97 lines
2.4 KiB
Python
97 lines
2.4 KiB
Python
|
import os
|
||
|
|
import statistics
|
||
|
|
|
||
|
|
import imageio
|
||
|
|
|
||
|
|
from PIL import Image, ImageFilter, ImageMath
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
import SimpleITK as sitk
|
||
|
|
|
||
|
|
STUDY_PATH = "/media/nfs/SRS/storage/0/CT Without Contrast-Brain_55121720"
|
||
|
|
STUDY_PATH = '/media/nfs/SRS/storage/0/MRI With_Without Contrast--Brain_54141890'
|
||
|
|
|
||
|
|
MODEL_PATH = '/home/xfr/nni/model-5-64/TwNuKtj7/best_zdoyO.pth'
|
||
|
|
|
||
|
|
|
||
|
|
# Write image series using SimpleITK
|
||
|
|
def flush_file(shape, fileNames):
|
||
|
|
if len(fileNames) > 1:
|
||
|
|
|
||
|
|
xy = min(shape)
|
||
|
|
|
||
|
|
outfile = '%s.nii.gz' % os.path.basename(fileNames[0]).split('.')[0]
|
||
|
|
img = sitk.ReadImage(fileNames)
|
||
|
|
img.SetSpacing([1.0,1.0, 1.0*xy/len(fileNames)])
|
||
|
|
sitk.WriteImage(img, outfile)
|
||
|
|
|
||
|
|
|
||
|
|
COR_ABS_THRESHOLD = 0.5
|
||
|
|
COR_REL_THRESHOLD = 0.8
|
||
|
|
|
||
|
|
def lower_bound(cors):
|
||
|
|
THRESHOLD = 3
|
||
|
|
if len(cors) < 2:
|
||
|
|
return 0
|
||
|
|
|
||
|
|
return min(statistics.mean(cors) - statistics.stdev(cors) * THRESHOLD, min(cors[:-1]))
|
||
|
|
|
||
|
|
def lower_bound2(cors):
|
||
|
|
THRESHOLD = 1.5
|
||
|
|
if len(cors) < 1:
|
||
|
|
return 0
|
||
|
|
Q1 = np.percentile(cors, 25, interpolation = 'lower')
|
||
|
|
Q3 = np.percentile(cors, 25, interpolation = 'higher')
|
||
|
|
IQR = Q3 - Q1
|
||
|
|
return min(Q1 - THRESHOLD * IQR, min(cors[:-1]))
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
old_shape = None
|
||
|
|
old_array = None
|
||
|
|
old_cor = COR_ABS_THRESHOLD
|
||
|
|
fileNames = []
|
||
|
|
cors = []
|
||
|
|
|
||
|
|
for jpg_file in sorted(os.listdir(STUDY_PATH)):
|
||
|
|
jpg_path = os.path.join(STUDY_PATH, jpg_file)
|
||
|
|
|
||
|
|
array = np.asarray(Image.open(jpg_path).convert('L'))
|
||
|
|
shape = array.shape
|
||
|
|
|
||
|
|
# LB = lower_bound(cors)
|
||
|
|
|
||
|
|
if not fileNames:
|
||
|
|
cor = COR_ABS_THRESHOLD
|
||
|
|
else:
|
||
|
|
if old_shape != shape:
|
||
|
|
cor =0
|
||
|
|
else:
|
||
|
|
# cor = correlate (old_array, array)
|
||
|
|
cor = np.corrcoef(old_array.flat, array.flat)[0,1]
|
||
|
|
cors.append(cor)
|
||
|
|
|
||
|
|
# if cor < COR_ABS_THRESHOLD or cor < old_cor * COR_REL_THRESHOLD:
|
||
|
|
LB = lower_bound(cors)
|
||
|
|
if cor < COR_ABS_THRESHOLD or cor < LB:
|
||
|
|
flush_file(old_shape, fileNames)
|
||
|
|
fileNames = [jpg_path]
|
||
|
|
cors = []
|
||
|
|
mark = '**********'
|
||
|
|
else:
|
||
|
|
fileNames.append(jpg_path)
|
||
|
|
mark = len(fileNames)
|
||
|
|
print('%s %.4f %.4f %s' %(jpg_file,cor, LB, mark))
|
||
|
|
|
||
|
|
old_array = array
|
||
|
|
old_shape = shape
|
||
|
|
old_cor = cor
|
||
|
|
|
||
|
|
flush_file(old_shape, fileNames)
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
main()
|