def get_coordinate(point_path_lst):
lst = []
for item in point_path_lst:
basename = os.path.basename(item['path'])
point = get_location_from_filename(basename)
if not point:
print(basename)
exit()
_, x, y, w, h, _ = point
lst.append((x, y, w, h))
return lst
def get_cell_image(path, ctype, parent_pathes):
"""
获取细胞文件路径
:param path: 细胞图像路径
:param ctype: 标注类别 MANUAL or AUTO
:param parent_pathes: 大图名称及对应路径字典
:return:
"""
# 检查本地有无细胞图像文件路径信息文件
# 如果存在，则直接读取
# 如果没有，通过 FileScanner 工具类获取并写入本地文件
# image_path_info_dict_path = ctype + '_IMAGES_PATH_DICT.txt'
# check_name = os.path.join(METADATA_FILE_PATH, image_path_info_dict_path)
# if os.path.exists(check_name):
# with open(os.path.join(METADATA_FILE_PATH, image_path_info_dict_path)) as f:
# files = [item.replace('\n', '') for item in f.readlines()]
# else:
files = FilesScanner(path, ['.bmp', '.jpg']).get_files()
# with open(os.path.join(METADATA_FILE_PATH, image_path_info_dict_path), 'w') as o:
# o.writelines([item + '\n' for item in files])
# 根据细胞图像文件名生成细胞坐标信息
cells_dict = {}
# # 1-p0.6042_BD1607254-子宫内膜C_2018-10-09 16_42_03_x23043_y40485_w162_h218_2x.jpg
pattern00 = re.compile(
r'1-p\d\.\d+_(.*?)_x(\d+)_y(\d+)_w(\d+)_h(\d+)(_\dx)?.(bmp|jpg)')
# 2018-03-22-11_26_58_x15789_y31806_w63_h61_s385.jpg
pattern01 = re.compile(
r'(.*?)_x(\d+)_y(\d+)_w(\d+)_h(\d+)(_s\d+)?.(bmp|jpg)')
for item in files:
if item.endswith('.bmp'):
# 细胞图文件名
basename = os.path.basename(item).replace(' ', '-')
parent = os.path.dirname(item)
# 细胞所属类别
clas_type = os.path.basename(parent)
if "_NEW" in clas_type or "_2" in clas_type or "_1" in clas_type:
clas_type = clas_type.split("_")[0]
parent = os.path.dirname(parent)
items = re.findall(pattern00, basename)
if not items:
items = re.findall(pattern01, basename)
if items:
parent_name, x, y, w, h, _ = items[0]
else:
raise Exception("%s IS NOT ACCEPTED!" % basename)
exit()
# parent_name = os.path.basename(parent).replace(' ', '-')
parent = os.path.dirname(parent)
# 大图所属类别
parent_type = os.path.basename(parent)
# 大图原始路径
try:
parent_path = parent_pathes[parent_name]
except Exception as e:
print("%s NOT FOUND" % parent_name)
print("CANNOT FIND RELATIVE TIFF PATH INFO, %s\n%s" %
(str(e), item))
exit()
# 解析坐标信息
point = get_location_from_filename(basename)
assert point, "THIS JPG NAME IS NOT ACCEPTED => %s" % basename
_, x, y, w, h, _ = point
x, y, w, h = int(x), int(y), int(w), int(h)
# 修正 AGC 细胞类别
if clas_type in AGC_CLASSES:
clas_type = 'AGC'
if parent_type in AGC_CLASSES:
parent_type = 'AGC'
# if parent_type not in PATHOLOGY_TYPE_CLASSES:
# raise Exception(item + " PARENT_TYPE NOT FOUND")
# 细胞位置及类别信息
info = {
'name': basename,
'cell_type': clas_type,
'cell_path': item,
'parent': parent_name,
'parent_full_name': os.path.basename(parent_path),
'parent_type': parent_type,
'x': x,
'y': y,
'w': w,
'h': h,
}
if parent_name in cells_dict:
cells_dict[parent_name].append(info)
else:
cells_dict[parent_name] = [info]
# 将解析细胞数据按归属大图名称写入文件
for key, lines in cells_dict.items():
# 生成输出路径
save_path = os.path.join(METADATA_FILE_PATH,
ctype + '_IMAGES_PATH_DICT')
os.makedirs(save_path, exist_ok=True)
with open(os.path.join(save_path, key + '.txt'), 'w') as f:
for line in lines:
f.write(json.dumps(line) + '\n')
return cells_dict
for item in manual_point_lst:
path = item['path']
cell_type = item['type']
cell_save_path = os.path.join(merge_dir_path, parent_type, key,
cell_type)
if not os.path.exists(cell_save_path):
os.makedirs(cell_save_path)
shutil.copy(path, cell_save_path)
# 检测算法识别细胞的坐标位置，进行重复性判断
manual_point_coordinate_lst = get_coordinate(manual_point_lst)
for point in auto_point_lst:
basename = os.path.basename(point['path'])
_, x, y, w, h, _ = get_location_from_filename(basename)
# 与审核图像存在重复
for item in manual_point_coordinate_lst:
if cal_IOU((x, y, w, h), item) > 0.8:
break
else:
path = point['path']
cell_type = point['type']
cell_save_path = os.path.join(merge_dir_path, parent_type,
key, cell_type + '_NEW')
if not os.path.exists(cell_save_path):
os.makedirs(cell_save_path)
# 该图像不存在对应审核图像，直接拷贝图像至目标文件夹
shutil.copy(path, cell_save_path)
def get_cell_image(path, ctype, parent_pathes):
"""
获取细胞文件路径
:param path: 细胞图像路径
:param ctype: 标注类别 MANUAL or AUTO
:param parent_pathes: 大图名称及对应路径字典
:return:
"""
# 检查本地有无细胞图像文件路径信息文件
# 如果存在，则直接读取
# 如果没有，通过 FileScanner 工具类获取并写入本地文件
image_path_info_dict_path = ctype + '_IMAGES_PATH_DICT.txt'
check_name = os.path.join(METADATA_FILE_PATH, image_path_info_dict_path)
if os.path.exists(check_name):
with open(os.path.join(METADATA_FILE_PATH,
image_path_info_dict_path)) as f:
files = [item.replace('\n', '') for item in f.readlines()]
else:
files = FilesScanner(path, ['.jpg']).get_files()
with open(os.path.join(METADATA_FILE_PATH, image_path_info_dict_path),
'w') as o:
o.writelines([item + '\n' for item in files])
# 根据细胞图像文件名生成细胞坐标信息
cells_dict = {}
for item in files:
if item.endswith('.jpg'):
# 细胞图文件名
basename = os.path.basename(item)
parent = os.path.dirname(item)
# 细胞所属类别
clas_type = os.path.basename(parent)
parent = os.path.dirname(parent)
# 细胞所属大图名称
parent_name = os.path.basename(parent)
parent = os.path.dirname(parent)
# 大图所属类别
parent_type = os.path.basename(parent)
# 大图原始路径
try:
parent_path = parent_pathes[parent_name]
except Exception as e:
print("CANNOT FIND RELATIVE TIFF PATH INFO, %s" % str(e))
exit()
# 解析坐标信息
point = get_location_from_filename(basename)
assert point, "THIS JPG NAME IS NOT ACCEPTED => %s" % basename
_, x, y, w, h, _ = point
# 修正 AGC 细胞类别
if clas_type in AGC_CLASSES:
clas_type = 'AGC'
# 解析与修正大图分类
if '_' in parent_type:
parent_type = parent_type.split('_')[-1]
if parent_type in AGC_CLASSES:
parent_type = 'AGC'
# 细胞位置及类别信息
info = {
'name': basename,
'cell_type': clas_type,
'cell_path': item,
'parent': parent_name,
'parent_full_name': os.path.basename(parent_path),
'parent_type': parent_type,
'x': x,
'y': y,
'w': w,
'h': h,
}
if parent_name in cells_dict:
cells_dict[parent_name].append(info)
else:
cells_dict[parent_name] = [info]
# 将解析细胞数据按归属大图名称写入文件
for key, lines in cells_dict.items():
# 生成输出路径
save_path = os.path.join(METADATA_FILE_PATH,
ctype + '_IMAGES_PATH_DICT')
os.makedirs(save_path, exist_ok=True)
with open(os.path.join(save_path, key + '.txt'), 'w') as f:
for line in lines:
f.write(json.dumps(line) + '\n')
return cells_dict