将自己的dcm数据制作成LUNA16数据集提供数据样式之代码整理

1.获取mhd和raw

import cv2
import os
import pydicom
import numpy
import SimpleITK

# 路径和列表声明
rootpath="E:/DcmData/xlc/Fracture_data/Me/"
PathDicom = "E:/DcmData/xlc/Fracture_data/Me/3004291153/3307885/"  # 与python文件同一个目录下的文件夹,存储dicom文件
SaveRawDicom = "E:/DcmData/xlc/Fracture_data/mhd_raw/"  # 与python文件同一个目录下的文件夹,用来存储mhd文件和raw文件
def getSubPaths(dir):
    list = []
    # 判断路径是否存在
    if (os.path.exists(dir)):
        # 获取该目录下的所有文件或文件夹目录
        files = os.listdir(dir)
        for file in files:
            # 得到该文件下所有目录的路径
            m = os.path.join(dir, file)
            # 判断该路径下是否是文件夹
            if (os.path.isdir(m)):
                h = os.path.split(m)
                list.append(m)
    return list
def get_mhd_raw(PathDicom,SaveRawDicom):
    lstFilesDCM = []
    # for root, dirs, files in os.walk(PathDicom):
    #     for name in files:
    #         print(os.path.join(root, name))
    #     for name in dirs:
    #         print(os.path.join(root, name))

    # 将PathDicom文件夹下的dicom文件地址读取到lstFilesDCM中
    for dirName, subdirList, fileList in os.walk(PathDicom):
        for filename in fileList:
            if ".dcm" in filename.lower():  # 判断文件是否为dicom文件
                #print(filename)
                lstFilesDCM.append(os.path.join(dirName, filename))  # 加入到列表中

    # 第一步：将第一张图片作为参考图片，并认为所有图片具有相同维度
    RefDs = pydicom.read_file(lstFilesDCM[0])  # 读取第一张dicom图片
    print(RefDs.SOPInstanceUID)
    # 第二步：得到dicom图片所组成3D图片的维度
    ConstPixelDims = (int(RefDs.Rows), int(RefDs.Columns), len(lstFilesDCM))  # ConstPixelDims是一个元组

    # 第三步：得到x方向和y方向的Spacing并得到z方向的层厚
    ConstPixelSpacing = (float(RefDs.PixelSpacing[0]), float(RefDs.PixelSpacing[1]), float(RefDs.SliceThickness))

    # 第四步：得到图像的原点
    Origin = RefDs.ImagePositionPatient

    # 第五步：得到序列名称用于命名
    Seriesname=RefDs.SeriesInstanceUID

    # 根据维度创建一个numpy的三维数组，并将元素类型设为：pixel_array.dtype
    ArrayDicom = numpy.zeros(ConstPixelDims, dtype=RefDs.pixel_array.dtype)  # array is a numpy array

    # 第五步:遍历所有的dicom文件，读取图像数据，存放在numpy数组中
    i = 0
    for filenameDCM in lstFilesDCM:
        ds = pydicom.read_file(filenameDCM)
        #print(ds.SOPInstanceUID)
        #print(lstFilesDCM.index(filenameDCM))
        ArrayDicom[:, :, lstFilesDCM.index(filenameDCM)] = ds.pixel_array
        #cv2.imwrite("out_" + str(i) + ".png", ArrayDicom[:, :, lstFilesDCM.index(filenameDCM)])
        i += 1

    # 第六步：对numpy数组进行转置，即把坐标轴（x,y,z）变换为（z,y,x）,这样是dicom存储文件的格式，即第一个维度为z轴便于图片堆叠
    ArrayDicom = numpy.transpose(ArrayDicom, (2, 0, 1))

    # 第七步：将现在的numpy数组通过SimpleITK转化为mhd和raw文件
    sitk_img = SimpleITK.GetImageFromArray(ArrayDicom, isVector=False)
    sitk_img.SetSpacing(ConstPixelSpacing)
    sitk_img.SetOrigin(Origin)
    SimpleITK.WriteImage(sitk_img, os.path.join(SaveRawDicom, Seriesname+ ".mhd"))

list_classes = getSubPaths(rootpath)
for li in range(len(list_classes)):
    lc=getSubPaths(list_classes[li])
    PathDicom=lc[0]
    get_mhd_raw(PathDicom,SaveRawDicom)

2.根据csv（这里是dec文件，这是解码的锅，在pandas中功能与csv一致）获取转换后的数据csv

import pandas as pd
import os
import pydicom
#import csv
import numpy as np
#任意的多组列表
rootpath='E:/DcmData/xlc/Fracture_data/Me/'
#PathDicom = 'E:/DcmData/xlc/Fracture_data/Me/3004276169/3302845/'
#candidates = os.path.join(PathDicom,'RibFracture.dec')
def getSubPaths(dir):
    list = []
    # 判断路径是否存在
    if (os.path.exists(dir)):
        # 获取该目录下的所有文件或文件夹目录
        files = os.listdir(dir)
        for file in files:
            # 得到该文件下所有目录的路径
            m = os.path.join(dir, file)
            # 判断该路径下是否是文件夹
            if (os.path.isdir(m)):
                h = os.path.split(m)
                list.append(m)
    return list
def dcm_rename(dir):
    # 判断路径是否存在
    if (os.path.exists(dir)):
        # 获取该目录下的所有文件或文件夹目录
        files = os.listdir(dir)
        for file in files:
            # 得到该文件下所有目录的路径
            m = os.path.join(dir, file)
            #mp=os.path.splitext(file)[0] #获取文件名前缀,[-1]为后缀。
            if ".dcm" in file.lower():
                RefDs = pydicom.read_file(m)
                filename = RefDs.SOPInstanceUID
                os.rename(m, os.path.join(dir, filename + ".DCM"))

def csv_ch(PathDicom,rootpath):
    seriesuid = []
    coordX = []
    coordY = []
    coordZ = []
    DX = []
    DY = []
    cl = []
    candidates = os.path.join(PathDicom, 'RibFracture.dec')
    candidatesList = pd.read_csv(candidates)
    for i in range(len(candidatesList)):
        m = os.path.join(PathDicom, candidatesList.loc[i][5]+'.DCM')
        #print(m)
        if not os.path.isfile(m):#防止csv里SOPInstanceUID找不到对应dcm，相当于这些标记无用
            continue
        RefDs = pydicom.read_file(m)
        coordZ.append(RefDs.ImagePositionPatient[2])

        seriesuid.append(RefDs.SeriesInstanceUID)

        deslist = np.array(['正常', '隐匿型', '无错位', '有错位', '有骨痂', '畸形愈合'])
        for j in range(6):
            if candidatesList.loc[i][6] == deslist[j]:
                cl.append(j)
                break

        X = candidatesList.loc[i][9].split(';')
        Y = candidatesList.loc[i][10].split(';')
        ax = []
        ay = []
        for xi in range(len(X)-1):
            ax.append(X[xi])
        for yi in range(len(Y)-1):
            ay.append(Y[yi])
        ax = list(map(float, ax))
        ay = list(map(float, ay))
        minx = np.min(ax)*RefDs.PixelSpacing[0]+RefDs.ImagePositionPatient[0]
        maxx = np.max(ax)*RefDs.PixelSpacing[0]+RefDs.ImagePositionPatient[0]
        miny = np.min(ay)*RefDs.PixelSpacing[1]+RefDs.ImagePositionPatient[1]
        maxy = np.max(ay)*RefDs.PixelSpacing[1]+RefDs.ImagePositionPatient[1]
        coordX.append(minx)
        coordY.append(miny)
        DX.append(maxx-minx)
        DY.append(maxy-miny)

        csv_name=RefDs.SeriesInstanceUID+'.csv'
        csv_name=os.path.join(rootpath,csv_name)
    #字典中的key值即为csv中列名(放一起它的顺序很乱，只能一个一个往后面插入)
    dataframe = pd.DataFrame({'seriesuid':seriesuid})
    dataframe['coordX'] = coordX
    dataframe['coordY'] = coordY
    dataframe['coordZ'] = coordZ
    dataframe['DistanceX_mm'] = DX
    dataframe['DistanceY_mm'] = DY
    dataframe['class'] = cl

    #将DataFrame存储为csv,index表示是否显示行名，default=True
    dataframe.to_csv(csv_name,index=False,sep=',')
    return csv_name


# dcm_rename(PathDicom)
# csv_ch(PathDicom)
csv_path=os.path.join(rootpath,'candidates.csv')

list_classes = getSubPaths(rootpath)
for li in range(len(list_classes)):
    lc=getSubPaths(list_classes[li])
    PathDicom=lc[0]
    #print(PathDicom)
    dcm_rename(PathDicom)
    csv_ch(PathDicom,rootpath)

3.将这些csv合并

import pandas as pd
import os
import glob
csv_files = glob.glob('E:/DcmData/xlc/Fracture_data/Me/*.csv')
df = df = pd.DataFrame(columns=['seriesuid', 'coordX', 'coordY', 'coordZ', 'DistanceX_mm','DistanceY_mm','class'])
for csv in csv_files:
    df = pd.merge(df,pd.read_csv(csv),how='outer')
    os.remove(csv)
df_to_save = pd.DataFrame(df,columns=['seriesuid', 'coordX', 'coordY', 'coordZ', 'DistanceX_mm','DistanceY_mm','class'])
df_to_save.to_csv('annotations.csv',index=False)