celldetective 1.3.2__py3-none-any.whl → 1.3.4__py3-none-any.whl

celldetective/measure.py

@@ -15,6 +15,7 @@ import subprocess
 from math import ceil
 
 from skimage.draw import disk as dsk
+from skimage.feature import blob_dog, blob_log
 
 from celldetective.utils import rename_intensity_column, create_patch_mask, remove_redundant_features, \
 	remove_trajectory_measurements, contour_of_instance_segmentation, extract_cols_from_query, step_function, interpolate_nan
@@ -325,12 +326,7 @@ def measure_features(img, label, features=['area', 'intensity_mean'], channels=N
 			for index, channel in enumerate(channels):
 				if channel == spot_detection['channel']:
 					ind = index
-					blobs = blob_detection(img[:, :, ind], label, diameter=spot_detection['diameter'],
-								   threshold=spot_detection['threshold'])
-					df_spots = pd.DataFrame.from_dict(blobs, orient='index',
-													  columns=['count', 'spot_mean_intensity']).reset_index()
-			# Rename columns
-			df_spots.columns = ['label', 'spot_count', 'spot_mean_intensity']
+					df_spots = blob_detection(img, label, diameter=spot_detection['diameter'],threshold=spot_detection['threshold'], channel_name=spot_detection['channel'], target_channel=ind)
 		
 		if normalisation_list:
 			for norm in normalisation_list:
@@ -362,47 +358,27 @@ def measure_features(img, label, features=['area', 'intensity_mean'], channels=N
 	props = regionprops_table(label, intensity_image=img, properties=feats, extra_properties=extra_props_list)
 	df_props = pd.DataFrame(props)
 	if spot_detection is not None:
-		df_props = df_props.merge(df_spots, how='outer', on='label')
-		df_props['spot_count'] = df_props['spot_count'].replace(np.nan, 0).infer_objects(copy=False)
-		df_props['spot_mean_intensity'] = df_props['spot_mean_intensity'].replace(np.nan, 0).infer_objects(copy=False)
-
-
-
-	# if spot_detection is not None:
-	#     for index, channel in enumerate(channels):
-	#         if channel == spot_detection['channel']:
-	#             ind = index
-	#     blobs = blob_detection(img[:, :, ind], label, diameter=spot_detection['diameter'],
-	#                            threshold=spot_detection['threshold'])
-	#     df_spots = pd.DataFrame.from_dict(blobs, orient='index', columns=['count', 'spot_mean_intensity']).reset_index()
-	#     # Rename columns
-	#     df_spots.columns = ['label', 'spot_count', 'spot_mean_intensity']
-	#     df_props = df_props.merge(df_spots, how='outer', on='label')
-	#     df_props['spot_count'] = df_props['spot_count'].replace(np.nan, 0)
-	#     df_props['spot_mean_intensity'] = df_props['spot_mean_intensity'].replace(np.nan, 0)
-
+		if df_spots is not None:
+			df_props = df_props.merge(df_spots, how='outer', on='label',suffixes=('_delme', ''))
+			df_props = df_props[[c for c in df_props.columns if not c.endswith('_delme')]]
 
 	if border_dist is not None:
 		# automatically drop all non intensity features
 		intensity_features_test = [('intensity' in s and 'centroid' not in s and 'peripheral' not in s) for s in
 								   features]
 		intensity_features = list(np.array(features)[np.array(intensity_features_test)])
-		# intensity_extra = [(s in extra_props_list)for s in intensity_features]
-		# print(intensity_extra)
 		intensity_extra = []
 		for s in intensity_features:
 			if s in extra_props:
 				intensity_extra.append(getattr(extra_properties, s))
 				intensity_features.remove(s)
-		# print(intensity_features)
-		# If no intensity feature was passed still measure mean intensity
+
 		if len(intensity_features) == 0:
 			if verbose:
 				print('No intensity feature was passed... Adding mean intensity for edge measurement...')
 			intensity_features = np.append(intensity_features, 'intensity_mean')
 		intensity_features = list(np.append(intensity_features, 'label'))
 
-		# Remove extra intensity properties from border measurements
 		new_intensity_features = intensity_features.copy()
 		for int_feat in intensity_features:
 			if int_feat in extra_props:
@@ -439,8 +415,10 @@ def measure_features(img, label, features=['area', 'intensity_mean'], channels=N
 	if haralick_options is not None:
 		try:
 			df_haralick = compute_haralick_features(img, label, channels=channels, **haralick_options)
-			df_props = df_props.merge(df_haralick, left_on='label',right_on='cell_id')
-			#df_props = df_props.drop(columns=['cell_label'])
+			if df_haralick is not None:
+				df_haralick = df_haralick.rename(columns={"cell_id": "label"})
+				df_props = df_props.merge(df_haralick, how='outer', on='label', suffixes=('_delme', ''))
+				df_props = df_props[[c for c in df_props.columns if not c.endswith('_delme')]]
 		except Exception as e:
 			print(e)
 			pass
@@ -541,6 +519,10 @@ def compute_haralick_features(img, labels, channels=None, target_channel=0, scal
 	if len(img.shape)==3:
 		img = img[:,:,target_channel]
 
+	# Routine to skip black frames
+	if np.percentile(img.flatten(),99.9)==0.0:
+		return None
+
 	img = interpolate_nan(img)
 
 	# Rescale image and mask
@@ -916,67 +898,125 @@ def normalise_by_cell(image, labels, distance=5, model='median', operation='subt
 	return normalised_frame
 
 
-def blob_detection(image, label, threshold, diameter):
-	"""
-	Perform blob detection on an image based on labeled regions.
+def extract_blobs_in_image(image, label, diameter, threshold=0., method="log"):
+	
+	if np.percentile(image.flatten(),99.9)==0.0:
+		return None
 
-	Parameters:
-	- image (numpy.ndarray): The input image data.
-	- label (numpy.ndarray): An array specifying labeled regions in the image.
-	- threshold (float): The threshold value for blob detection.
-	- diameter (float): The expected diameter of blobs.
+	dilated_image = ndimage.grey_dilation(label, footprint=disk(10))
 
-	Returns:
-	- dict: A dictionary containing information about detected blobs.
+	masked_image = image.copy()
+	masked_image[np.where((dilated_image == 0)|(image!=image))] = 0
+	min_sigma = (1 / (1 + math.sqrt(2))) * diameter
+	max_sigma = math.sqrt(2) * min_sigma
+	if method=="dog":
+		blobs = blob_dog(masked_image, threshold=threshold, min_sigma=min_sigma, max_sigma=max_sigma, overlap=0.75)
+	elif method=="log":
+		blobs = blob_log(masked_image, threshold=threshold, min_sigma=min_sigma, max_sigma=max_sigma, overlap=0.75)		
+	# Exclude spots outside of cell masks
+	mask = np.array([label[int(y), int(x)] != 0 for y, x, _ in blobs])
+	if np.any(mask):
+		blobs_filtered = blobs[mask]
+	else:
+		blobs_filtered=[]
 
-	This function performs blob detection on an image based on labeled regions. It iterates over each labeled region
-	and detects blobs within the region using the Difference of Gaussians (DoG) method. Detected blobs are filtered
-	based on the specified threshold and expected diameter. The function returns a dictionary containing the number of
-	detected blobs and their mean intensity for each labeled region.
+	return blobs_filtered
 
-	Example:
-	>>> image = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
-	>>> label = np.array([[0, 1, 1], [2, 2, 0], [3, 3, 0]])
-	>>> threshold = 0.1
-	>>> diameter = 5.0
-	>>> result = blob_detection(image, label, threshold, diameter)
-	>>> print(result)
-	{1: [1, 4.0], 2: [0, nan], 3: [0, nan]}
 
-	Note:
-	- Blobs are detected using the Difference of Gaussians (DoG) method.
-	- Detected blobs are filtered based on the specified threshold and expected diameter.
-	- The returned dictionary contains information about the number of detected blobs and their mean intensity
-	  for each labeled region.
-	"""
-	blob_labels = {}
-	dilated_image = ndimage.grey_dilation(label, footprint=disk(10))
-	for mask_index in np.unique(label):
-		if mask_index == 0:
-			continue
-		removed_background = image.copy()
-		one_mask = label.copy()
-		one_mask[np.where(label != mask_index)] = 0
-		dilated_copy = dilated_image.copy()
-		dilated_copy[np.where(dilated_image != mask_index)] = 0
-		removed_background[np.where(dilated_copy == 0)] = 0
-		min_sigma = (1 / (1 + math.sqrt(2))) * diameter
-		max_sigma = math.sqrt(2) * min_sigma
-		blobs = skimage.feature.blob_dog(removed_background, threshold=threshold, min_sigma=min_sigma,
-										 max_sigma=max_sigma)
-
-		mask = np.array([one_mask[int(y), int(x)] != 0 for y, x, r in blobs])
-		if not np.any(mask):
-			continue
-		blobs_filtered = blobs[mask]
-		binary_blobs = np.zeros_like(label)
-		for blob in blobs_filtered:
-			y, x, r = blob
-			rr, cc = dsk((y, x), r, shape=binary_blobs.shape)
-			binary_blobs[rr, cc] = 1
-		spot_intensity = regionprops_table(binary_blobs, removed_background, ['intensity_mean'])
-		blob_labels[mask_index] = [blobs_filtered.shape[0], spot_intensity['intensity_mean'][0]]
-	return blob_labels
+def blob_detection(image, label, diameter, threshold=0., channel_name=None, target_channel=0, method="log"):
+	
+	image = image[:, :, target_channel].copy()
+	if np.percentile(image.flatten(),99.9)==0.0:
+		return None
+
+	detections = []
+	blobs_filtered = extract_blobs_in_image(image, label, diameter, threshold=threshold)
+
+	for lbl in np.unique(label):
+		if lbl>0:
+			
+			blob_selection = np.array([label[int(y), int(x)] == lbl for y, x, _ in blobs_filtered])
+			if np.any(blob_selection):
+				# if any spot
+				blobs_in_cell = blobs_filtered[blob_selection]
+				n_spots = len(blobs_in_cell)
+				binary_blobs = np.zeros_like(label)
+				for blob in blobs_in_cell:
+					y, x, sig = blob
+					r = np.sqrt(2)*sig
+					rr, cc = dsk((y, x), r, shape=binary_blobs.shape)
+					binary_blobs[rr, cc] = 1    
+				intensity_mean = np.nanmean(image[binary_blobs==1].flatten())
+			else:
+				n_spots = 0
+				intensity_mean = np.nan
+			detections.append({'label': lbl, f'{channel_name}_spot_count': n_spots, f'{channel_name}_mean_spot_intensity': intensity_mean})
+	detections = pd.DataFrame(detections)
+
+	return detections
+
+
+# def blob_detectionv0(image, label, threshold, diameter):
+# 	"""
+# 	Perform blob detection on an image based on labeled regions.
+
+# 	Parameters:
+# 	- image (numpy.ndarray): The input image data.
+# 	- label (numpy.ndarray): An array specifying labeled regions in the image.
+# 	- threshold (float): The threshold value for blob detection.
+# 	- diameter (float): The expected diameter of blobs.
+
+# 	Returns:
+# 	- dict: A dictionary containing information about detected blobs.
+
+# 	This function performs blob detection on an image based on labeled regions. It iterates over each labeled region
+# 	and detects blobs within the region using the Difference of Gaussians (DoG) method. Detected blobs are filtered
+# 	based on the specified threshold and expected diameter. The function returns a dictionary containing the number of
+# 	detected blobs and their mean intensity for each labeled region.
+
+# 	Example:
+# 	>>> image = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
+# 	>>> label = np.array([[0, 1, 1], [2, 2, 0], [3, 3, 0]])
+# 	>>> threshold = 0.1
+# 	>>> diameter = 5.0
+# 	>>> result = blob_detection(image, label, threshold, diameter)
+# 	>>> print(result)
+# 	{1: [1, 4.0], 2: [0, nan], 3: [0, nan]}
+
+# 	Note:
+# 	- Blobs are detected using the Difference of Gaussians (DoG) method.
+# 	- Detected blobs are filtered based on the specified threshold and expected diameter.
+# 	- The returned dictionary contains information about the number of detected blobs and their mean intensity
+# 	  for each labeled region.
+# 	"""
+# 	blob_labels = {}
+# 	dilated_image = ndimage.grey_dilation(label, footprint=disk(10))
+# 	for mask_index in np.unique(label):
+# 		if mask_index == 0:
+# 			continue
+# 		removed_background = image.copy()
+# 		one_mask = label.copy()
+# 		one_mask[np.where(label != mask_index)] = 0
+# 		dilated_copy = dilated_image.copy()
+# 		dilated_copy[np.where(dilated_image != mask_index)] = 0
+# 		removed_background[np.where(dilated_copy == 0)] = 0
+# 		min_sigma = (1 / (1 + math.sqrt(2))) * diameter
+# 		max_sigma = math.sqrt(2) * min_sigma
+# 		blobs = blob_dog(removed_background, threshold=threshold, min_sigma=min_sigma,
+# 										 max_sigma=max_sigma)
+
+# 		mask = np.array([one_mask[int(y), int(x)] != 0 for y, x, r in blobs])
+# 		if not np.any(mask):
+# 			continue
+# 		blobs_filtered = blobs[mask]
+# 		binary_blobs = np.zeros_like(label)
+# 		for blob in blobs_filtered:
+# 			y, x, r = blob
+# 			rr, cc = dsk((y, x), r, shape=binary_blobs.shape)
+# 			binary_blobs[rr, cc] = 1
+# 		spot_intensity = regionprops_table(binary_blobs, removed_background, ['intensity_mean'])
+# 		blob_labels[mask_index] = [blobs_filtered.shape[0], spot_intensity['intensity_mean'][0]]
+# 	return blob_labels
 
 ### Classification ####
 

celldetective/models/segmentation_effectors/ricm_bf_all_last/config_input.json

@@ -0,0 +1,79 @@
+{
+    "channels": [
+        "adhesion_channel",
+        "brightfield_channel"
+    ],
+    "diameter": 30.0,
+    "cellprob_threshold": 0.0,
+    "flow_threshold": 0.4,
+    "normalization_percentile": [
+        false,
+        true
+    ],
+    "normalization_clip": [
+        true,
+        true
+    ],
+    "normalization_values": [
+        [
+            0.75,
+            1.25
+        ],
+        [
+            1.0,
+            99.0
+        ]
+    ],
+    "model_type": "cellpose",
+    "spatial_calibration": 0.2,
+    "dataset": {
+        "train": [
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_404_0066_roi_429_935_159_649.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_200_0003_roi_457_991_5_488.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_508_0008.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_305_0075.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_302_0063_roi_405_865_462_937.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_506_0066_roi_473_944_494_953.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_202_0027_roi_557_998_3_447.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_208_0027_roi_600_997_5_387.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_206_0023_roi_251_707_249_666.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_201_0017_roi_324_961_23_596.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_102_0053_roi_511_996_4_433.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_403_0009_roi_554_996_460_994.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_508_0066.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_507_0066_roi_492_998_9_474.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_202_0029_roi_177_746_4_533.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_203_0060_roi_369_906_119_648.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_304_0025.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_207_0030_roi_152_661_531_998.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_105_0018_roi_510_954_13_422.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_507_0016_roi_29_585_462_996.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_504_0066_roi_305_866_382_909.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_605_0060_roi_6_479_351_847.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_403_0008.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_203_0029_roi_3_376_622_1000.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_102_0094.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_202_0055_roi_1_514_68_597.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_206_0000.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_302_0023_roi_295_768_6_437.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_805_0081.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_605_0010_roi_341_847_162_673.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_205_0002_roi_70_569_6_490.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_200_0055_roi_99_778_341_986.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_802_0040.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_206_0028_roi_2_426_487_995.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_706_0042_roi_99_515_11_394.tif"
+        ],
+        "validation": [
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_201_0003_roi_501_957_576_1000.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-11-23-analysis-2024_603_0032.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_706_0030_roi_323_824_488_995.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_202_0014_roi_258_711_504_959.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_207_0007_roi_119_611_5_451.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_206_0030.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_207_0055_roi_519_989_6_429.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-03-03-analysis-2024_506_0053_roi_190_724_13_490.tif",
+            "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects/Marie-20-06-analysis-2024_300_0047_roi_416_985_436_972.tif"
+        ]
+    }
+}

celldetective/models/segmentation_effectors/ricm_bf_all_last/training_instructions.json

@@ -0,0 +1,37 @@
+{
+    "model_name": "ricm_bf_all_last",
+    "model_type": "cellpose",
+    "pretrained": null,
+    "spatial_calibration": 0.2,
+    "channel_option": [
+        "adhesion_channel",
+        "brightfield_channel"
+    ],
+    "normalization_percentile": [
+        false,
+        true
+    ],
+    "normalization_clip": [
+        true,
+        true
+    ],
+    "normalization_values": [
+        [
+            0.75,
+            1.25
+        ],
+        [
+            1.0,
+            99.0
+        ]
+    ],
+    "ds": [
+        "/home/limozin/Downloads/dataset-marie-all-objects(1)/dataset-marie-all-objects"
+    ],
+    "augmentation_factor": 3.0,
+    "validation_split": 0.2,
+    "learning_rate": 0.008,
+    "batch_size": 8,
+    "epochs": 3000,
+    "target_directory": "/home/limozin/Documents/GitHub/celldetective/celldetective/models/segmentation_effectors"
+}

celldetective/models/segmentation_effectors/test-transfer/config_input.json

@@ -0,0 +1,39 @@
+{
+    "channels": [
+        "brightfield_channel",
+        "None"
+    ],
+    "diameter": 30.0,
+    "cellprob_threshold": 0.0,
+    "flow_threshold": 0.4,
+    "normalization_percentile": [
+        true,
+        true
+    ],
+    "normalization_clip": [
+        true,
+        true
+    ],
+    "normalization_values": [
+        [
+            1.0,
+            99.0
+        ],
+        [
+            1.0,
+            99.0
+        ]
+    ],
+    "model_type": "cellpose",
+    "spatial_calibration": 0.36666666666666664,
+    "dataset": {
+        "train": [
+            "/home/torro/Documents/Experiments/Marie-03-03-analysis-2024/annotations_effectors/Marie-03-03-analysis-2024_206_0028_roi_2_426_487_995.tif",
+            "/home/torro/Documents/Experiments/Marie-03-03-analysis-2024/annotations_effectors/Marie-03-03-analysis-2024_203_0029_roi_3_376_622_1000.tif",
+            "/home/torro/Documents/Experiments/Marie-03-03-analysis-2024/annotations_effectors/Marie-03-03-analysis-2024_208_0027_roi_600_997_5_387.tif"
+        ],
+        "validation": [
+            "/home/torro/Documents/Experiments/Marie-03-03-analysis-2024/annotations_effectors/Marie-03-03-analysis-2024_206_0023_roi_251_707_249_666.tif"
+        ]
+    }
+}

celldetective/neighborhood.py

@@ -7,8 +7,6 @@ from celldetective.utils import contour_of_instance_segmentation, extract_identi
 from scipy.spatial.distance import cdist
 from celldetective.io import locate_labels, get_position_pickle, get_position_table
 
-import matplotlib.pyplot as plt
-
 abs_path = os.sep.join([os.path.split(os.path.dirname(os.path.realpath(__file__)))[0], 'celldetective'])
 
 

celldetective/scripts/measure_cells.py

@@ -5,7 +5,7 @@ Copright © 2022 Laboratoire Adhesion et Inflammation, Authored by Remy Torro.
 import argparse
 import os
 import json
-from celldetective.io import auto_load_number_of_frames, load_frames
+from celldetective.io import auto_load_number_of_frames, load_frames, fix_missing_labels, locate_labels
 from celldetective.utils import extract_experiment_channels, ConfigSectionMap, _get_img_num_per_channel, extract_experiment_channels
 from celldetective.utils import remove_redundant_features, remove_trajectory_measurements
 from celldetective.measure import drop_tonal_features, measure_features, measure_isotropic_intensity
@@ -16,7 +16,6 @@ import numpy as np
 import pandas as pd
 from natsort import natsorted
 from art import tprint
-from tifffile import imread
 import threading
 import datetime
 
@@ -165,6 +164,8 @@ else:
 	features += ['centroid']
 	do_iso_intensities = False
 
+# if 'centroid' not in features:
+# 	features += ['centroid']
 
 # if (features is not None) and (trajectories is not None):
 # 	features = remove_redundant_features(features, 
@@ -176,6 +177,12 @@ len_movie_auto = auto_load_number_of_frames(file)
 if len_movie_auto is not None:
 	len_movie = len_movie_auto
 
+if label_path is not None and file is not None:
+	test = len(label_path)==len_movie
+	if not test:
+		fix_missing_labels(pos, population=mode, prefix=movie_prefix)
+		label_path = natsorted(glob(os.sep.join([pos, label_folder, '*.tif'])))
+
 img_num_channels = _get_img_num_per_channel(channel_indices, len_movie, nbr_channels)
 
 
@@ -203,6 +210,8 @@ if trajectories is None:
 	if 'label' not in features:
 		features.append('label')
 
+if label_path is not None:
+	label_names = [os.path.split(lbl)[-1] for lbl in label_path]
 
 
 features_log=f'features: {features}'
@@ -228,7 +237,10 @@ def measure_index(indices):
 			img = load_frames(img_num_channels[:,t], file, scale=None, normalize_input=False)
 
 		if label_path is not None:
-			lbl = imread(label_path[t])
+			
+			lbl = locate_labels(pos, population=mode, frames=t)
+			if lbl is None:
+				continue
 
 		if trajectories is not None:
 
@@ -286,16 +298,16 @@ for th in threads:
 
 
 if len(timestep_dataframes)>0:
+	
 	df = pd.concat(timestep_dataframes)	
-	df.reset_index(inplace=True, drop=True)
 
-	if trajectories is None:
+	if trajectories is not None:
+		df = df.sort_values(by=[column_labels['track'],column_labels['time']])
+		df = df.dropna(subset=[column_labels['track']])
+	else:
 		df['ID'] = np.arange(len(df))
 
-	if column_labels['track'] in df.columns:
-		df = df.sort_values(by=[column_labels['track'], column_labels['time']])
-	else:
-		df = df.sort_values(by=column_labels['time'])
+	df = df.reset_index(drop=True)
 
 	df.to_csv(pos+os.sep.join(["output", "tables", table_name]), index=False)
 	print(f'Measurements successfully written in table {pos+os.sep.join(["output", "tables", table_name])}')