import numpy as np
import SlideRunner.general.dependencies
from SlideRunner.dataAccess.database import Database
import os
import openslide
import sqlite3
import cv2
import sys
if (len(sys.argv) < 2) or (sys.argv[1] not in ['3', '6', '12']):
print('syntax: exportDataset_ODAEL_xWSI.py x')
print(' where x is the number of WSI to export (3,6,12)')
exit()
DB = Database()
basepath = '../../WSI/'
patchSize = 128
os.system('mkdir -p DataODAEL_%sWSI' % sys.argv[1])
dirs = ['Mitosis', 'Mitosislike', 'Tumorcells', 'Granulocytes']
for k in dirs:
os.system('mkdir -p DataODAEL_%sWSI/train/%s' % (sys.argv[1], k))
os.system('mkdir -p DataODAEL_%sWSI/test/%s' % (sys.argv[1], k))
def listOfSlides(DB):
DB.execute('SELECT uid,filename from Slides')
return DB.fetchall()
from SlideRunner.dataAccess.database import Database
DB = Database()
slidelist_test = ['27', '30', '31', '6', '18', '20', '1', '2', '3', '9', '11']
clause = ','.join(slidelist_test)
files = [
'MITOS_WSI_CCMCT_ODAEL_50HPF.sqlite', 'MITOS_WSI_CCMCT_ODAEL_10HPF.sqlite',
'MITOS_WSI_CCMCT_ODAEL_5HPF.sqlite', 'MITOS_WSI_CCMCT_ODAEL_12WSI.sqlite',
'MITOS_WSI_CCMCT_ODAEL_6WSI.sqlite', 'MITOS_WSI_CCMCT_ODAEL_3WSI.sqlite',
'MITOS_WSI_CCMCT_ODAEL.sqlite'
]
for f in files:
DB.open('databases/' + f)
cnt = DB.execute(
'SELECT COUNT(*) FROM Annotations where agreedClass==2 and slide not in (%s)'
% clause).fetchone()[0]
print('%40s: %d mitotic figures in training set' % (f, cnt))
DB.open(files[-1])
slidelist_train = [
s[0] for s in DB.execute(
'SELECT Slides.filename, count(*) as cnt FROM Slides left join Annotations on Annotations.slide == Slides.uid where Slides.uid not in (%s) and Annotations.agreedClass==2 group by slide order by cnt asc'
% clause).fetchall()
]
slidelist_cnt = {
# Export Dataset (patch-wise) to learn classifier easier
import numpy as np
import SlideRunner.general.dependencies
from SlideRunner.dataAccess.database import Database
from SlideRunner.dataAccess.annotations import ViewingProfile
import os
import openslide
import sqlite3
import cv2
import sys
DB = Database()
basepath='../WSI/'
patchSize=128
os.system('mkdir -p DataODAEL')
dirs = ['Mitosis', 'Mitosislike', 'Tumorcells', 'Granulocytes']
for k in dirs:
os.system('mkdir -p DataODAEL/train/%s' % (k))
os.system('mkdir -p DataODAEL/test/%s' % (k))
def listOfSlides(DB):
DB.execute('SELECT uid,filename from Slides')
return DB.fetchall()
test_slide_filenames = ['be10fa37ad6e88e1f406.svs',
'f3741e764d39ccc4d114.svs',
'c86cd41f96331adf3856.svs',
if (len(sys.argv) < 5):
print(
'Syntax: Inference-RetinaNet-var.py ModelSavepath.pkl Database.sqlite DatasetName val/test [SlideDir]'
)
exit()
fname = 'RetinaNet-CMC-CODAEL-512sh-repetition1.pkl'
if len(sys.argv) > 1:
fname = sys.argv[1]
size = 512
path = Path('./')
database = Database()
database.open(str(
sys.argv[2])) #Slides_Mitosis_final_checked_cleaned.sqlite'))
slidedir = 'WSI' if len(sys.argv) < 5 else sys.argv[5]
datasetname = sys.argv[3]
size = 512
level = 0
files = []
# In[3]:
test_slide_filenames = [
'be10fa37ad6e88e1f406.svs', 'f3741e764d39ccc4d114.svs',
'c86cd41f96331adf3856.svs', '552c51bfb88fd3e65ffe.svs',
def test_pushannos():
imageset = 1
product_id = 1
exm = ExactManager('sliderunner_unittest', 'unittestpw',
EXACT_UNITTEST_URL)
randstr = ''.join(
['{:02x}'.format(x) for x in np.random.randint(0, 255, 6)])
imagename = f'dummy{randstr}.tiff'
# generate dummy image
dummy = np.random.randint(0, 255, (200, 200, 3))
cv2.imwrite(imagename, dummy)
exm.upload_image_to_imageset(imageset_id=imageset, filename=imagename)
imageset_details = exm.retrieve_imageset(imageset)
# print(imageset_details)
for imset in imageset_details['images']:
if (imset['name'] == imagename):
imageid = imset['id']
DB = Database().create(':memory:')
# DB = Database().create('test.sqlite')
# Add slide to database
slideuid = DB.insertNewSlide(imagename, '')
DB.insertClass('BB')
DB.insertAnnotator('sliderunner_unittest')
DB.insertAnnotator(
'otherexpert') # we will only send annotations of the marked expert
DB.insertClass('POLY')
coords = np.array([[100, 200], [150, 220], [180, 250]])
DB.insertNewPolygonAnnotation(annoList=coords,
slideUID=1,
classID=2,
annotator=1)
coords = np.array([[150, 250], [350, 220], [0, 250]])
DB.insertNewPolygonAnnotation(annoList=coords,
slideUID=1,
classID=2,
annotator=1)
coords = np.array([[150, 255], [350, 210], [50, 250]])
DB.insertNewPolygonAnnotation(annoList=coords,
slideUID=1,
classID=2,
annotator=2)
DB.setExactPerson(1)
#empty image
annos = exm.retrieve_annotations(imageid)
for anno in annos:
exm.delete_annotation(anno['id'], keep_deleted_element=False)
# for anno in exm.retrieve_annotations(imageid):
# print(anno)
# All annotations have been removed
assert (len(exm.retrieve_annotations(imageid)) == 0)
exm.sync(imageid,
imageset_id=imageset,
product_id=product_id,
slideuid=slideuid,
database=DB)
# Only 2 annotations have been inserted
assert (len(exm.retrieve_annotations(imageid)) == 2)
uuids = [x['unique_identifier'] for x in exm.retrieve_annotations(imageid)]
# All were created with correct guid
for dbanno in list(DB.annotations.keys())[:-1]:
assert (DB.annotations[dbanno].guid in uuids)
print('--- resync ---')
# Sync again
exm.sync(imageid,
imageset_id=imageset,
product_id=product_id,
slideuid=slideuid,
database=DB)
# No change
assert (len(exm.retrieve_annotations(imageid)) == 2)
# All were created with correct guid
uuids = [x['unique_identifier'] for x in exm.retrieve_annotations(imageid)]
for dbanno in list(DB.annotations.keys())[:-1]:
assert (DB.annotations[dbanno].guid in uuids)
print('--- local update created ---')
# Now let's create a local update - keep same exact_id (crucial!)
DB.loadIntoMemory(1)
DB.setAnnotationLabel(classId=1,
person=1,
annoIdx=1,
entryId=DB.annotations[1].labels[0].uid,
exact_id=DB.annotations[1].labels[0].exact_id)
# Sync again
exm.sync(imageid,
imageset_id=imageset,
product_id=product_id,
slideuid=slideuid,
database=DB)
# check if remote has been updated
annos = exm.retrieve_annotations(imageid)
for anno in annos:
if (anno['id'] == DB.annotations[1].labels[0].exact_id):
assert (anno['annotation_type']['name'] == 'BB')
annotype_id = anno['annotation_type']['id']
# Now update remotely and see if changes are reflected
newguid = str(uuid.uuid4())
created = exm.create_annotation(image_id=imageid,
annotationtype_id=annotype_id,
vector=[[90, 80], [20, 30]],
last_modified=time.time(),
guid=newguid,
description='abcdef')
exm.sync(imageid,
imageset_id=imageset,
product_id=product_id,
slideuid=slideuid,
database=DB)
found = False
for annoI in DB.annotations:
anno = DB.annotations[annoI]
if (anno.guid == newguid):
found = True
assert (anno.annotationType == AnnotationType.POLYGON)
assert (anno.text == 'abcdef')
assert (anno.labels[0].exact_id == created['annotations']['id'])
assert (found)
# also check in stored database
DB.loadIntoMemory(1)
for annoI in DB.annotations:
anno = DB.annotations[annoI]
if (anno.guid == newguid):
found = True
assert (anno.annotationType == AnnotationType.POLYGON)
assert (anno.labels[0].exact_id == created['annotations']['id'])
# Clean up --> remove all annotations
annos = exm.retrieve_annotations(imageid)
for anno in annos:
exm.delete_annotation(anno['id'], keep_deleted_element=False)
# All gone
assert (len(exm.retrieve_annotations(imageid)) == 0)
# Now delete image
exm.delete_image(imageid)
os.remove(imagename)
exm.terminate()
def calculate_F1_fromCSV(databasefile,
csv_directory,
hotclass=1,
verbose=False):
DB = Database()
DB = DB.open(databasefile)
import os
import csv
result_boxes = {}
for root, dirs, files in os.walk(csv_directory):
if len(dirs) > 0: continue
slidenr = int(root.split('/')[-1])
result_boxes['%02d_test.tif' % slidenr] = []
f = open(root + '/' + files[0], 'r')
for y, x in csv.reader(f, delimiter=','):
result_boxes['%02d_test.tif' % slidenr].append([int(x), int(y), 1])
sTP, sFN, sFP = 0, 0, 0
F1dict = dict()
sP = 0
print('Calculating F1 for test set of %d files' % len(result_boxes), ':',
result_boxes.keys())
mitcount = DB.execute(
f'SELECT COUNT(*) FROM Annotations where agreedClass={hotclass}'
).fetchall()
print('Official count of mitotic figures in DB: ', mitcount)
slideids = []
for resfile in result_boxes:
boxes = np.array(result_boxes[resfile])
TP, FP, FN, F1 = 0, 0, 0, 0
slide_id = DB.findSlideWithFilename(resfile, '')
slideids.append(str(slide_id))
DB.loadIntoMemory(slide_id)
annoList = []
for annoI in DB.annotations:
anno = DB.annotations[annoI]
if anno.agreedClass == hotclass:
annoList.append([anno.x1, anno.y1])
centers_DB = np.array(annoList)
if boxes.shape[0] > 0:
score = boxes[:, -1]
F1, TP, FP, FN = _F1_core(centers_DB, boxes, score, 0)
if (centers_DB.shape[0] != TP + FN):
print(resfile, centers_DB.shape[0], TP + FN)
else: # no detections --> missed all
FN = centers_DB.shape[0]
if (verbose):
print(f'{resfile}: F1:{F1}, TP:{TP}, FP:{FP}, FN:{FN}')
sTP += TP
sFP += FP
sP += centers_DB.shape[0]
sFN += FN
F1dict[resfile] = F1
print('Overall: ')
sF1 = 2 * sTP / (2 * sTP + sFP + sFN)
print('F1: ', sF1)
print('Precision: %.3f ' % (sTP / (sTP + sFP)))
print('Recall: %.3f' % (sTP / (sTP + sFN)))
return sF1, F1dict
def optimize_threshold(databasefile,
result_boxes=None,
resfile=None,
hotclass=2,
minthres=0.5):
DB = Database()
DB = DB.open(databasefile)
if (result_boxes is None):
if resfile is None:
raise ValueError(
'At least one of resfile/result_boxes must be given')
if (resfile[-3:] == 'bz2'):
f = bz2.BZ2File(resfile, 'rb')
else:
f = open(resfile, 'rb')
result_boxes = pickle.load(f)
sTP, sFN, sFP = 0, 0, 0
F1dict = dict()
MIN_THR = minthres
result_boxes = nms(result_boxes, MIN_THR)
TPd, FPd, FNd, F1d = dict(), dict(), dict(), dict()
thresholds = np.arange(MIN_THR, 0.99, 0.01)
print(
'Optimizing threshold for validation set of %d files: ' %
len(result_boxes.keys()), ','.join(list(result_boxes.keys())))
for resfile in result_boxes:
boxes = np.array(result_boxes[resfile])
TP, FP, FN = 0, 0, 0
TPd[resfile] = list()
FPd[resfile] = list()
FNd[resfile] = list()
F1d[resfile] = list()
if (boxes.shape[0] > 0):
score = boxes[:, -1]
DB.loadIntoMemory(DB.findSlideWithFilename(resfile, ''))
# perform NMS on detections
annoList = []
for annoI in DB.annotations:
anno = DB.annotations[annoI]
if anno.agreedClass == hotclass:
annoList.append([anno.x1, anno.y1])
centers_DB = np.array(annoList)
for det_thres in thresholds:
F1, TP, FP, FN = _F1_core(centers_DB, boxes, score, det_thres)
TPd[resfile] += [TP]
FPd[resfile] += [FP]
FNd[resfile] += [FN]
F1d[resfile] += [F1]
else:
for det_thres in thresholds:
TPd[resfile] += [0]
FPd[resfile] += [0]
FNd[resfile] += [0]
F1d[resfile] += [0]
F1 = 0
F1dict[resfile] = F1
allTP = np.zeros(len(thresholds))
allFP = np.zeros(len(thresholds))
allFN = np.zeros(len(thresholds))
allF1 = np.zeros(len(thresholds))
allF1M = np.zeros(len(thresholds))
for k in range(len(thresholds)):
allTP[k] = np.sum([TPd[x][k] for x in result_boxes])
allFP[k] = np.sum([FPd[x][k] for x in result_boxes])
allFN[k] = np.sum([FNd[x][k] for x in result_boxes])
allF1[k] = 2 * allTP[k] / (2 * allTP[k] + allFP[k] + allFN[k])
allF1M[k] = np.mean([F1d[x][k] for x in result_boxes])
print('Best threshold: F1=', np.max(allF1), 'Threshold=',
thresholds[np.argmax(allF1)])
return thresholds[np.argmax(allF1)], allF1, thresholds
def calculate_F1(databasefile,
result_boxes=None,
resfile=None,
det_thres=0.5,
hotclass=2,
verbose=False):
DB = Database()
DB = DB.open(databasefile)
if (result_boxes is None):
if resfile is None:
raise ValueError(
'At least one of resfile/result_boxes must be given')
if (resfile[-3:] == 'bz2'):
f = bz2.BZ2File(resfile, 'rb')
else:
f = open(resfile, 'rb')
result_boxes = pickle.load(f)
sTP, sFN, sFP = 0, 0, 0
F1dict = dict()
sP = 0
result_boxes = nms(result_boxes, det_thres)
print('Calculating F1 for test set of %d files' % len(result_boxes), ':',
result_boxes.keys())
mitcount = DB.execute(
f'SELECT COUNT(*) FROM Annotations where agreedClass={hotclass}'
).fetchall()
print('Official count of mitotic figures in DB: ', mitcount)
slideids = []
for resfile in result_boxes:
boxes = np.array(result_boxes[resfile])
TP, FP, FN, F1 = 0, 0, 0, 0
slide_id = DB.findSlideWithFilename(resfile, '')
slideids.append(str(slide_id))
DB.loadIntoMemory(slide_id)
annoList = []
for annoI in DB.annotations:
anno = DB.annotations[annoI]
if anno.agreedClass == hotclass:
annoList.append([anno.x1, anno.y1])
centers_DB = np.array(annoList)
if boxes.shape[0] > 0:
score = boxes[:, -1]
F1, TP, FP, FN = _F1_core(centers_DB, boxes, score, det_thres)
if (centers_DB.shape[0] != TP + FN):
print(resfile, centers_DB.shape[0], TP + FN)
else: # no detections --> missed all
FN = centers_DB.shape[0]
if (verbose):
print(f'{resfile}: F1:{F1}, TP:{TP}, FP:{FP}, FN:{FN}')
sTP += TP
sFP += FP
sP += centers_DB.shape[0]
sFN += FN
F1dict[resfile] = F1
print('Overall: ')
sF1 = 2 * sTP / (2 * sTP + sFP + sFN)
print('F1: ', sF1)
print('Precision: %.3f ' % (sTP / (sTP + sFP)))
print('Recall: %.3f' % (sTP / (sTP + sFN)))
return sF1, F1dict
from SlideRunner.dataAccess.database import Database
import SlideRunner.dataAccess.annotations as annotations
import openslide
import os
import numpy as np
import sys
if len(sys.argv) < 2:
print('syntax:', sys.argv[0], '<area in WSI>')
else:
hpf = int(sys.argv[1])
os.system('mkdir -p %dHPF' % hpf)
DB = Database()
DB.open('../databases/MITOS_WSI_CCMCT_ODAEL.sqlite')
DBRK = Database()
DBRK.open('databases/HighMCAreas.sqlite')
os.system(
'cp ../databases/MITOS_WSI_CCMCT_ODAEL.sqlite MITOS_WSI_CCMCT_ODAEL_%dHPF.sqlite'
% hpf)
DBnew = Database()
DBnew.open('MITOS_WSI_CCMCT_ODAEL_%dHPF.sqlite' % hpf)
DBnew.execute('ATTACH `../databases/MITOS_WSI_CCMCT_ODAEL.sqlite` as orig')
for uid, filename in DB.listOfSlides():
print(uid, filename)
