def prepare_dicom_images(input_data_folder, output_data_folder,
exam_list_path):
dcm_files = glob.glob(os.path.join(input_data_folder, "**", "*.dcm"),
recursive=True)
os.makedirs(output_data_folder, exist_ok=True)
saving_images.save_dicom_image_as_png(
find_view(dcm_files, "L", "CC"),
os.path.join(output_data_folder, "L_CC.png"))
saving_images.save_dicom_image_as_png(
find_view(dcm_files, "R", "CC"),
os.path.join(output_data_folder, "R_CC.png"))
saving_images.save_dicom_image_as_png(
find_view(dcm_files, "L", "MLO"),
os.path.join(output_data_folder, "L_MLO.png"))
saving_images.save_dicom_image_as_png(
find_view(dcm_files, "R", "MLO"),
os.path.join(output_data_folder, "R_MLO.png"))
exam_list = [{
'horizontal_flip': 'NO',
'L-CC': ['L_CC'],
'R-CC': ['R_CC'],
'L-MLO': ['L_MLO'],
'R-MLO': ['R_MLO']
}]
pickling.pickle_to_file(exam_list_path, exam_list)
def crop_single_mammogram(mammogram_path, horizontal_flip, view,
cropped_mammogram_path, metadata_path,
num_iterations, buffer_size):
"""
Crop a single mammogram image
"""
metadata_dict = dict(
short_file_path=None,
horizontal_flip=horizontal_flip,
full_view=view,
side=view[0],
view=view[2:],
)
cropped_image_info = crop_mammogram.crop_mammogram_one_image(
scan=metadata_dict,
input_file_path=mammogram_path,
output_file_path=cropped_mammogram_path,
num_iterations=num_iterations,
buffer_size=buffer_size,
)
metadata_dict["window_location"] = cropped_image_info[0]
metadata_dict["rightmost_points"] = cropped_image_info[1]
metadata_dict["bottommost_points"] = cropped_image_info[2]
metadata_dict["distance_from_starting_side"] = cropped_image_info[3]
pickling.pickle_to_file(metadata_path, metadata_dict)
def get_optimal_center_single(cropped_mammogram_path, metadata_path):
"""
Get optimal center for single example
"""
metadata = pickling.unpickle_from_file(metadata_path)
image = reading_images.read_image_png(cropped_mammogram_path)
optimal_center = get_optimal_centers.extract_center(metadata, image)
metadata["best_center"] = optimal_center
pickling.pickle_to_file(metadata_path, metadata)
def main(cropped_exam_list_path, data_prefix, output_exam_list_path, num_processes=1):
exam_list = pickling.unpickle_from_file(cropped_exam_list_path)
data_list = data_handling.unpack_exam_into_images(exam_list, cropped=True)
optimal_centers = get_optimal_centers(
data_list=data_list,
data_prefix=data_prefix,
num_processes=num_processes
)
data_handling.add_metadata(exam_list, "best_center", optimal_centers)
os.makedirs(os.path.dirname(output_exam_list_path), exist_ok=True)
pickling.pickle_to_file(output_exam_list_path, exam_list)
def crop_mammogram():
id_patient = request.args.get('id')
input_data_folder = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/sample_data/' + id_patient
# exam_list_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/sample_data/exam_list_before_cropping.pkl'
exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/sample_data/filename.pkl'
cropped_exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient + '/' + id_patient + '.pkl'
output_data_folder = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient
num_processes = 10
num_iterations = 100
buffer_size = 50
exam_list = pickling.unpickle_from_file(exam_list_path)
image_list = data_handling.unpack_exam_into_images(exam_list)
if os.path.exists(output_data_folder):
# Prevent overwriting to an existing directory
print("Error: the directory to save cropped images already exists.")
sh.rmtree(
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/cropped_images'
)
os.makedirs(output_data_folder)
crop_mammogram_one_image_func = partial(
crop_mammogram_one_image,
input_data_folder=input_data_folder,
output_data_folder=output_data_folder,
num_iterations=num_iterations,
buffer_size=buffer_size,
)
with Pool(num_processes) as pool:
cropped_image_info = pool.map(crop_mammogram_one_image_func,
image_list)
window_location_dict = dict([x[0] for x in cropped_image_info])
rightmost_points_dict = dict([x[1] for x in cropped_image_info])
bottommost_points_dict = dict([x[2] for x in cropped_image_info])
distance_from_starting_side_dict = dict([x[3] for x in cropped_image_info])
data_handling.add_metadata(exam_list, "window_location",
window_location_dict)
data_handling.add_metadata(exam_list, "rightmost_points",
rightmost_points_dict)
data_handling.add_metadata(exam_list, "bottommost_points",
bottommost_points_dict)
data_handling.add_metadata(exam_list, "distance_from_starting_side",
distance_from_starting_side_dict)
pickling.pickle_to_file(cropped_exam_list_path, exam_list)
return jsonify("Done")
def crop_mammogram(input_data_folder, exam_list_path,
cropped_exam_list_path, output_data_folder,
num_processes, num_iterations, buffer_size):
"""
In parallel, crops mammograms in DICOM format found in input_data_folder and save as png format in
output_data_folder and saves new image list in cropped_image_list_path
"""
exam_list = pickling.unpickle_from_file(exam_list_path)
image_list = data_handling.unpack_exam_into_images(exam_list)
if os.path.exists(output_data_folder):
# Prevent overwriting to an existing directory
print(
"Error: the directory to save cropped images already exists."
)
return
else:
os.makedirs(output_data_folder)
#global crop_mammogram_one_image_func
crop_mammogram_one_image_func = partial(
crop_mammogram_one_image_short_path,
input_data_folder=input_data_folder,
output_data_folder=output_data_folder,
num_iterations=num_iterations,
buffer_size=buffer_size,
)
with Pool(num_processes) as pool:
cropped_image_info = pool.map(
crop_mammogram_one_image_func, image_list)
window_location_dict = dict([x[0] for x in cropped_image_info])
rightmost_points_dict = dict(
[x[1] for x in cropped_image_info])
bottommost_points_dict = dict(
[x[2] for x in cropped_image_info])
distance_from_starting_side_dict = dict(
[x[3] for x in cropped_image_info])
data_handling.add_metadata(exam_list, "window_location",
window_location_dict)
data_handling.add_metadata(exam_list, "rightmost_points",
rightmost_points_dict)
data_handling.add_metadata(exam_list, "bottommost_points",
bottommost_points_dict)
data_handling.add_metadata(exam_list,
"distance_from_starting_side",
distance_from_starting_side_dict)
pickling.pickle_to_file(cropped_exam_list_path, exam_list)
def crop_mammogram(input_data_folder, exam_list_path, cropped_exam_list_path,
output_data_folder, num_processes, num_iterations,
buffer_size):
"""
In parallel, crops mammograms in DICOM format found in input_data_folder and save as png format in
output_data_folder and saves new image list in cropped_image_list_path
"""
# list of exams (one dictionary per exam)
exam_list = pickling.unpickle_from_file(exam_list_path)
# list per image (one dictionary per image). It contains same information than in list of exams + cropped information if present.
image_list = data_handling.unpack_exam_into_images(exam_list)
if os.path.exists(output_data_folder):
# Prevent overwriting to an existing directory
print("Error: the directory to save cropped images already exists.")
return
else:
os.makedirs(output_data_folder)
crop_mammogram_one_image_func = partial(
crop_mammogram_one_image_short_path,
input_data_folder=input_data_folder,
output_data_folder=output_data_folder,
num_iterations=num_iterations,
buffer_size=buffer_size,
)
with Pool(num_processes) as pool:
cropped_image_info = pool.map(crop_mammogram_one_image_func,
image_list)
# F: cropped image info returns a list. Each entry is the return of a single execution
# F: of crop_mammogram_one_image_func.
# F: each dict defined contains the information of all images
window_location_dict = dict([x[0] for x in cropped_image_info])
rightmost_points_dict = dict([x[1] for x in cropped_image_info])
bottommost_points_dict = dict([x[2] for x in cropped_image_info])
distance_from_starting_side_dict = dict([x[3] for x in cropped_image_info])
data_handling.add_metadata(exam_list, "window_location",
window_location_dict)
data_handling.add_metadata(exam_list, "rightmost_points",
rightmost_points_dict)
data_handling.add_metadata(exam_list, "bottommost_points",
bottommost_points_dict)
data_handling.add_metadata(exam_list, "distance_from_starting_side",
distance_from_starting_side_dict)
pickling.pickle_to_file(cropped_exam_list_path, exam_list)
def main():
id_patient = request.args.get('id');
cropped_exam_list_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/'+id_patient+'/'+id_patient+'.pkl'
data_prefix='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/'+id_patient
output_exam_list_path='sample_output/'+id_patient+'.pkl'
num_processes = 10
id_patient = request.args.get('id');
exam_list = pickling.unpickle_from_file(cropped_exam_list_path)
data_list = data_handling.unpack_exam_into_images(exam_list, cropped=True)
optimal_centers = get_optimal_centers(
data_list=data_list,
data_prefix=data_prefix,
num_processes=num_processes
)
data_handling.add_metadata(exam_list, "best_center", optimal_centers)
os.makedirs(os.path.dirname(output_exam_list_path), exist_ok=True)
pickling.pickle_to_file(output_exam_list_path, exam_list)
return jsonify("Done")
def crop_mammogram():
id_patient = request.args.get('id')
input_data_folder = 'C:/Users/ultra/PycharmProjects/BIRADS_classifier-master/images/' + id_patient
# exam_list_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/sample_data/exam_list_before_cropping.pkl'
exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/sample_data/filename.pkl'
cropped_exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient + '/' + id_patient + '.pkl'
output_data_folder = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient
num_processes = 10
num_iterations = 100
buffer_size = 50
exam_list = pickling.unpickle_from_file(exam_list_path)
image_list = data_handling.unpack_exam_into_images(exam_list)
if os.path.exists(output_data_folder):
# Prevent overwriting to an existing directory
print("Error: the directory to save cropped images already exists.")
sh.rmtree(
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/'
+ id_patient)
os.makedirs(output_data_folder)
crop_mammogram_one_image_func = ps(
crop_mammogram_one_image,
input_data_folder=input_data_folder,
output_data_folder=output_data_folder,
num_iterations=num_iterations,
buffer_size=buffer_size,
)
with Pool(num_processes) as pool:
cropped_image_info = pool.map(crop_mammogram_one_image_func,
image_list)
window_location_dict = dict([x[0] for x in cropped_image_info])
rightmost_points_dict = dict([x[1] for x in cropped_image_info])
bottommost_points_dict = dict([x[2] for x in cropped_image_info])
distance_from_starting_side_dict = dict([x[3] for x in cropped_image_info])
data_handling.add_metadata(exam_list, "window_location",
window_location_dict)
data_handling.add_metadata(exam_list, "rightmost_points",
rightmost_points_dict)
data_handling.add_metadata(exam_list, "bottommost_points",
bottommost_points_dict)
data_handling.add_metadata(exam_list, "distance_from_starting_side",
distance_from_starting_side_dict)
pickling.pickle_to_file(cropped_exam_list_path, exam_list)
###NEXT####
cropped_exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient + '/' + id_patient + '.pkl'
data_prefix = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/' + id_patient
output_exam_list_path = 'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/' + id_patient + '.pkl'
num_processes = 10
id_patient = request.args.get('id')
exam_list = pickling.unpickle_from_file(cropped_exam_list_path)
data_list = data_handling.unpack_exam_into_images(exam_list, cropped=True)
optimal_centers = get_optimal_centers(data_list=data_list,
data_prefix=data_prefix,
num_processes=num_processes)
data_handling.add_metadata(exam_list, "best_center", optimal_centers)
os.makedirs(os.path.dirname(output_exam_list_path), exist_ok=True)
pickling.pickle_to_file(output_exam_list_path, exam_list)
###NEXT #####
parser = argparse.ArgumentParser(
description='Run image-only model or image+heatmap model')
# parser.add_argument('--model-path', required=True)
# parser.add_argument('--data-path', required=True)
# parser.add_argument('--image-path', required=True)
# parser.add_argument('--output-path', required=True)
parser.add_argument('--batch-size', default=1, type=int)
parser.add_argument('--seed', default=0, type=int)
parser.add_argument('--use-heatmaps', action="store_true")
parser.add_argument('--heatmaps-path')
parser.add_argument('--use-augmentation', action="store_true")
parser.add_argument('--use-hdf5', action="store_true")
# parser.add_argument('--num-epochs', default=1, type=int)
# parser.add_argument('--device-type', default="cpu", choices=['gpu', 'cpu'])
# parser.add_argument("--gpu-number", type=int, default=0)
args = parser.parse_args()
parameters = {
"device_type":
'gpu',
"gpu_number":
0,
"max_crop_noise": (100, 100),
"max_crop_size_noise":
100,
"image_path":
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/cropping/sample_output/'
+ id_patient,
"batch_size":
args.batch_size,
"seed":
args.seed,
"augmentation":
args.use_augmentation,
"num_epochs":
10,
"use_heatmaps":
args.use_heatmaps,
"heatmaps_path":
args.heatmaps_path,
# "heatmaps_path": 'C:/Users/ultra/jPycharmProjects/breast_cancer_classifier/src/cropping/sample_output/heatmaps_'+id_patient,
"use_hdf5":
args.use_hdf5
}
# load_run_save(
# model_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/models/sample_image_model.p',
# data_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/' + id_patient + '.pkl',
# # output_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/image_predictions.csv',
# output_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/' + id_patient + '.csv',
# parameters=parameters,
# )
return load_run_save(
model_path=
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/models/sample_image_model.p',
data_path=
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/'
+ id_patient + '.pkl',
# output_path='C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/image_predictions.csv',
output_path=
'C:/Users/ultra/PycharmProjects/breast_cancer_classifier/src/optimal_centers/sample_output/'
+ id_patient + '.csv',
parameters=parameters,
)
import os, sys
# print(sys.path)
current_dir = os.path.dirname(os.path.abspath(__file__))
# appending parent dir of current_dir to sys.path
sys.path.append(os.path.dirname(current_dir))
from multiprocessing import Pool
import argparse
from functools import partial
import scipy.ndimage
import numpy as np
import pandas as pd
import src.utilities.pickling as pickling
import src.utilities.reading_images as reading_images
import src.utilities.saving_images as saving_images
import src.utilities.data_handling as data_handling
# list of exams (one dictionary per exam)
exam_list = pickling.unpickle_from_file('exam_list_before_cropping.pkl')
cropped_exam_list_path = '../sample_output/cropped_images/cropped_exam_list_test.pkl'
print(exam_list)
exam_list[0]['L-CC'] = []
# list per image (one dictionary per image). It contains same information than in list of exams + cropped information if present.
image_list = data_handling.unpack_exam_into_images(exam_list)
pickling.pickle_to_file(cropped_exam_list_path, exam_list)