3dimaging

import numpy as np
from sklearn.metrics import roc_curve,  precision_recall_curve, auc, average_precision_score
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score
import pandas as pd
import pickle
#read in files
X_tumor = pd.read_csv('/home/wzli/Downloads/PF_parameter_MethodII_no_norm/data_sheet_for_random_forest_16_strike_tumor_9_0502_Method_II_no_norm.csv')
X_normal = pd.read_csv('/home/wzli/Downloads/PF_parameter_MethodII_no_norm/data_sheet_for_random_forest_16_strike_normal_9_0502_Method_II_no_norm.csv')

3dimaging

#!/usr/bin/env python3


#If you need more information about how ElementTree package handle XML file, please follow the link:
#https://docs.python.org/3/library/xml.etree.elementtree.html


#import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
import cv2

3dimaging

#!/usr/bin/env python3


#If you need more information about how ElementTree package handle XML file, please follow the link:
#https://docs.python.org/3/library/xml.etree.elementtree.html


#import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
import cv2

3dimaging

#!/usr/bin/env python3
import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
import os.path as osp
import openslide
import matplotlib.pyplot as plt
from pathlib import Path
import glob
import re
#please make sure the same number of files in the folder of tumor file and folder of annotation files

3dimaging

from keras.callbacks import Callback
import keras.backend as K
import numpy as np

class SGDRScheduler(Callback):
    '''Cosine annealing learning rate scheduler with periodic restarts.

    # Usage
        ```python
            schedule = SGDRScheduler(min_lr=1e-5,

3dimaging

from scipy.misc import imread, imresize

from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, merge, Reshape, Activation
from keras.models import Model
from keras.regularizers import l2
from keras.optimizers import SGD
from googlenet_custom_layers import PoolHelper,LRN


def create_googlenet(weights_path=None):

3dimaging

#!/usr/bin/env python3
import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
import os.path as osp
import openslide
import matplotlib.pyplot as plt
from pathlib import Path
import glob
#please make sure the same number of files in the folder of tumor file and folder of annotation files
#please change the slide_path, anno_path, mask_path accordingly, and leave everything else untouched. 

3dimaging

#!/usr/bin/env python3

import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
reader = mir.MultiResolutionImageReader()
mr_image = reader.open('/home/wli/Downloads/tumor_009.tif')
# dims=mr_image.getLevelDimensions(6)
# tile = mr_image.getUCharPatch(0, 0, dims[0], dims[1], 6)
# plt.imshow(tile)
# plt.show()

3dimaging

#!/usr/bin/env python3

import multiresolutionimageinterface as mir
import matplotlib.pyplot as plt
import cv2
import numpy as np

reader = mir.MultiResolutionImageReader()
mr_image = reader.open('/home/wli/Downloads/tumor_036.tif')
Ximageorg, Yimageorg = mr_image.getDimensions()

3dimaging

I did this under python3.5, which is the default version for python3 in Ubuntu

sudo apt-get install python3-tk
sudo apt-get install libpython3.6-dev
pip3 install matplotlib numpy


then download ASAP from the website: https://github.com/computationalpathologygroup/ASAP/releases