-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcreate_patches.py
324 lines (262 loc) · 11.6 KB
/
create_patches.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
# internal imports
from wsi_core.WholeSlideImage import WholeSlideImage
from wsi_core.wsi_utils import StitchCoords
from wsi_core.batch_process_utils import initialize_df
# other imports
import os
import numpy as np
import time
import argparse
import pdb
import pandas as pd
def stitching(file_path, wsi_object, downscale = 64):
start = time.time()
heatmap = StitchCoords(file_path, wsi_object, downscale=downscale, bg_color=(255,255,255), alpha=-1, draw_grid=True)
total_time = time.time() - start
return heatmap, total_time
def segment(WSI_object, seg_params, filter_params):
### Start Seg Timer
start_time = time.time()
# Segment
WSI_object.segmentTissue(**seg_params, filter_params=filter_params)
### Stop Seg Timers
seg_time_elapsed = time.time() - start_time
return WSI_object, seg_time_elapsed
def patching(WSI_object, **kwargs):
### Start Patch Timer
start_time = time.time()
# Patch
magnification = WSI_object.wsi.properties['aperio.AppMag']
kwargs['mag'] = str(magnification)
file_path = WSI_object.process_contours(**kwargs)
### Stop Patch Timer
patch_time_elapsed = time.time() - start_time
return file_path, patch_time_elapsed
def seg_and_patch(source, save_dir, patch_save_dir, mask_save_dir, only_mask_save_dir, stitch_save_dir,
slide_name_file,
patch_size = 256, step_size = 256,
seg_params = {'seg_level': -1, 'sthresh': 8, 'mthresh': 7, 'close': 4, 'use_otsu': False,
'keep_ids': 'none', 'exclude_ids': 'none'},
filter_params = {'a_t':100, 'a_h': 16, 'max_n_holes':8},
vis_params = {'vis_level': -1, 'line_thickness': 500},
patch_params = {'use_padding': True, 'contour_fn': 'four_pt'},
patch_level = 0,
use_default_params = False,
seg = False, save_mask = True,
stitch= False,
patch = False, auto_skip = True, process_list = None, uuid_name_file = None):
all_data = np.array(pd.read_excel(uuid_name_file, engine='openpyxl', header=None))
slides = []
id_names = {}
for data in all_data:
slides.append(data[1])
id_names[data[1]] = data[0]
slides = [slide for slide in slides if os.path.isfile(os.path.join(source, id_names[str(slide)], slide))]
if process_list is None:
df = initialize_df(slides, seg_params, filter_params, vis_params, patch_params)
else:
df = pd.read_csv(process_list)
df = initialize_df(df, seg_params, filter_params, vis_params, patch_params)
mask = df['process'] == 1
process_stack = df[mask]
total = len(process_stack)
legacy_support = 'a' in df.keys()
if legacy_support:
print('detected legacy segmentation csv file, legacy support enabled')
df = df.assign(**{'a_t': np.full((len(df)), int(filter_params['a_t']), dtype=np.uint32),
'a_h': np.full((len(df)), int(filter_params['a_h']), dtype=np.uint32),
'max_n_holes': np.full((len(df)), int(filter_params['max_n_holes']), dtype=np.uint32),
'line_thickness': np.full((len(df)), int(vis_params['line_thickness']), dtype=np.uint32),
'contour_fn': np.full((len(df)), patch_params['contour_fn'])})
seg_times = 0.
patch_times = 0.
stitch_times = 0.
for i in range(total):
df.to_csv(os.path.join(save_dir, 'process_list_autogen.csv'), index=False)
idx = process_stack.index[i]
slide = process_stack.loc[idx, 'slide_id']
print("\n\nprogress: {:.2f}, {}/{}".format(i/total, i, total))
print('processing {}'.format(slide))
df.loc[idx, 'process'] = 0
slide_id, _ = os.path.splitext(slide)
if auto_skip and os.path.isfile(os.path.join(patch_save_dir, slide_id + '.h5')):
print('{} already exist in destination location, skipped'.format(slide_id))
print('{} already exist in destination location, skipped'.format(slide_id))
df.loc[idx, 'status'] = 'already_exist'
continue
# Inialize WSI
full_path = os.path.join(source, id_names[slide], slide)
WSI_object = WholeSlideImage(full_path)
if use_default_params:
current_vis_params = vis_params.copy()
current_filter_params = filter_params.copy()
current_seg_params = seg_params.copy()
current_patch_params = patch_params.copy()
else:
current_vis_params = {}
current_filter_params = {}
current_seg_params = {}
current_patch_params = {}
for key in vis_params.keys():
if legacy_support and key == 'vis_level':
df.loc[idx, key] = -1
current_vis_params.update({key: df.loc[idx, key]})
for key in filter_params.keys():
if legacy_support and key == 'a_t':
old_area = df.loc[idx, 'a']
seg_level = df.loc[idx, 'seg_level']
scale = WSI_object.level_downsamples[seg_level]
adjusted_area = int(old_area * (scale[0] * scale[1]) / (512 * 512))
current_filter_params.update({key: adjusted_area})
df.loc[idx, key] = adjusted_area
current_filter_params.update({key: df.loc[idx, key]})
for key in seg_params.keys():
if legacy_support and key == 'seg_level':
df.loc[idx, key] = -1
current_seg_params.update({key: df.loc[idx, key]})
for key in patch_params.keys():
current_patch_params.update({key: df.loc[idx, key]})
if current_vis_params['vis_level'] < 0:
if len(WSI_object.level_dim) == 1:
current_vis_params['vis_level'] = 0
else:
wsi = WSI_object.getOpenSlide()
best_level = wsi.get_best_level_for_downsample(64)
current_vis_params['vis_level'] = best_level
if current_seg_params['seg_level'] < 0:
if len(WSI_object.level_dim) == 1:
current_seg_params['seg_level'] = 0
else:
wsi = WSI_object.getOpenSlide()
best_level = wsi.get_best_level_for_downsample(64)
current_seg_params['seg_level'] = best_level
keep_ids = str(current_seg_params['keep_ids'])
if keep_ids != 'none' and len(keep_ids) > 0:
str_ids = current_seg_params['keep_ids']
current_seg_params['keep_ids'] = np.array(str_ids.split(',')).astype(int)
else:
current_seg_params['keep_ids'] = []
exclude_ids = str(current_seg_params['exclude_ids'])
if exclude_ids != 'none' and len(exclude_ids) > 0:
str_ids = current_seg_params['exclude_ids']
current_seg_params['exclude_ids'] = np.array(str_ids.split(',')).astype(int)
else:
current_seg_params['exclude_ids'] = []
w, h = WSI_object.level_dim[current_seg_params['seg_level']]
if w * h > 1e8:
print('level_dim {} x {} is likely too large for successful segmentation, aborting'.format(w, h))
df.loc[idx, 'status'] = 'failed_seg'
continue
df.loc[idx, 'vis_level'] = current_vis_params['vis_level']
df.loc[idx, 'seg_level'] = current_seg_params['seg_level']
seg_time_elapsed = -1
if seg:
WSI_object, seg_time_elapsed = segment(WSI_object, current_seg_params, current_filter_params)
if save_mask:
mask, only_mask = WSI_object.visWSI(**current_vis_params)
mask_path = os.path.join(mask_save_dir, slide_id +'.jpg')
mask.save(mask_path)
only_mask_path = os.path.join(only_mask_save_dir, slide_id +'.png')
only_mask.save(only_mask_path)
patch_time_elapsed = -1 # Default time
if patch:
current_patch_params.update({'patch_level': patch_level, 'patch_size': patch_size, 'step_size': step_size,
'save_path': patch_save_dir})
file_path, patch_time_elapsed = patching(WSI_object = WSI_object, **current_patch_params,)
stitch_time_elapsed = -1
if stitch:
file_path = os.path.join(patch_save_dir, slide_id +'.h5')
if os.path.isfile(file_path):
heatmap, stitch_time_elapsed = stitching(file_path, WSI_object, downscale=64)
stitch_path = os.path.join(stitch_save_dir, slide_id +'.jpg')
# print(stitch_path)
heatmap.save(stitch_path)
print("segmentation took {} seconds".format(seg_time_elapsed))
print("patching took {} seconds".format(patch_time_elapsed))
print("stitching took {} seconds".format(stitch_time_elapsed))
df.loc[idx, 'status'] = 'processed'
seg_times += seg_time_elapsed
patch_times += patch_time_elapsed
stitch_times += stitch_time_elapsed
seg_times /= total
patch_times /= total
stitch_times /= total
df.to_csv(os.path.join(save_dir, 'process_list_autogen.csv'), index=False)
print("average segmentation time in s per slide: {}".format(seg_times))
print("average patching time in s per slide: {}".format(patch_times))
print("average stiching time in s per slide: {}".format(stitch_times))
return seg_times, patch_times
parser = argparse.ArgumentParser(description='seg and patch')
parser.add_argument('--source', type = str,
help='path to folder containing raw wsi image files')
parser.add_argument('--step_size', type = int, default=256,
help='step_size')
parser.add_argument('--patch_size', type = int, default=256,
help='patch_size')
parser.add_argument('--patch', default=False, action='store_true')
parser.add_argument('--seg', default=False, action='store_true')
parser.add_argument('--stitch', default=False, action='store_true')
parser.add_argument('--no_auto_skip', default=False, action='store_false')
parser.add_argument('--save_dir', type = str,
help='directory to save processed data')
parser.add_argument('--preset', default=None, type=str,
help='predefined profile of default segmentation and filter parameters (.csv)')
parser.add_argument('--patch_level', type=int, default=0,
help='downsample level at which to patch')
parser.add_argument('--process_list', type = str, default=None,
help='name of list of images to process with parameters (.csv)')
parser.add_argument('--slide_name_file', type=str,
help='a file stored all slides name needed in this project')
parser.add_argument('--uuid_name_file', type=str,
help='a file stored all slides info')
if __name__ == '__main__':
args = parser.parse_args()
patch_save_dir = os.path.join(args.save_dir, 'patches_' + str(args.patch_size))
mask_save_dir = os.path.join(args.save_dir, 'masks')
stitch_save_dir = os.path.join(args.save_dir, 'graph_' + str(args.patch_size))
only_mask_save_dir = os.path.join(args.save_dir, 'only_masks')
if args.process_list:
process_list = os.path.join(args.save_dir, args.process_list)
else:
process_list = None
print('source: ', args.source)
print('patch_save_dir: ', patch_save_dir)
print('mask_save_dir: ', mask_save_dir)
print('stitch_save_dir: ', stitch_save_dir)
directories = {'source': args.source,
'save_dir': args.save_dir,
'patch_save_dir': patch_save_dir,
'mask_save_dir' : mask_save_dir,
'only_mask_save_dir' : only_mask_save_dir,
'stitch_save_dir': stitch_save_dir}
for key, val in directories.items():
print("{} : {}".format(key, val))
if key not in ['source']:
os.makedirs(val, exist_ok=True)
seg_params = {'seg_level': -1, 'sthresh': 8, 'mthresh': 7, 'close': 4, 'use_otsu': False,
'keep_ids': 'none', 'exclude_ids': 'none'}
filter_params = {'a_t':100, 'a_h': 16, 'max_n_holes':8}
vis_params = {'vis_level': -1, 'line_thickness': 250}
patch_params = {'use_padding': True, 'contour_fn': 'four_pt'}
if args.preset:
preset_df = pd.read_csv(os.path.join('presets', args.preset))
for key in seg_params.keys():
seg_params[key] = preset_df.loc[0, key]
for key in filter_params.keys():
filter_params[key] = preset_df.loc[0, key]
for key in vis_params.keys():
vis_params[key] = preset_df.loc[0, key]
for key in patch_params.keys():
patch_params[key] = preset_df.loc[0, key]
parameters = {'seg_params': seg_params,
'filter_params': filter_params,
'patch_params': patch_params,
'vis_params': vis_params}
print(parameters)
seg_times, patch_times = seg_and_patch(**directories, **parameters,
slide_name_file=args.slide_name_file,
patch_size = args.patch_size, step_size=args.step_size,
seg = args.seg, use_default_params=False, save_mask = True,
stitch= args.stitch,
patch_level=args.patch_level, patch = args.patch,
process_list = process_list, auto_skip=args.no_auto_skip, uuid_name_file=args.uuid_name_file)