celldetective 1.3.9.post3__py3-none-any.whl → 1.3.9.post5__py3-none-any.whl

celldetective/_version.py

@@ -1 +1 @@
-__version__ = "1.3.9.post3"
+__version__ = "1.3.9.post5"

celldetective/extra_properties.py

@@ -1,23 +1,45 @@
 """
-Copyright © 2022 Laboratoire Adhesion et Inflammation, Authored by Remy Torro, 
-Ksenija Dervanova.
-
-Add extra properties to measure using regionprops (measure_features). 
-The functions must take "regionmask" as the first argument, corresponding
-to the binary mask of each cell of interest generated by regionprops 
-and an optional "intensity_image" second argument, i.e. the associated 
-multichannel image crop. The measurement will be named after the function
-name. If a function function() has several outputs (e.g. due to a multichannel image),
-they will be labelled with an index as function-0, function-1... A routine 
-automatically replacements keywords "intensity-0", "intensity-1" and so on,
-with the actual name of the intensity channel (e.g. "intensity-0" -> 
-"brightfield_channel"). Due to this indexing behavior, avoid using digits 
-in the function names and prefer text instead: "intensity-99()" --> 
-"intensity-ninety-nine()".
-
-New functions appear automatically in the ConfigMeasurements widget of the
-GUI.
-
+Copyright © 2022 Laboratoire Adhesion et Inflammation  
+Authored by R. Torro, K. Dervanova, L. Limozin
+
+This module defines additional measurement functions for use with `regionprops` via `measure_features`.  
+
+Usage
+-----
+Each function must follow these conventions:
+
+- **First argument:** `regionmask` (numpy array)  
+  A binary mask of the cell of interest, as provided by `regionprops`.
+- **Optional second argument:** `intensity_image` (numpy array)  
+  An image crop/bounding box associated with the cell (single-channel at a time).  
+
+Unlike the default `regionprops` from `scikit-image`, the cell image is **not** masked with zeros outside its boundaries.  
+This allows thresholding techniques to be used in measurements.  
+
+Naming Conventions & Indexing
+------------------------------
+- The measurement name is derived from the function name.  
+- If a function returns multiple values (e.g., for multichannel images), outputs are labeled sequentially:  
+  `function-0`, `function-1`, etc.  
+- To rename these outputs, use `rename_intensity_column` from `celldetective.utils`.  
+- `"intensity"` in function names is automatically replaced with the actual channel name:  
+  - Example: `"intensity-0"` → `"brightfield_channel"`.  
+- **Avoid digits smaller than the number of channels in function names** to prevent indexing conflicts.  
+  Prefer text-based names instead:  
+
+  .. code-block:: python
+
+	  # Bad practice:
+	  def intensity2(regionmask, intensity_image):
+		  pass
+
+	  # Recommended:
+	  def intensity_two(regionmask, intensity_image):
+		  pass
+
+GUI Integration
+---------------
+New functions are **automatically** added to the list of available measurements in the graphical interface.  
 """
 
 import warnings
@@ -97,6 +119,45 @@ def fraction_of_area_detected_in_intensity(regionmask, intensity_image, target_c
 
 def area_detected_in_intensity(regionmask, intensity_image, target_channel='adhesion_channel'):
 
+	"""
+	Computes the detected area within the regionmask based on threshold-based segmentation.
+
+	The function applies a predefined filtering and thresholding pipeline to the intensity image (normalized adhesion channel)
+	to detect significant regions. The resulting segmented regions are restricted to the 
+	`regionmask`, ensuring that only the relevant area is measured.
+
+	Parameters
+	----------
+	regionmask : ndarray
+		A binary mask (2D array) where nonzero values define the region of interest.
+	intensity_image : ndarray
+		A 2D array of the same shape as `regionmask`, representing the intensity 
+		values associated with the region.
+	target_channel : str, optional
+		Name of the intensity channel used for measurement. Defaults to `'adhesion_channel'`.
+
+	Returns
+	-------
+	detected_area : float
+		The total area (number of pixels) detected based on intensity-based segmentation.
+
+	Notes
+	-----
+	- The segmentation is performed using `segment_frame_from_thresholds()` with predefined parameters:
+	  
+	  - Thresholding range: `[0.02, 1000]`
+	  - Filters applied in sequence:
+
+		- `"subtract"` with value `1` (subtract 1 from intensity values)
+		- `"abs"` (take absolute value of intensities)
+		- `"gauss"` with sigma `0.8` (apply Gauss filter with sigma `0.8`)
+
+	- The segmentation includes hole filling.
+	- The detected regions are converted to a binary mask (`lbl > 0`).
+	- Any pixels outside the `regionmask` are excluded from the measurement.
+
+	"""
+
 	instructions = {
 		"thresholds": [
 			0.02,
@@ -125,9 +186,46 @@ def area_detected_in_intensity(regionmask, intensity_image, target_channel='adhe
 	return float(np.sum(lbl))
 
 
-def area_dark_intensity(regionmask, intensity_image, target_channel='adhesion_channel', fill_holes=True): #, target_channel='adhesion_channel'
+def area_dark_intensity(regionmask, intensity_image, target_channel='adhesion_channel', fill_holes=True, threshold=0.95): #, target_channel='adhesion_channel'
 	
-	subregion = (intensity_image < 0.95)*regionmask # under one, under 0.8, under 0.6, whatever value!
+	"""
+	Computes the absolute area within the regionmask where the intensity is below a given threshold.
+
+	This function identifies pixels in the region where the intensity is lower than `threshold`. 
+	If `fill_holes` is `True`, small enclosed holes in the detected dark regions are filled before 
+	computing the total area.
+
+	Parameters
+	----------
+	regionmask : ndarray
+		A binary mask (2D array) where nonzero values define the region of interest.
+	intensity_image : ndarray
+		A 2D array of the same shape as `regionmask`, representing the intensity 
+		values associated with the region.
+	target_channel : str, optional
+		Name of the intensity channel used for measurement. Defaults to `'adhesion_channel'`.
+	fill_holes : bool, optional
+		If `True`, fills enclosed holes in the detected dark intensity regions before computing 
+		the area. Defaults to `True`.
+	threshold : float, optional
+		Intensity threshold below which a pixel is considered part of a dark region. 
+		Defaults to `0.95`.
+
+	Returns
+	-------
+	dark_area : float
+		The absolute area (number of pixels) where intensity values are below `threshold`, within the regionmask.
+
+	Notes
+	-----
+	- The default threshold for defining "dark" intensity regions is `0.95`, but it can be adjusted.
+	- If `fill_holes` is `True`, the function applies hole-filling to the detected dark regions
+	  using `skimage.measure.label` and `fill_label_holes()`.
+	- The `target_channel` parameter tells regionprops to only measure this channel.
+
+	"""
+
+	subregion = (intensity_image < threshold)*regionmask # under one, under 0.8, under 0.6, whatever value!
 	if fill_holes:
 		subregion = skm.label(subregion, connectivity=2, background=0)
 		subregion = fill_label_holes(subregion)
@@ -136,9 +234,9 @@ def area_dark_intensity(regionmask, intensity_image, target_channel='adhesion_ch
 	return float(np.sum(subregion))
 
 
-def fraction_of_area_dark_intensity(regionmask, intensity_image, target_channel='adhesion_channel', fill_holes=True): #, target_channel='adhesion_channel'
+def fraction_of_area_dark_intensity(regionmask, intensity_image, target_channel='adhesion_channel', fill_holes=True, threshold=0.95): #, target_channel='adhesion_channel'
 	
-	subregion = (intensity_image < 0.95)*regionmask # under one, under 0.8, under 0.6, whatever value!
+	subregion = (intensity_image < threshold)*regionmask # under one, under 0.8, under 0.6, whatever value!
 	if fill_holes:
 		subregion = skm.label(subregion, connectivity=2, background=0)
 		subregion = fill_label_holes(subregion)
@@ -181,7 +279,39 @@ def intensity_nanmean(regionmask, intensity_image):
 	else:
 		return np.nanmean(intensity_image[regionmask])
 
-def intensity_centre_of_mass_displacement(regionmask, intensity_image):
+def intensity_center_of_mass_displacement(regionmask, intensity_image):
+
+	"""
+	Computes the displacement between the geometric centroid and the 
+	intensity-weighted center of mass of a region.
+
+	Parameters
+	----------
+	regionmask : ndarray
+		A binary mask (2D array) where nonzero values indicate the region of interest.
+	intensity_image : ndarray
+		A 2D array of the same shape as `regionmask`, representing the intensity 
+		values associated with the region.
+
+	Returns
+	-------
+	distance : float
+		Euclidean distance between the geometric centroid and the intensity-weighted center of mass.
+	direction_arctan : float
+		Angle (in degrees) of displacement from the geometric centroid to the intensity-weighted center of mass,
+		computed using `arctan2(delta_y, delta_x)`.
+	delta_x : float
+		Difference in x-coordinates (intensity-weighted centroid - geometric centroid).
+	delta_y : float
+		Difference in y-coordinates (intensity-weighted centroid - geometric centroid).
+
+	Notes
+	-----
+	- If the `intensity_image` contains NaN values, it is first processed using `interpolate_nan()`.
+	- Negative intensity values are set to zero to prevent misbehavior in center of mass calculation.
+	- If the intensity image is entirely zero, all outputs are `NaN`.
+
+	"""
 
 	if np.any(intensity_image!=intensity_image):
 		intensity_image = interpolate_nan(intensity_image.copy())
@@ -211,7 +341,7 @@ def intensity_centre_of_mass_displacement(regionmask, intensity_image):
 		return np.nan, np.nan, np.nan, np.nan
 
 
-def intensity_centre_of_mass_displacement_edge(regionmask, intensity_image):
+def intensity_center_of_mass_displacement_edge(regionmask, intensity_image):
 
 	if np.any(intensity_image!=intensity_image):
 		intensity_image = interpolate_nan(intensity_image.copy())
@@ -247,7 +377,41 @@ def intensity_centre_of_mass_displacement_edge(regionmask, intensity_image):
 def intensity_radial_gradient(regionmask, intensity_image):
 
 	"""
-	Determine if intensities are following a linear gradient from center to edge of the cell.
+	Determines whether the intensity follows a radial gradient from the center to the edge of the cell.
+
+	The function fits a linear model to the intensity values as a function of distance from the center
+	(computed via the Euclidean distance transform). The slope of the fitted line indicates whether 
+	the intensity is higher at the center or at the edges.
+
+	Parameters
+	----------
+	regionmask : ndarray
+		A binary mask (2D array) where nonzero values define the region of interest.
+	intensity_image : ndarray
+		A 2D array of the same shape as `regionmask`, representing the intensity 
+		values associated with the region.
+
+	Returns
+	-------
+	slope : float
+		Slope of the fitted linear model.  
+
+		- If `slope > 0`: Intensity increases towards the edge.  
+		- If `slope < 0`: Intensity is higher at the center.  
+
+	intercept : float
+		Intercept of the fitted linear model.
+	r2 : float
+		Coefficient of determination (R²), indicating how well the linear model fits the intensity profile.
+
+	Notes
+	-----
+	- If the `intensity_image` contains NaN values, they are interpolated using `interpolate_nan()`.
+	- The Euclidean distance transform (`distance_transform_edt`) is used to compute the distance 
+	  of each pixel from the edge.
+	- The x-values for the linear fit are reversed so that the origin is at the center.
+	- A warning suppression is applied to ignore messages about poorly conditioned polynomial fits.
+
 	"""
 	
 	if np.any(intensity_image!=intensity_image):

celldetective/gui/classifier_widget.py

@@ -482,8 +482,12 @@ class ClassifierWidget(QWidget, Styles):
 
 		if 'custom' in list(self.df.columns):
 			self.df = self.df.drop(['custom'],axis=1)
-
+		
+		self.fig_props.set_size_inches(4,3)
+		self.fig_props.suptitle(self.property_query_le.text(), fontsize=10)
+		self.fig_props.tight_layout()
 		for pos,pos_group in self.df.groupby('position'):
+			self.fig_props.savefig(pos+os.sep.join(['output',f'{self.class_name}.png']), bbox_inches='tight', dpi=300)
 			pos_group.to_csv(pos+os.sep.join(['output', 'tables', f'trajectories_{self.mode}.csv']), index=False)
 
 		self.parent_window.parent_window.update_position_options()

celldetective/gui/plot_signals_ui.py

@@ -297,9 +297,12 @@ class ConfigSignalPlot(QWidget, Styles):
 			self.compute_signal_functions()
 			if self.open_widget:
 				self.interpret_pos_location()
-				self.plot_window = GenericSignalPlotWidget(parent_window=self, df=self.df, df_pos_info = self.df_pos_info, df_well_info = self.df_well_info, feature_selected=self.feature_selected, title='plot signals')
-				self.plot_window.show()
-
+				try:
+					self.plot_window = GenericSignalPlotWidget(parent_window=self, df=self.df, df_pos_info = self.df_pos_info, df_well_info = self.df_well_info, feature_selected=self.feature_selected, title='plot signals')
+					self.plot_window.show()
+				except Exception as e:
+					print(f"{e=}")
+		
 	def process_signal(self):
 
 		self.FrameToMin = float(self.time_calibration_le.text().replace(',','.'))

celldetective/gui/signal_annotator.py

@@ -807,8 +807,6 @@ class SignalAnnotator(QMainWindow, Styles):
 			cols_to_remove += time_cols
 			#cols_to_remove.extend(self.df_tracks.select_dtypes(include=['object']).columns)
 
-			print(f"{cols_to_remove=}")
-
 			for tr in cols_to_remove:
 				try:
 					self.columns_to_rescale.remove(tr)
@@ -856,6 +854,16 @@ class SignalAnnotator(QMainWindow, Styles):
 					 'class', 't0', 'POSITION_X', 'POSITION_Y', 'position', 'well', 'well_index', 'well_name',
 					 'pos_name', 'index','class_color','status_color']
 
+		meta = get_experiment_metadata(self.exp_dir)
+		if meta is not None:
+			keys = list(meta.keys())
+			to_remove.extend(keys)
+
+		labels = get_experiment_labels(self.exp_dir)
+		if labels is not None:
+			keys = list(labels.keys())
+			to_remove.extend(labels)
+
 		for c in to_remove:
 			if c in signals:
 				signals.remove(c)

celldetective/io.py

@@ -1941,10 +1941,10 @@ def relabel_segmentation(labels, df, exclude_nans=True, column_labels={'track':
 
 	def rewrite_labels(indices):
 
-		all_track_ids = df[column_labels['track']].unique()
+		all_track_ids = df[column_labels['track']].dropna().unique()
 		
 		for t in tqdm(indices):
-
+			
 			f = int(t)
 			cells = df.loc[df[column_labels['frame']] == f, [column_labels['track'], column_labels['label']]].to_numpy()
 			tracks_at_t = list(cells[:,0])
@@ -1974,15 +1974,23 @@ def relabel_segmentation(labels, df, exclude_nans=True, column_labels={'track':
 				
 				loc_i, loc_j = np.where(labels[f] == identities[k])
 				track_id = tracks_at_t[k]
-				new_labels[f, loc_i, loc_j] = round(track_id)
+
+				if track_id==track_id:
+					new_labels[f, loc_i, loc_j] = round(track_id)
 
 	# Multithreading
-	indices = list(df[column_labels['frame']].unique())
+	indices = list(df[column_labels['frame']].dropna().unique())
 	chunks = np.array_split(indices, n_threads)
 
-	with concurrent.futures.ThreadPoolExecutor() as executor:
-		executor.map(rewrite_labels, chunks)
-	
+	with concurrent.futures.ThreadPoolExecutor(max_workers=threads) as executor:
+		
+		results = executor.map(rewrite_labels, chunks) #list(map(lambda x: executor.submit(self.parallel_job, x), chunks))
+		try:
+			for i,return_value in enumerate(results):
+				print(f"Thread {i} output check: ",return_value)
+		except Exception as e:
+			print("Exception: ", e)
+
 	print("\nDone.")
 
 	return new_labels
@@ -2088,6 +2096,7 @@ def tracks_to_btrack(df, exclude_nans=False):
 	graph = {}
 	if exclude_nans:
 		df.dropna(subset='class_id',inplace=True)
+		df.dropna(subset='TRACK_ID',inplace=True)
 
 	df["z"] = 0.
 	data = df[["TRACK_ID","FRAME","z","POSITION_Y","POSITION_X"]].to_numpy()

celldetective/regionprops/_regionprops.py

@@ -108,10 +108,17 @@ class CustomRegionProps(RegionProperties):
 								
 								idx = self.channel_names.index(default_channel)
 								res = func(self.image, self.image_intensity[..., idx])
-								len_output = len(res)
+								if isinstance(res, tuple):
+									len_output = len(res)
+								else:
+									len_output = 1
 
-								multichannel_list = [[np.nan]*len_output for c in range(len(self.channel_names))]
-								multichannel_list[idx] = res
+								if len_output > 1:
+									multichannel_list = [[np.nan]*len_output for c in range(len(self.channel_names))]
+									multichannel_list[idx] = res
+								else:
+									multichannel_list = [np.nan for c in range(len(self.channel_names))]
+									multichannel_list[idx] = res
 
 							else:
 								print(f'Warning... Channel required by custom measurement ({default_channel}) could not be found in your data...')

celldetective/utils.py

@@ -1264,7 +1264,6 @@ def rename_intensity_column(df, channels):
 			if s.isdigit():
 				if int(s)<len(channel_names):
 					test_digit[j] = True
-		print(f"{test_digit=}")
 			
 		if np.any(test_digit):
 			index = int(sections[np.where(test_digit)[0]][-1])
@@ -1289,36 +1288,36 @@ def rename_intensity_column(df, channels):
 				new_name = np.delete(measure, -1)
 				new_name = '_'.join(list(new_name))
 				if 'edge' in intensity_cols[k]:
-					new_name = new_name.replace('centre_of_mass_displacement', "edge_centre_of_mass_displacement_in_px")
+					new_name = new_name.replace('center_of_mass_displacement', "edge_center_of_mass_displacement_in_px")
 				else:
-					new_name = new_name.replace('centre_of_mass', "centre_of_mass_displacement_in_px")
+					new_name = new_name.replace('center_of_mass', "center_of_mass_displacement_in_px")
 				to_rename.update({intensity_cols[k]: new_name.replace('-', '_')})
 			
 			elif sections[-2] == "1":
 				new_name = np.delete(measure, -1)
 				new_name = '_'.join(list(new_name))
 				if 'edge' in intensity_cols[k]:
-					new_name = new_name.replace('centre_of_mass_displacement', "edge_centre_of_mass_orientation")
+					new_name = new_name.replace('center_of_mass_displacement', "edge_center_of_mass_orientation")
 				else:
-					new_name = new_name.replace('centre_of_mass', "centre_of_mass_orientation")
+					new_name = new_name.replace('center_of_mass', "center_of_mass_orientation")
 				to_rename.update({intensity_cols[k]: new_name.replace('-', '_')})
 				
 			elif sections[-2] == "2":
 				new_name = np.delete(measure, -1)
 				new_name = '_'.join(list(new_name))
 				if 'edge' in intensity_cols[k]:
-					new_name = new_name.replace('centre_of_mass_displacement', "edge_centre_of_mass_x")
+					new_name = new_name.replace('center_of_mass_displacement', "edge_center_of_mass_x")
 				else:
-					new_name = new_name.replace('centre_of_mass', "centre_of_mass_x")
+					new_name = new_name.replace('center_of_mass', "center_of_mass_x")
 				to_rename.update({intensity_cols[k]: new_name.replace('-', '_')})
 			
 			elif sections[-2] == "3":
 				new_name = np.delete(measure, -1)
 				new_name = '_'.join(list(new_name))
 				if 'edge' in intensity_cols[k]:
-					new_name = new_name.replace('centre_of_mass_displacement', "edge_centre_of_mass_y")
+					new_name = new_name.replace('center_of_mass_displacement', "edge_center_of_mass_y")
 				else:
-					new_name = new_name.replace('centre_of_mass', "centre_of_mass_y")
+					new_name = new_name.replace('center_of_mass', "center_of_mass_y")
 				to_rename.update({intensity_cols[k]: new_name.replace('-', '_')})
 		
 		if 'radial_gradient' in intensity_cols[k]:

{celldetective-1.3.9.post3.dist-info → celldetective-1.3.9.post5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: celldetective
-Version: 1.3.9.post3
+Version: 1.3.9.post5
 Summary: description
 Home-page: http://github.com/remyeltorro/celldetective
 Author: Rémy Torro

{celldetective-1.3.9.post3.dist-info → celldetective-1.3.9.post5.dist-info}/RECORD

@@ -1,10 +1,10 @@
 celldetective/__init__.py,sha256=bi3SGTMo6s2qQBsJAaKy-a4xaGcTQVW8zsqaiX5XKeY,139
 celldetective/__main__.py,sha256=bxTlSvbKhqn3LW_azd2baDCnDsgb37PAP9DfuAJ1_5M,1844
-celldetective/_version.py,sha256=7LdGJtBuAQ99wkn-0aLzi5WGP1RCrguzXtOTqLyM6m8,28
+celldetective/_version.py,sha256=LI2Zi5wYb3f4Us7DLo9zDTT_AexVCZzSS1LVTRQbzKQ,28
 celldetective/events.py,sha256=UkjY_-THo6WviWWCLnDbma7jWOd_O9a60C4IOX2htG8,8254
-celldetective/extra_properties.py,sha256=nP_EX2yxJuZRP283uYzN8km-_uOfW94u0zD_K2bIub8,8689
+celldetective/extra_properties.py,sha256=N1cZZNAqhuZDxsw6EzATnze5fharxaMvzQ6IjuJfqS0,14866
 celldetective/filters.py,sha256=6pl2IGPK2FH8KPWbjzQEbT4C-ruqE1fQ8NQNN7Euvy8,4433
-celldetective/io.py,sha256=KDb1N7ccUAUXKE2NHo9TIC7A5u2A9wYieGteoa0ymN0,121754
+celldetective/io.py,sha256=TLnYok-AiCTUVKABew7Irf-FlV2ofg-RjN7EneptjMc,122104
 celldetective/measure.py,sha256=h1F08Vf7sy-20syMFZTUl1lHzE4h6cQvswJpwD9fcfE,58475
 celldetective/neighborhood.py,sha256=s-zVsfGnPlqs6HlDJCXRh21lLiPKbA_S1JC6uZvfG_0,56712
 celldetective/preprocessing.py,sha256=Wlt_PJua97CpMuWe_M65znUmz_yjYPqWIcs2ZK_RLgk,44109
@@ -12,7 +12,7 @@ celldetective/relative_measurements.py,sha256=-GWig0lC5UWAcJSPlo9Sp45khGj80fxuQf
 celldetective/segmentation.py,sha256=WApzoU1s3Ntvp0eIw_pRZXNwCA8LDKC9YoyR52tioz4,30943
 celldetective/signals.py,sha256=nMyyGUpla8D2sUYKY1zjbWsAueVPI_gUalY0KXfWteI,111595
 celldetective/tracking.py,sha256=VBJLd-1EeJarOVPBNEomhVBh9UYAMdSnH0tmUiUoTrY,40242
-celldetective/utils.py,sha256=0LENOCxNMuEmClLiyvo_jIO2as4i7a5bMk1NaXUhgVs,104430
+celldetective/utils.py,sha256=u9mvb4ajP4eE_usnkz9fBxkVOLrd2HfuPPE9FgAhTbc,104404
 celldetective/datasets/segmentation_annotations/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/datasets/signal_annotations/blank,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 celldetective/gui/InitWindow.py,sha256=TPKWYczhPHvPKWg654sXnE9xCEx6U-oWX0_OJgLTWbU,15044
@@ -20,7 +20,7 @@ celldetective/gui/__init__.py,sha256=2_r2xfOj4_2xj0yBkCTIfzlF94AHKm-j6Pvpd7DddQc
 celldetective/gui/about.py,sha256=FJZrj6C-p6uqp_3UaprKosuW-Sw9_HPNQAvFbis9Gdk,1749
 celldetective/gui/analyze_block.py,sha256=h0sp7Tk3hZFM8w0yTidwIjZX4WRI-lQF3JCFObrLCPo,2761
 celldetective/gui/btrack_options.py,sha256=F2wrhuaNSaBr6vNApI22XSjdI5Cl3q138qCYBk-FDu4,44684
-celldetective/gui/classifier_widget.py,sha256=73h13QFtvYEy_jLl2DfSy9P3ERIOjWJAPn5mllYMPGc,20224
+celldetective/gui/classifier_widget.py,sha256=81B9iDVSYsCp9O1noyLVOKiEZ6YhxWX4S-O0xB9U8-c,20476
 celldetective/gui/configure_new_exp.py,sha256=N4SdL-4Xo0XbTAkCtt1ywr74HmHc5eaPlHGv1XgxAX0,20772
 celldetective/gui/control_panel.py,sha256=jFpedm03x6_jKabeadsNiigKnlh7sXCkulwe4gMCJaM,22042
 celldetective/gui/generic_signal_plot.py,sha256=Gv4KhA5vhbgVSj5jteE42T0aNCoQZtmIAUkEsMi6JNA,36309
@@ -30,12 +30,12 @@ celldetective/gui/layouts.py,sha256=XsqiHR58DXsG5SSD5S8KOtUv4yw-y-s2_wZx_XsHeJs,
 celldetective/gui/measurement_options.py,sha256=sxtQPKSixVbrFcBC1XLLC4-h7ZHlgTLcPfVAW2RVV7w,40357
 celldetective/gui/neighborhood_options.py,sha256=FBNDvlzMPKp8s0Grxds90pCPHG1s27XrpMN0HV2gf0I,19839
 celldetective/gui/plot_measurements.py,sha256=n0pDUcYcsKlSMaUaBSVplGziuWp_7jKaeXdREs-MqyI,50848
-celldetective/gui/plot_signals_ui.py,sha256=7jCu-wLk_NDL4ThLZwhltODngre8iqPMUcEhJNNllo8,18189
+celldetective/gui/plot_signals_ui.py,sha256=ttm5ijtZV5wAvy8uOq45YfybvubVFHvDN1hSHC_Kkk8,18249
 celldetective/gui/process_block.py,sha256=rFmtrnYBohjNRqSTjxC86yDNnzcXE7w9eo9Vm0heh6A,71215
 celldetective/gui/retrain_segmentation_model_options.py,sha256=7iawDN4kwq56Z-dX9kQe9tLW8B3YMrIW_D85LMAAYwk,23906
 celldetective/gui/retrain_signal_model_options.py,sha256=GCa0WKKsgmH2CFDHAKxPGbHtCE19p1_bbcWNasyZw5o,22482
 celldetective/gui/seg_model_loader.py,sha256=b1BiHuAf_ZqroE4jSEVCo7ASQv-xyWMPWU799alpbNM,19727
-celldetective/gui/signal_annotator.py,sha256=lf15PWZoWx2S1qZtrMsbBeZKtwVEKTjwwyIIG-XHdQA,89541
+celldetective/gui/signal_annotator.py,sha256=xr3w8nLD8JeAp_7Y851OqUKGUKeF2xrpbz3mNs5HJp4,89765
 celldetective/gui/signal_annotator2.py,sha256=RhcMX32FH_zg8GgAofGIyda9H8euSFADau301qi1NU0,106342
 celldetective/gui/signal_annotator_options.py,sha256=Tq20tybpelHFUqFCSemqH9es2FqM8S3I6Fab-u0FK0A,11015
 celldetective/gui/styles.py,sha256=SZy_ACkA6QB_4ANyY1V0m1QF66C0SVGssOrwW1Qt1Aw,5076
@@ -99,7 +99,7 @@ celldetective/models/tracking_configs/no_z_motion.json,sha256=b4RWOJ0w6Y2e0vJYwK
 celldetective/models/tracking_configs/ricm.json,sha256=L-vmwCR1f89U-qnH2Ms0cBfPFR_dxIWoe2ccH8V-QBA,2727
 celldetective/models/tracking_configs/ricm2.json,sha256=DDjJ6ScYcDWvlsy7ujPID8v8H28vcNcMuZmNR8XmGxo,2718
 celldetective/regionprops/__init__.py,sha256=ohe9vC7j4lnpKnGXidVo1PVfoQfC8TqCuHTNo8rXmdg,44
-celldetective/regionprops/_regionprops.py,sha256=5pxet-E2Eg6bSs7n0xjknDPQr15G14nUAqPRfDffzz0,10042
+celldetective/regionprops/_regionprops.py,sha256=a68bAytxgy-WFUzrjWg-xViSE27ehN9PdKfyO-dxKxM,10275
 celldetective/regionprops/props.json,sha256=sCwACmbh0n-JAw9eve9yV85REukoMBJLsRjxCwTRMm8,2424
 celldetective/scripts/analyze_signals.py,sha256=YE05wZujl2hQFWkvqATBcCx-cAd_V3RxnvKoh0SB7To,2194
 celldetective/scripts/measure_cells.py,sha256=edZ9xlUsLg1TI_yudp7bd04B_oqdHk9Ee4mSDe8G86w,11769
@@ -121,9 +121,9 @@ tests/test_segmentation.py,sha256=k1b_zIZdlytEdJcHjAUQEO3gTBAHtv5WvrwQN2xD4kc,34
 tests/test_signals.py,sha256=No4cah6KxplhDcKXnU8RrA7eDla4hWw6ccf7xGnBokU,3599
 tests/test_tracking.py,sha256=8hebWSqEIuttD1ABn-6dKCT7EXKRR7-4RwyFWi1WPFo,8800
 tests/test_utils.py,sha256=NKRCAC1d89aBK5cWjTb7-pInYow901RrT-uBlIdz4KI,3692
-celldetective-1.3.9.post3.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-celldetective-1.3.9.post3.dist-info/METADATA,sha256=IH5Ea7-lEKV8k_kgSYxLmxN9mB_IcncHnRExw5HSN5w,10753
-celldetective-1.3.9.post3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-celldetective-1.3.9.post3.dist-info/entry_points.txt,sha256=2NU6_EOByvPxqBbCvjwxlVlvnQreqZ3BKRCVIKEv3dg,62
-celldetective-1.3.9.post3.dist-info/top_level.txt,sha256=6rsIKKfGMKgud7HPuATcpq6EhdXwcg_yknBVWn9x4C4,20
-celldetective-1.3.9.post3.dist-info/RECORD,,
+celldetective-1.3.9.post5.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+celldetective-1.3.9.post5.dist-info/METADATA,sha256=jn77YGkfor9ud4o0cvkEtDDwsKj4LnrMy6EDQj6aVWs,10753
+celldetective-1.3.9.post5.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+celldetective-1.3.9.post5.dist-info/entry_points.txt,sha256=2NU6_EOByvPxqBbCvjwxlVlvnQreqZ3BKRCVIKEv3dg,62
+celldetective-1.3.9.post5.dist-info/top_level.txt,sha256=6rsIKKfGMKgud7HPuATcpq6EhdXwcg_yknBVWn9x4C4,20
+celldetective-1.3.9.post5.dist-info/RECORD,,

{celldetective-1.3.9.post3.dist-info → celldetective-1.3.9.post5.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any