可视化医学图像CT

DICOM格式

Digital Imaging and Communications in Medicine (DICOM)是医学标准格式的医学图像

2加载第三方包

IS_LOCAL = False
import numpy as np
import pandas as pd
from skimage.io import imread
import seaborn as sns
import matplotlib.pyplot as plt
from glob import glob
if(IS_LOCAL):
    import pydicom as dicom
else:
    import dicom
import os

2.参数设置和文件路径

if(IS_LOCAL):
    PATH="../input/siim-medical-image/"
else:
    PATH="../input/"
print(os.listdir(PATH))

3.读取数据

data_df = pd.read_csv(os.path.join(PATH,"overview.csv"))
Hide
In [4]:

print("CT Medical images -  rows:",data_df.shape[0]," columns:", data_df.shape[1])

4读取TIFF格式数据

print("Number of TIFF images:", len(os.listdir(os.path.join(PATH,"tiff_images"))))

tiff_data = pd.DataFrame([{\'path\': filepath} for filepath in glob(PATH+\'tiff_images/*.tif\')])

5.处理TIFF数据

def process_data(path):
    data = pd.DataFrame([{\'path\': filepath} for filepath in glob(PATH+path)])
    data[\'file\'] = data[\'path\'].map(os.path.basename)
    data[\'ID\'] = data[\'file\'].map(lambda x: str(x.split(\'_\')[1]))
    data[\'Age\'] = data[\'file\'].map(lambda x: int(x.split(\'_\')[3]))
    data[\'Contrast\'] = data[\'file\'].map(lambda x: bool(int(x.split(\'_\')[5])))
    data[\'Modality\'] = data[\'file\'].map(lambda x: str(x.split(\'_\')[6].split(\'.\')[-2]))
    return data

tiff_data = process_data(\'tiff_images/*.tif\')

6.检查数据集信息

tiff_data.head(10)

7.读取DICOM数据集

print("Number of DICOM files:", len(os.listdir(PATH+"dicom_dir")))

8.处理DICOM数据

dicom_data = process_data(\'dicom_dir/*.dcm\')

9.检查信息

dicom_data.head(10)

10.检查数据的一致性，

def countplot_comparison(feature):
    fig, (ax1, ax2, ax3) = plt.subplots(1,3, figsize = (16, 4))
    s1 = sns.countplot(data_df[feature], ax=ax1)
    s1.set_title("Overview data")
    s2 = sns.countplot(tiff_data[feature], ax=ax2)
    s2.set_title("Tiff files data")
    s3 = sns.countplot(dicom_data[feature], ax=ax3)
    s3.set_title("Dicom files data")
    plt.show()

11.显示TIFF图像

def show_images(data, dim=16, imtype=\'TIFF\'):
    img_data = list(data[:dim].T.to_dict().values())
    f, ax = plt.subplots(4,4, figsize=(16,20))
    for i,data_row in enumerate(img_data):
        if(imtype==\'TIFF\'): 
            data_row_img = imread(data_row[\'path\'])
        elif(imtype==\'DICOM\'):
            data_row_img = dicom.read_file(data_row[\'path\'])
        if(imtype==\'TIFF\'):
            ax[i//4, i%4].matshow(data_row_img,cmap=\'gray\')
        elif(imtype==\'DICOM\'):
            ax[i//4, i%4].imshow(data_row_img.pixel_array, cmap=plt.cm.bone) 
        ax[i//4, i%4].axis(\'off\')
        ax[i//4, i%4].set_title(\'Modality: {Modality} Age: {Age}\nSlice: {ID} Contrast: {Contrast}\'.format(**data_row))
    plt.show()

应用函数，显示图像

show_images(tiff_data,16,\'TIFF\')

12.显示DICOM数据

# extract voxel data  
def extract_voxel_data(list_of_dicom_files):  
    datasets = [dicom.read_file(f) for f in list_of_dicom_files]  
     try:  
         voxel_ndarray, ijk_to_xyz = dicom_numpy.combine_slices(datasets)  
     except dicom_numpy.DicomImportException as e:  
     # invalid DICOM data  
         raise  
     return voxel_ndarray

13.查看DICOMM更多的信息

dicom_file_path = list(dicom_data[:1].T.to_dict().values())[0][\'path\']
dicom_file_dataset = dicom.read_file(dicom_file_path)
dicom_file_dataset

更多的信息：哪个医院，病人年龄、性别、名字、病人的ID、诊断方式

14.我们可以修改可视化函数，来显示参数

def show_dicom_images(data):
    img_data = list(data[:16].T.to_dict().values())
    f, ax = plt.subplots(4,4, figsize=(16,20))
    for i,data_row in enumerate(img_data):
    data_row_img = dicom.read_file(data_row[\'path\'])
    modality = data_row_img.Modality
    age = data_row_img.PatientAge
    
    ax[i//4, i%4].imshow(data_row_img.pixel_array, cmap=plt.cm.bone) 
    ax[i//4, i%4].axis(\'off\')
    ax[i//4, i%4].set_title(\'Modality: {} Age: {}\nSlice: {} Contrast: {}\'.format(
     modality, age, data_row[\'ID\'], data_row[\'Contrast\']))
plt.show()</code></pre> 

  
参考资料https://www.kaggle.com/gpreda/visualize-ct-dicom-data