Candidate Generation and LUNA16 preprocessing

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here‘s several helpful packages to load in 

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import skimage, os
from skimage.morphology import ball, disk, dilation, binary_erosion, remove_small_objects, erosion, closing, reconstruction, binary_closing
from skimage.measure import label,regionprops, perimeter
from skimage.morphology import binary_dilation, binary_opening
from skimage.filters import roberts, sobel
from skimage import measure, feature
from skimage.segmentation import clear_border
from skimage import data
from scipy import ndimage as ndi
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d.art3d import Poly3DCollection
import dicom
import scipy.misc
import numpy as np

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

from subprocess import check_output
print(check_output(["ls", "../input"]).decode("utf8"))
#上面两句话是无法在windows下执行的（没有ls的binay文件）
import os

cwd = os.getcwd()
file_path=cwd+‘/input‘
print(os.listdir(file_path))

image_path=file_path+‘/sample_images‘
print(os.listdir(image_path))

# Any results you write to the current directory are saved as output.
def loadFileInformation(filename):
    information = {}
    ds = dicom.read_file(filename)
    information[‘PatientID‘] = ds.PatientID
    information[‘PatientName‘] = ds.PatientName
    information[‘PatientBirthDate‘] = ds.PatientBirthDate
    return information

random_dcm_path=image_path+‘/00cba091fa4ad62cc3200a657aeb957e/38c4ff5d36b5a6b6dc025435d62a143d.dcm‘
# print(loadFileInformation(random_dcm_path))
lung = dicom.read_file(random_dcm_path)

slice = lung.pixel_array
slice[slice == -2000] = 0
plt.imshow(slice, cmap=plt.cm.gray)
plt.show()

def read_ct_scan(folder_name):
    # Read the slices from the dicom file
    slices = [dicom.read_file(folder_name + ‘/‘+filename) for filename in os.listdir(folder_name)]

    # Sort the dicom slices in their respective order
    slices.sort(key=lambda x: int(x.InstanceNumber))

    # Get the pixel values for all the slices
    slices = np.stack([s.pixel_array for s in slices])
    slices[slices == -2000] = 0
    return slices
某个病人CT_path=image_path+‘/00cba091fa4ad62cc3200a657aeb957e‘
ct_scan = read_ct_scan(某个病人CT_path)

def plot_ct_scan(scan):
    f, plots = plt.subplots(int(scan.shape[0] / 20) + 1, 4, figsize=(25, 25))
    for i in range(0, scan.shape[0], 5):
        plots[int(i / 20), int((i % 20) / 5)].axis(‘off‘)
        plots[int(i / 20), int((i % 20) / 5)].imshow(scan[i], cmap=plt.cm.bone)
plot_ct_scan(ct_scan)
plt.show()

def get_segmented_lungs(im, plot=False):
    ‘‘‘
    This funtion segments the lungs from the given 2D slice.
    ‘‘‘
    if plot == True:
        f, plots = plt.subplots(8, 1, figsize=(5, 40))
    ‘‘‘
    Step 1: Convert into a binary image.
    ‘‘‘
    binary = im < 604
    if plot == True:
        plots[0].axis(‘off‘)
        plots[0].imshow(binary, cmap=plt.cm.bone)
    ‘‘‘
    Step 2: Remove the blobs connected to the border of the image.
    ‘‘‘
    cleared = clear_border(binary)
    if plot == True:
        plots[1].axis(‘off‘)
        plots[1].imshow(cleared, cmap=plt.cm.bone)
    ‘‘‘
    Step 3: Label the image.
    ‘‘‘
    label_image = label(cleared)
    if plot == True:
        plots[2].axis(‘off‘)
        plots[2].imshow(label_image, cmap=plt.cm.bone)
    ‘‘‘
    Step 4: Keep the labels with 2 largest areas.
    ‘‘‘
    areas = [r.area for r in regionprops(label_image)]
    areas.sort()
    if len(areas) > 2:
        for region in regionprops(label_image):
            if region.area < areas[-2]:
                for coordinates in region.coords:
                    label_image[coordinates[0], coordinates[1]] = 0
    binary = label_image > 0
    if plot == True:
        plots[3].axis(‘off‘)
        plots[3].imshow(binary, cmap=plt.cm.bone)
    ‘‘‘
    Step 5: Erosion operation with a disk of radius 2. This operation is
    seperate the lung nodules attached to the blood vessels.
    ‘‘‘
    selem = disk(2)
    binary = binary_erosion(binary, selem)
    if plot == True:
        plots[4].axis(‘off‘)
        plots[4].imshow(binary, cmap=plt.cm.bone)
    ‘‘‘
    Step 6: Closure operation with a disk of radius 10. This operation is
    to keep nodules attached to the lung wall.
    ‘‘‘
    selem = disk(10)
    binary = binary_closing(binary, selem)
    if plot == True:
        plots[5].axis(‘off‘)
        plots[5].imshow(binary, cmap=plt.cm.bone)
    ‘‘‘
    Step 7: Fill in the small holes inside the binary mask of lungs.
    ‘‘‘
    edges = roberts(binary)
    binary = ndi.binary_fill_holes(edges)
    if plot == True:
        plots[6].axis(‘off‘)
        plots[6].imshow(binary, cmap=plt.cm.bone)
    ‘‘‘
    Step 8: Superimpose the binary mask on the input image.
    ‘‘‘
    get_high_vals = binary == 0
    im[get_high_vals] = 0
    if plot == True:
        plots[7].axis(‘off‘)
        plots[7].imshow(im, cmap=plt.cm.bone)

    return im

get_segmented_lungs(ct_scan[71], True)
plt.show()