer0 = sitk.ReadImage("test-slice0.nii.gz")
slicer1 = sitk.ReadImage("test-slice1.nii.gz")
slicer0_arr = sitk.GetArrayFromImage(slicer0)
slicer1_arr = sitk.GetArrayFromImage(slicer1)
comp = slicer0_arr == slicer1_arr
print(comp)
Fig2.jpg
- 將差異的部分保存為影像導(dǎo)出
image_arr = slicer0_arr - slicer1_arr
image_arr[image_arr != 0] = 1
size = slicer0.GetSize()
origin = slicer0.GetOrigin() #order: x, y, z
spacing = slicer0.GetSpacing() #order:x, y, z
direction = slicer0.GetDirection()
image_new = sitk.GetImageFromArray(image_arr)
image_new.SetDirection(direction)
image_new.SetSpacing(spacing)
image_new.SetOrigin(origin)
sitk.WriteImage(image_new,"comp.nii.gz")
- 此時(shí)在軟件中打開
comp.nii.gz文件驾锰，查看差異(在于右下角的水印部分)(視頻中是左下角的水印)。換句話說(shuō)走越，這3張test-slice0.nii.gz椭豫，test-slice1.nii.gz，test-slice2.nii.gz是一樣的旨指，差別僅在于右下角的水印赏酥。所以，后續(xù)的工作只需選擇其中的一個(gè)即可。 - 再次查看
test-slice0.nii.gz和mask文件，發(fā)現(xiàn)mask文件和源文件不對(duì)應(yīng)欠橘。mask.nii.gz是基于test.nii.gz文件畫出并保存的啃勉，但是在test.nii.gz保存為test1.nii.gz時(shí)存在一個(gè)翻轉(zhuǎn)(我沒(méi)有搞明白這一點(diǎn))，所以應(yīng)重新保存一下mask文件
Fig3.jpg
import SimpleITK as sitk
import numpy as np
folderPath = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/"
mask = sitk.ReadImage('mask.nii.gz')
mask_arr = sitk.GetArrayFromImage(mask)
reader = sitk.ImageSeriesReader()
dicom_names = reader.GetGDCMSeriesFileNames(folderPath)
reader.SetFileNames(dicom_names)
image = reader.Execute()
image_arr = sitk.GetArrayFromImage(image) # Note: order:z, y, x !!
size = image.GetSize()
origin = image.GetOrigin() #order: x, y, z
spacing = image.GetSpacing() #order:x, y, z
direction = image.GetDirection()
pixelType = sitk.sitkInt8 #注意這里是Int8
image_new = sitk.Image(size,pixelType)
mask_new = sitk.Image(size,pixelType)
#image_arr_new = image_arr[:,:,::-1] #鏡像翻轉(zhuǎn)操作
image_arr_new = image_arr[:,:,:,0]
print(image_arr.shape)
image_new = sitk.GetImageFromArray(image_arr_new)
image_new.SetDirection(direction)
image_new.SetSpacing(spacing)
image_new.SetOrigin(origin)
mask_new = sitk.GetImageFromArray(mask_arr) # 視頻里勘誤為mask_new,其實(shí)就應(yīng)該是mask_arr, print二者可以看出區(qū)別來(lái)
mask_new.SetDirection(direction)
mask_new.SetSpacing(spacing)
mask_new.SetOrigin(origin)
sitk.WriteImage(image_new,"test0.nii.gz")
sitk.WriteImage(mask_new,"mask0.nii.gz")
Fig4.jpg
-
再次嘗試提取影像組學(xué)特征(代碼[2])诡右，發(fā)現(xiàn)代碼可以運(yùn)行鲜侥。但是這里有一個(gè)隱藏的bug漂坏，就是mask文件雖然重新保存了摸屠，但是并不能和原來(lái)的位置匹配谓罗。通過(guò)軟件查看圖像可以發(fā)現(xiàn)其中的區(qū)別
Fig5.jpg 再次回到原始代碼里查找問(wèn)題來(lái)源
import SimpleITK as sitk
import numpy as np
folderPath = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/"
mask = sitk.ReadImage('mask.nii.gz')
mask_arr = sitk.GetArrayFromImage(mask)
#reader = sitk.ImageSeriesReader()
#dicom_names = reader.GetGDCMSeriesFileNames(folderPath)
#reader.SetFileNames(dicom_names)
#image = reader.Execute()
image = sitk.ReadImage('test.nii.gz')
image_arr = sitk.GetArrayFromImage(image) # Note: order:z, y, x !!
size = image.GetSize()
origin = image.GetOrigin() #order: x, y, z
spacing = image.GetSpacing() #order:x, y, z
direction = image.GetDirection()
pixelType = sitk.sitkInt8 #注意這里是Int8
image_new = sitk.Image(size,pixelType)
mask_new = sitk.Image(size,pixelType)
#image_arr_new = image_arr[:,:,::-1] #鏡像翻轉(zhuǎn)操作
image_arr_new = image_arr[:,:,:,0]
print(image_arr.shape)
image_new = sitk.GetImageFromArray(image_arr_new)
image_new.SetDirection(direction)
image_new.SetSpacing(spacing)
image_new.SetOrigin(origin)
mask_new = sitk.GetImageFromArray(mask_arr)
mask_new.SetDirection(direction)
mask_new.SetSpacing(spacing)
mask_new.SetOrigin(origin)
sitk.WriteImage(image_new,"test0.nii.gz")
sitk.WriteImage(mask_new,"mask0.nii.gz")
- 歷盡周折，現(xiàn)在test0.nii.gz文件和mask0.nii.gz文件相匹配了餐塘！可以愉快地提取影像組學(xué)特征了
Fig6.jpg
import radiomics
from radiomics import featureextractor
imageFile = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/test0.nii.gz"
maskFile = "/Users/Mac/Documents/JianShuNotes/2D_Ultrasound/mask0.nii.gz"
extractor = featureextractor.RadiomicsFeatureExtractor()
featureVector = extractor.execute(imageFile, maskFile)
#print(featureVector.items())
for featureName in featureVector.keys():
print("%s: %s" % (featureName, featureVector[featureName]))
Fig7.jpg
