def get_id_list(slides_dir):
id_list = []
svs_file_list = filesystem.find_ext_files(slides_dir, "svs")
id_list.extend([os.path.basename(ele) for ele in svs_file_list])
SVS_file_list = filesystem.find_ext_files(slides_dir, "SVS")
id_list.extend([os.path.basename(ele) for ele in SVS_file_list])
id = [os.path.splitext(ele)[0] for ele in id_list]
return id
def get_slide_list(slides_dir):
slide_list = []
svs_file_list = filesystem.find_ext_files(slides_dir, "svs")
slide_list.extend(svs_file_list)
SVS_file_list = filesystem.find_ext_files(slides_dir, "SVS")
slide_list.extend(SVS_file_list)
return slide_list
def get_slide_filenames(slides_dir):
slide_list = []
svs_file_list = filesystem.find_ext_files(slides_dir, "svs")
slide_list.extend([os.path.basename(ele) for ele in svs_file_list])
SVS_file_list = filesystem.find_ext_files(slides_dir, "SVS")
slide_list.extend([os.path.basename(ele) for ele in SVS_file_list])
slide_filenames = [os.path.splitext(ele)[0] for ele in slide_list]
slide_filenames.sort()
return slide_filenames
def locate_tissue(slides_dir):
slide_list = []
svs_file_list = filesystem.find_ext_files(slides_dir, "svs")
slide_list.extend(svs_file_list)
SVS_file_list = filesystem.find_ext_files(slides_dir, "SVS")
slide_list.extend(SVS_file_list)
tissue_dir = os.path.join(os.path.dirname(slides_dir), "Visualization/TissueLoc")
filesystem.overwrite_dir(tissue_dir)
for ind, slide_path in enumerate(slide_list):
print("processing {}/{}".format(ind+1, len(slide_list)))
# locate tissue contours with default parameters
cnts, d_factor = tl.locate_tissue_cnts(slide_path, max_img_size=2048, smooth_sigma=13,
thresh_val=0.88, min_tissue_size=120000)
cnts = sorted(cnts, key=lambda x: cv2.contourArea(x), reverse=True)
# if len(cnts) != 1:
# print("There are {} contours in {}".format(len(cnts), os.path.basename(slide_path)))
# load slide
select_level, select_factor = tl.select_slide_level(slide_path, max_size=2048)
wsi_head = pyramid.load_wsi_head(slide_path)
slide_img = wsi_head.read_region((0, 0), select_level, wsi_head.level_dimensions[select_level])
slide_img = np.asarray(slide_img)[:,:,:3]
slide_img = np.ascontiguousarray(slide_img, dtype=np.uint8)
# change not valid poly to convex_hull
cnt_arr = cv_cnt_to_np_arr(cnts[0])
cnt_poly = np_arr_to_poly(cnt_arr)
if cnt_poly.is_valid == True:
valid_cnt = cnts[0].astype(int)
else:
valid_arr = poly_to_np_arr(cnt_poly.convex_hull)
valid_cnt = np_arr_to_cv_cnt(valid_arr).astype(int)
cv2.drawContours(slide_img, [valid_cnt], 0, (0, 255, 0), 8)
# overlay and save
# cv2.drawContours(slide_img, cnts, 0, (0, 255, 0), 8)
tissue_save_name = os.path.splitext(os.path.basename(slide_path))[0] + ".png"
tissue_save_path = os.path.join(tissue_dir, tissue_save_name)
io.imsave(tissue_save_path, slide_img)
def test_find_ext_files():
input_dir = os.path.join(DATA_DIR, 'input')
ext = '.png'
filelist = find_ext_files(input_dir, ext)
if len(filelist) == 0:
print("No file with given extension")
else:
print("There are {} files end with {}".format(len(filelist), ext))
for ind, cur_file in enumerate(filelist):
print("{}: {}".format(ind + 1, cur_file))
def predit_all_feas(model, args):
slide_path = os.path.join(args.slide_dir, args.dset)
slide_list = filesystem.find_ext_files(slide_path, "tiff")
print("There are {} slides in totoal.".format(len(slide_list)))
slide_list.sort()
fea_dir = os.path.join(args.fea_dir, args.model_type, args.dset)
print("Start processing...")
print("="*80)
slide_start = time.time()
for ind, slide_path in enumerate(slide_list):
slide_filename = os.path.splitext(os.path.basename(slide_path))[0]
slide_head = openslide.OpenSlide(slide_path)
print("Processing {}, width: {}, height: {}, {}/{}".format(
slide_filename, slide_head.dimensions[0], slide_head.dimensions[1], ind+1, len(slide_list)))
predict_slide_fea(slide_path, model, fea_dir, args)
print("="*80)
slide_elapsed = time.time() - slide_start
print("Time cost: " + time.strftime("%H:%M:%S", time.gmtime(slide_elapsed)))
print("Finish Prediction...")
# -*- coding: utf-8 -*-
import os, sys
from pydaily import filesystem
from skimage.external.tifffile import imsave
sys.path.insert(0, '.')
from kfb_io.io_image import patch_read_slide
if __name__ == "__main__":
input_root = str(sys.argv[1]) # kfb folder
save_root = str(sys.argv[2]) # tif folder
if not os.path.exists(save_root):
os.makedirs(save_root)
kfb_files = filesystem.find_ext_files(input_root, "kfb")
for ind, this_kfb_path in enumerate(kfb_files):
print("Processing {}/{}".format(ind+1, len(kfb_files)))
img_name = os.path.basename(this_kfb_path)
img_name_noext = os.path.splitext(img_name)[0]
this_raw_data = patch_read_slide(this_kfb_path, level=1)
save_path = os.path.join(save_root, img_name_noext+'.tif')
imsave(save_path, this_raw_data, compress=9, bigtiff=True)
# -*- coding: utf-8 -*-
import os, sys
import deepdish as dd
import argparse
from pydaily import filesystem
def set_args():
parser = argparse.ArgumentParser(description="check fea generation")
parser.add_argument('--fea_dir',
type=str,
default="../data/CV04/Feas/vgg16bn")
parser.add_argument('--dset', type=str, default="train")
args = parser.parse_args()
return args
if __name__ == "__main__":
args = set_args()
feas_dir = os.path.join(args.fea_dir, args.dset)
h5_list = filesystem.find_ext_files(feas_dir, ".h5")
for ele in h5_list:
cur_fea_dict = dd.io.load(ele)
num_patch = len(cur_fea_dict['probs'])
if num_patch <= 128:
print("Regions in {} is {}".format(ele, num_patch))