python - 如何使用 Python 中的自适应阈值从 numpy ndarray 类型的 CT 图像中分割骨骼

Question

这是我的示例代码。我尝试将自适应阈值应用于分割骨骼。加载存储为 mat 文件的 Dicom 文件数据并提取 ct 图像。然后取一片 NumPy.ndarray 类型的 CT 数据，然后将其转换为 CV_8UC1 类型以应用阈值。

param = yaml.load(open("parameters.yaml"))
filenames = os.listdir(param['path_to_data'])
targetfolder = []

for i in range(0,len(filenames)):
  data = read_mat(os.path.join(param['path_to_data'],filenames[i]))
    
  ct_image = data['ct_image']
  mid_slice = np.round(np.array(data['ct_image'].shape)/2).astype(int)          
  ct_slice = ct_image[:,:,mid_slice[2]]
   
  u8 = ct_slice.astype(np.uint8)    
  cv2.imshow('im',u8)
  
  thresh1 = cv2.adaptiveThreshold(u8, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 701, 2)   
  thresh2 = cv2.adaptiveThreshold(u8,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,11,2)   

  titles = ['Original Image', 'Adaptive Mean Thresholding', 'Adaptive Gaussian Thresholding']
  images = [u8, thresh1,thresh2,thresh3]

  for i in range(4):
    plt.subplot(2,2,i+1),plt.imshow(images[i],'gray')
    plt.title(titles[i])
    plt.xticks([]),plt.yticks([])
  plt.show()