本人下载的CT医学影像数据集源文件为DICOM文件,需要进行数据集处理后进行后续的模型训练。
1.dcm格式转换为jpg格式
首先考虑将dcm格式转换为jpg格式。代码实现如下。
ps:需要手动更改dicom文件夹源路径以及输出文件夹源路径。
import SimpleITK as sitk
import numpy as np
import cv2
import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'
import PIL
import image
count = 1
path = "D:\\**********/"
filename = os.listdir(path)
print(filename)
for i in filename:
document = os.path.join(path, i)
outputpath = "E:\\*******/"
countname = str(count)
countfullname = countname + '.jpg'
output_jpg_path = os.path.join(outputpath, countfullname)
def convert_from_dicom_to_jpg(img, low_window, high_window, save_path):
lungwin = np.array([low_window * 1., high_window * 1.])
newimg = (img - lungwin[0]) / (lungwin[1] - lungwin[0])
newimg = (newimg * 255).astyp