small-fish-gui 1.0.4__py3-none-any.whl → 1.2.0__py3-none-any.whl

small_fish_gui/README.md

@@ -1,19 +1,27 @@
 # Small Fish
 **Small Fish** is a python application for the analysis of smFish images. It provides a ready to use graphical interface to combine famous python packages for cell analysis without any need for coding.
 
-Cell segmentation is peformed using *cellpose* (published work) : https://github.com/MouseLand/cellpose
+Cell segmentation (**2D**) is peformed using *cellpose* (published work) : https://github.com/MouseLand/cellpose; compatible with your own cellpose models.
 
 Spot detection is performed via *big-fish* (published work) : https://github.com/fish-quant/big-fish
 
 Time stacks are not yet supported.
 
+## What can you do with small fish ?
+
+- Single molecule quantification (including a lot of spatial features)
+- Foci/Transcription site quantification
+- Nuclear signal quantification
+- Signal to noise analysis
+- multichannel colocalisation
+
 ## Installation
 
 It is higly recommanded to create a specific [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html) or [virtual](https://docs.python.org/3.6/library/venv.html) environnement to install small fish.
 
 ```bash
 conda create -n small_fish python=3.8
-activate small_fish
+conda activate small_fish
 ```
 Then download the small_fish package : 
 ```bash
@@ -35,6 +43,11 @@ Then launch Small fish :
 ```bash
 python -m small_fish_gui
 ```
+
+## Cellpose configuration
+
+If you want to train your own cellpose model or set-up your GPU you can follow the official cellpose documentation, just remember to **first activate your small_fish environnement**.
+
 ## Developpement
 
 Optional features to include in future versions : 

small_fish_gui/__init__.py

@@ -38,4 +38,4 @@ ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 """
-__version__ = "0.5.0"
+__version__ = "1.2.0"

small_fish_gui/__main__.py

@@ -1,12 +1,26 @@
-import sys
-import os
+import sys, subprocess
 import PySimpleGUI as sg
 
 def main():
     import small_fish_gui.pipeline.main
 
+def is_last_version() :
+    latest_version = str(subprocess.run([sys.executable, '-m', 'pip', 'install', '{}==random'.format('small_fish_gui')], capture_output=True, text=True))
+    latest_version = latest_version[latest_version.find('(from versions:')+15:]
+    latest_version = latest_version[:latest_version.find(')')]
+    latest_version = latest_version.replace(' ','').split(',')[-1]
+
+    current_version = str(subprocess.run([sys.executable, '-m', 'pip', 'show', '{}'.format('small_fish_gui')], capture_output=True, text=True))
+    current_version = current_version[current_version.find('Version:')+8:]
+    current_version = current_version[:current_version.find('\\n')].replace(' ','')
+
+    return current_version == latest_version
 
 if __name__ == "__main__":
+
+    if not is_last_version() :
+        print("A new version of Small Fish is available. To update close small fish and type :\npip install --upgrade small_fish_gui")
+
     try :
         sys.exit(main())
     except Exception as error :

small_fish_gui/gui/help_module.py

@@ -227,7 +227,7 @@ def _mapping_help() :
     This window present the shape of your image : example (1080,1080,4)
     1080x1080 are the xy dimension (pixel resolution); and 4 is the number of channel. Another example a 3D multichannel 
     stack could be (18,4,1080,1080)...
-    The machine understand the order of the information such as (1080,1080,4) positions are (0,1,2). /!\ It starts from zero! /!\
+    The machine understand the order of the information such as (1080,1080,4) positions are (0,1,2). It starts from zero!
     The mapping purpose is to link the position to the type of informations, in this case we want :
 
             x : 1

small_fish_gui/gui/layout.py

@@ -151,7 +151,7 @@ def radio_layout(values, header=None) :
         layout = add_header(header, layout=layout)
     return layout
 
-def _segmentation_layout(cytoplasm_model_preset= 'cyto2', nucleus_model_preset= 'nuclei', cytoplasm_channel_preset=0, nucleus_channel_preset=0, cyto_diameter_preset=30, nucleus_diameter_preset= 30, show_segmentation_preset= False, segment_only_nuclei_preset=False, saving_path_preset=os.getcwd(), filename_preset='cell_segmentation.png') :
+def _segmentation_layout(multichannel, cytoplasm_model_preset= 'cyto2', nucleus_model_preset= 'nuclei', cytoplasm_channel_preset=0, nucleus_channel_preset=0, cyto_diameter_preset=30, nucleus_diameter_preset= 30, show_segmentation_preset= False, segment_only_nuclei_preset=False, saving_path_preset=os.getcwd(), filename_preset='cell_segmentation.png',) :
     
     USE_GPU = use_gpu()
 
@@ -165,14 +165,14 @@ def _segmentation_layout(cytoplasm_model_preset= 'cyto2', nucleus_model_preset=
     layout += [add_header("Cell Segmentation", [sg.Text("Choose cellpose model for cytoplasm: \n")]),
               [combo_layout(models_list, key='cyto_model_name', default_value= cytoplasm_model_preset)]
                         ]
-    layout += [parameters_layout(['cytoplasm channel'],default_values= [cytoplasm_channel_preset])]
+    if multichannel : layout += [parameters_layout(['cytoplasm channel'],default_values= [cytoplasm_channel_preset])]
     layout += [parameters_layout(['cytoplasm diameter'], unit= "px", default_values= [cyto_diameter_preset])]
     #Nucleus parameters
     layout += [
             add_header("Nucleus segmentation",[sg.Text("Choose cellpose model for nucleus: \n")]),
               combo_layout(models_list, key='nucleus_model_name', default_value= nucleus_model_preset)
                 ]
-    layout += [parameters_layout(['nucleus channel'], default_values= [nucleus_channel_preset])]
+    if multichannel : layout += [parameters_layout(['nucleus channel'], default_values= [nucleus_channel_preset])]
     layout += [parameters_layout([ 'nucleus diameter'],unit= "px", default_values= [nucleus_diameter_preset])]
     layout += [bool_layout(["Segment only nuclei"], preset=segment_only_nuclei_preset)]
     

small_fish_gui/gui/prompts.py

@@ -1,6 +1,7 @@
 import PySimpleGUI as sg
 import pandas as pd
 import os
+import numpy as np
 from .layout import path_layout, parameters_layout, bool_layout, tuple_layout, combo_layout, add_header
 from ..interface import open_image, check_format, FormatError
 from .help_module import ask_help
@@ -266,6 +267,7 @@ def _warning_popup(warning:str) :
 def _sumup_df(results: pd.DataFrame) :
 
     if len(results) > 0 :
+        if 'channel to compute' not in results : results['channel to compute'] = np.NaN
         res = results.loc[:,['acquisition_id', 'spot_number', 'cell_number', 'filename', 'channel to compute']]
     else :
         res = pd.DataFrame(columns= ['acquisition_id', 'spot_number', 'cell_number', 'filename', 'channel to compute'])
@@ -284,9 +286,9 @@ def hub_prompt(fov_results, do_segmentation=False) :
     layout = [
         [sg.Text('RESULTS', font= 'bold 13')],
         [sg.Table(values= list(sumup_df.values), headings= list(sumup_df.columns), row_height=20, num_rows= 5, vertical_scroll_only=False, key= "result_table"), segmentation_object],
-        [sg.Button('Add detection'), sg.Button('Compute colocalisation'), sg.Button('Batch detection')],
-        # [sg.Button('Save results', button_color= 'green'), sg.Button('Delete acquisitions',button_color= 'gray'), sg.Button('Reset segmentation',button_color= 'gray'), sg.Button('Reset results',button_color= 'gray')]
-        [sg.Button('Save results', button_color= 'green'), sg.Button('Reset results',button_color= 'gray')]
+        [sg.Button('Add detection'), sg.Button('Compute colocalisation')],#, sg.Button('Batch detection')],
+        [sg.Button('Save results', button_color= 'green'), sg.Button('Delete acquisitions',button_color= 'gray'), sg.Button('Reset segmentation',button_color= 'gray'), sg.Button('Reset results',button_color= 'gray')]
+        # [sg.Button('Save results', button_color= 'green'), sg.Button('Reset results',button_color= 'gray')]
     ]
 
     window = sg.Window('small fish', layout= layout, margins= (10,10))

small_fish_gui/pipeline/_colocalisation.py

@@ -204,13 +204,9 @@ def launch_colocalisation(result_tables, result_dataframe, colocalisation_distan
         voxel_size = voxel_size1
 
     if shape1 != shape2 :
-        print(shape1)
-        print(shape2) 
         raise MissMatchError("shape 1 different than shape 2")
     else :
         shape = shape1
-        print(shape1)
-        print(shape2)
 
     acquisition_couple = (acquisition1.at['acquisition_id'], acquisition2.at['acquisition_id'])
 
@@ -235,6 +231,9 @@ def launch_colocalisation(result_tables, result_dataframe, colocalisation_distan
         except MissMatchError as e :
             sg.popup(str(e))
             fraction_spots2_coloc_cluster1 = np.NaN
+        except TypeError : # Clusters not computed
+            fraction_spots2_coloc_cluster1 = np.NaN
+
 
     else : fraction_spots2_coloc_cluster1 = np.NaN
 
@@ -242,9 +241,12 @@ def launch_colocalisation(result_tables, result_dataframe, colocalisation_distan
         try :
             clusters2 = acquisition2['clusters'][:,:len(voxel_size)]
             fraction_spots1_coloc_cluster2 = spots_colocalisation(image_shape=shape, spot_list1=spots1, spot_list2=clusters2, distance= colocalisation_distance, voxel_size=voxel_size) / spot1_total
-        except MissMatchError as e :
+        except MissMatchError as e :# Clusters not computed
             sg.popup(str(e))
             fraction_spots1_coloc_cluster2 = np.NaN
+        except TypeError :
+            fraction_spots1_coloc_cluster2 = np.NaN
+
 
     else : fraction_spots1_coloc_cluster2 = np.NaN
 
@@ -261,6 +263,4 @@ def launch_colocalisation(result_tables, result_dataframe, colocalisation_distan
         'fraction_spots1_coloc_cluster2' : [fraction_spots1_coloc_cluster2],
     })
 
-    print(coloc_df.loc[:,['fraction_spots1_coloc_spots2','fraction_spots2_coloc_spots1', 'fraction_spots2_coloc_cluster1', 'fraction_spots1_coloc_cluster2']])
-
     return coloc_df

small_fish_gui/pipeline/_preprocess.py

@@ -269,4 +269,16 @@ def reorder_shape(shape, map) :
         np.array(shape)[source]
     )
 
-    return new_shape
+    return new_shape
+
+def clean_unused_parameters_cache(user_parameters: dict) :
+    """
+    Clean unused parameters that were set to None in previous run.
+    """
+    parameters = ['alpha', 'beta', 'gamma', 'cluster size', 'min number of spots']
+    for parameter in parameters :
+        if parameter in user_parameters.keys() :
+            if type(user_parameters[parameter]) == type(None) :
+                del user_parameters[parameter]
+    
+    return user_parameters

small_fish_gui/pipeline/_segmentation.py

@@ -31,7 +31,7 @@ def launch_segmentation(image: np.ndarray, user_parameters: dict) :
 
     while True : # Loop if show_segmentation 
         #Default parameters
-        cyto_model_name = user_parameters.setdefault('cyto_model_name', 'cyto2')
+        cyto_model_name = user_parameters.setdefault('cyto_model_name', 'cyto3')
         cyto_size = user_parameters.setdefault('cytoplasm diameter', 180)
         cytoplasm_channel = user_parameters.setdefault('cytoplasm channel', 0)
         nucleus_model_name = user_parameters.setdefault('nucleus_model_name', 'nuclei')
@@ -42,6 +42,7 @@ def launch_segmentation(image: np.ndarray, user_parameters: dict) :
         segment_only_nuclei = user_parameters.setdefault('Segment only nuclei', False)
         filename = user_parameters['filename']
         available_channels = list(range(image.shape[0]))
+        multichannel = user_parameters.get('multichannel')
 
 
     #Ask user for parameters
@@ -58,6 +59,7 @@ def launch_segmentation(image: np.ndarray, user_parameters: dict) :
                 show_segmentation_preset=show_segmentation,
                 segment_only_nuclei_preset=segment_only_nuclei,
                 filename_preset=filename,
+                multichannel=multichannel,
             )
 
             event, values = prompt_with_help(layout, help='segmentation')
@@ -236,7 +238,10 @@ def _segmentate_object(im, model_name, object_size_px, channels = [0,0]) :
     
     return label
 
-def _cast_segmentation_parameters(values) :
+def _cast_segmentation_parameters(values:dict) :
+
+    values.setdefault('cytoplasm channel',0)
+    values.setdefault('nucleus channel',0)
 
     if values['cyto_model_name'] == '' :
         values['cyto_model_name'] = None

small_fish_gui/pipeline/actions.py

@@ -31,7 +31,8 @@ def add_detection(user_parameters, segmentation_done, acquisition_id, cytoplasm_
     if user_parameters['Segmentation'] and not segmentation_done:
         im_seg = reorder_image_stack(map, user_parameters)
         cytoplasm_label, nucleus_label, user_parameters = launch_segmentation(im_seg, user_parameters=user_parameters)
-
+    elif segmentation_done :
+        pass
     else :
         cytoplasm_label, nucleus_label = None,None
 
@@ -124,4 +125,36 @@ def compute_colocalisation(result_tables, result_dataframe) :
     else :
         res_coloc = launch_colocalisation(result_tables, result_dataframe=result_dataframe, colocalisation_distance=colocalisation_distance)
 
-    return res_coloc
+    return res_coloc
+
+def delete_acquisitions(selected_acquisitions : pd.DataFrame, 
+                        result_df : pd.DataFrame, 
+                        cell_result_df : pd.DataFrame, 
+                        coloc_df : pd.DataFrame
+                        ) :
+    
+    if len(result_df) == 0 :
+        sg.popup("No acquisition to delete.")
+        return result_df, cell_result_df, coloc_df
+
+    if len(selected_acquisitions) == 0 :
+        sg.popup("Please select the acquisitions you would like to delete.")
+    else :
+        acquisition_ids = list(result_df.iloc[list(selected_acquisitions)]['acquisition_id'])
+        print("Acquisitions to delete : ", acquisition_ids)
+        result_drop_idx = result_df[result_df['acquisition_id'].isin(acquisition_ids)].index
+        print("{0} acquisitions to delete.".format(len(result_drop_idx)))
+        
+        if len(cell_result_df) > 0 :
+            cell_result_df_drop_idx = cell_result_df[cell_result_df['acquisition_id'].isin(acquisition_ids)].index
+            print("{0} cells to delete.".format(len(cell_result_df_drop_idx)))
+            cell_result_df = cell_result_df.drop(cell_result_df_drop_idx, axis=0)
+        
+        if len(coloc_df) > 0 :
+            coloc_df_drop_idx = coloc_df[(coloc_df["acquisition_id_1"].isin(acquisition_ids)) | (coloc_df['acquisition_id_2'].isin(acquisition_ids))].index
+            print("{0} coloc measurement to delete.".format(len(coloc_df_drop_idx)))
+            coloc_df = coloc_df.drop(coloc_df_drop_idx, axis=0)
+
+        result_df = result_df.drop(result_drop_idx, axis=0)
+
+    return result_df, cell_result_df, coloc_df

small_fish_gui/pipeline/detection.py

@@ -357,15 +357,17 @@ def launch_post_detection(image, spots, image_input_values: dict,) :
     #features
     fov_res['spot_number'] = len(spots)
     snr_res = compute_snr_spots(image, spots, voxel_size, spot_size)
-        
-    if dim == 3 :
-        Z,Y,X = list(zip(*spots))
-        spots_values = image[Z,Y,X]
+    if len(spots) == 0 :
+        fov_res['spotsSignal_median'], fov_res['spotsSignal_mean'], fov_res['spotsSignal_std'] = np.NaN, np.NaN, np.NaN
     else :
-        Y,X = list(zip(*spots))
-        spots_values = image[Y,X]
-
-    fov_res['spotsSignal_median'], fov_res['spotsSignal_mean'], fov_res['spotsSignal_std'] = np.median(spots_values), np.mean(spots_values), np.std(spots_values)
+        if dim == 3 :
+            Z,Y,X = list(zip(*spots))
+            spots_values = image[Z,Y,X]
+        else :
+            Y,X = list(zip(*spots))
+            spots_values = image[Y,X]
+        fov_res['spotsSignal_median'], fov_res['spotsSignal_mean'], fov_res['spotsSignal_std'] = np.median(spots_values), np.mean(spots_values), np.std(spots_values)
+    
     fov_res['median_pixel'] = np.median(image)
     fov_res['mean_pixel'] = np.mean(image)
 
@@ -374,6 +376,38 @@ def launch_post_detection(image, spots, image_input_values: dict,) :
 
     return spots, fov_res
 
+def _compute_cell_snr(image: np.ndarray, bbox, spots, voxel_size, spot_size) :
+    
+    min_y, min_x, max_y, max_x = bbox
+    image= image[min_y: max_y, min_x: max_x]
+
+    if len(spots) == 0 :
+        res = {
+           'snr_mean' : np.NaN,
+           'snr_median' : np.NaN,
+           'snr_std' : np.NaN,
+        }
+
+        return res
+
+    if len(spots[0]) == 3 :
+        Z,Y,X = zip(*spots)
+        spots = np.array(
+            list(zip(Y,X)),
+            dtype= int
+        )
+        voxel_size = voxel_size[1:]
+        spot_size = spot_size[1:]
+
+    snr_dict = compute_snr_spots(
+            image= image,
+            spots= spots,
+            spot_radius= spot_size,
+            voxel_size=voxel_size
+            )
+        
+    return snr_dict
+
 @add_default_loading
 def launch_cell_extraction(acquisition_id, spots, clusters, image, nucleus_signal, cell_label, nucleus_label, user_parameters) :
 
@@ -414,6 +448,7 @@ def launch_cell_extraction(acquisition_id, spots, clusters, image, nucleus_signa
 
     #Nucleus features : area is computed in bigfish
     features_names += ['nucleus_mean_signal', 'nucleus_median_signal', 'nucleus_max_signal', 'nucleus_min_signal']
+    features_names += ['snr_mean', 'snr_median', 'snr_std']
 
     result_frame = pd.DataFrame()
 
@@ -450,8 +485,22 @@ def launch_cell_extraction(acquisition_id, spots, clusters, image, nucleus_signa
                 compute_topography=True
             )
 
+        #Signal to noise
+        snr_dict = _compute_cell_snr(
+            image,
+            cell_bbox,
+            spots=rna_coords,
+            voxel_size=voxel_size,
+            spot_size=user_parameters['spot_size']
+        )
+
+        snr_mean = snr_dict['snr_mean']
+        snr_median = snr_dict['snr_median']
+        snr_std = snr_dict['snr_std']
+
         features = list(features)
         features += [np.mean(nuc_signal), np.median(nuc_signal), np.max(nuc_signal), np.min(nuc_signal)]
+        features += [snr_mean, snr_median, snr_std]
 
         features = [acquisition_id, cell_id, cell_bbox] + features
         
@@ -554,9 +603,9 @@ def launch_features_computation(acquisition_id, image, nucleus_signal, spots, cl
     if user_parameters['Cluster computation'] : 
         frame_results['cluster_number'] = len(clusters)
         if dim == 3 :
-            frame_results['total_spots_in_clusters'] = clusters.sum(axis=0)[3]
+            frame_results['total_spots_in_clusters'] = clusters.sum(axis=0)[3] if len(clusters) >0 else  0
         else :
-            frame_results['total_spots_in_clusters'] = clusters.sum(axis=0)[2]
+            frame_results['total_spots_in_clusters'] = clusters.sum(axis=0)[2] if len(clusters) >0 else  0
     
     if type(cell_label) != type(None) and type(nucleus_label) != type(None): 
         cell_result_dframe = launch_cell_extraction(
@@ -626,7 +675,7 @@ def get_nucleus_signal(image, other_images, user_parameters) :
             return np.zeros(shape=image.shape)
 
         if rna_signal_channel == nucleus_signal_channel :
-            nucleus_signal == image
+            nucleus_signal = image
         
         elif nucleus_signal_channel > rna_signal_channel :
             nucleus_signal_channel -=1

small_fish_gui/pipeline/main.py

@@ -2,7 +2,8 @@
 import pandas as pd
 import PySimpleGUI as sg
 from ..gui import hub_prompt
-from .actions import add_detection, save_results, compute_colocalisation
+from .actions import add_detection, save_results, compute_colocalisation, delete_acquisitions
+from ._preprocess import clean_unused_parameters_cache
 
 #'Global' parameters
 user_parameters = dict() # Very important object containg all choice from user that will influence the behavior of the main loop.
@@ -15,10 +16,15 @@ cytoplasm_label = None
 nucleus_label = None
 
 while True : #Break this loop to close small_fish
+    result_df = result_df.reset_index(drop=True)
+    cell_result_df = cell_result_df.reset_index(drop=True)
+    coloc_df = coloc_df.reset_index(drop=True)
     try :
         event, values = hub_prompt(result_df, segmentation_done)
 
         if event == 'Add detection' :
+            user_parameters = clean_unused_parameters_cache(user_parameters)
+            
 
             new_result_df, new_cell_result_df, acquisition_id, user_parameters, segmentation_done, cytoplasm_label, nucleus_label =  add_detection(
                 user_parameters=user_parameters,
@@ -64,8 +70,8 @@ while True : #Break this loop to close small_fish
             nucleus_label = None
 
         elif event == "Delete acquisitions" :
-        #TODO
-            pass
+            selected_acquisitions = values.setdefault('result_table', []) #Contains the lines selected by the user on the sum-up array.
+            result_df, cell_result_df, coloc_df = delete_acquisitions(selected_acquisitions, result_df, cell_result_df, coloc_df)
 
         elif event == "Batch detection" :
         #TODO

{small_fish_gui-1.0.4.dist-info → small_fish_gui-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: small_fish_gui
-Version: 1.0.4
+Version: 1.2.0
 Summary: Small Fish is a python application for the analysis of smFish images. It provides a ready to use graphical interface to combine famous python packages for cell analysis without any need for coding.
 Project-URL: Homepage, https://github.com/2Echoes/small_fish
 Project-URL: Issues, https://github.com/2Echoes/small_fish/issues

{small_fish_gui-1.0.4.dist-info → small_fish_gui-1.2.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
 small_fish_gui/LICENSE,sha256=-iFy8VGBYs5VsHglKpk4D-hxqQ2jMJaqmfq_ulIzDks,1303
-small_fish_gui/README.md,sha256=ZTYZCvrjrC0380pYFrB_9IN-lDGIbwz4A174Spb0jyU,1320
-small_fish_gui/__init__.py,sha256=aAh4brM-eTSnFOWpYSFgMIqJzbjJX45RHIWi7ppl_nA,1941
-small_fish_gui/__main__.py,sha256=sQ_HejagRTOcVpMuwUnLSO4MTZwqZ8uEplLHgqVpa6o,464
+small_fish_gui/README.md,sha256=LuvmYYwCVw7-rKhdhrtqxnxUfQxPUE-bbPlGNwzJh_4,1830
+small_fish_gui/__init__.py,sha256=X2D6chgv6h8daHaMPwY_iCAscI86KwOkCCez6vsShPw,1941
+small_fish_gui/__main__.py,sha256=EzSCoJ7jpSdK-QbzUwQLGZeQWjybNeq8VnCBucA8MZw,1372
 small_fish_gui/requirements.txt,sha256=9OMfUAnLdHevq6w_fVoDmVmkSMJeFofkOK_86_fu9C0,321
 small_fish_gui/start.py,sha256=HTbzsVcaMji1BZnWyjfn3bDGIQeXGG4zFzvCBepqFvA,108
 small_fish_gui/utils.py,sha256=tSoMb8N69WdKTtMItPb1DYZiIAz1mjI26BCKJAi6vuc,1798
@@ -9,10 +9,10 @@ small_fish_gui/.github/workflows/python-publish.yml,sha256=5Ltnuhw9TevhzndlBmdUg
 small_fish_gui/gui/__init__.py,sha256=178HC3t2z4EnP0iBnMcaP_pyh5xHwOkEE6p3WJwBQeU,911
 small_fish_gui/gui/animation.py,sha256=6_Y15_NzJ_TYBYseu3sSKaVkYRp2UCsVClAWOk3dESY,714
 small_fish_gui/gui/general_help_screenshot.png,sha256=X4E6Td5f04K-pBUPDaBJRAE3D5b8fuEdiAUKhkIDr-0,54210
-small_fish_gui/gui/help_module.py,sha256=pVSpGwhkI3bNr1EgBjnd-SukPTx6wcuFnAyyVNMZmWo,9608
-small_fish_gui/gui/layout.py,sha256=E_Z87S1YUR1gx2447OM0156dKXbzMA_q9joCO4hsZd8,7644
+small_fish_gui/gui/help_module.py,sha256=PmgkkDs7bZ2-po83A_PK9uldQcHjehYmqre21nYb6DQ,9600
+small_fish_gui/gui/layout.py,sha256=_ErOS2IUejeUuPLkDmPB3FzLkoHOWR-Iaxz-aUeETks,7695
 small_fish_gui/gui/mapping_help_screenshot.png,sha256=HcuRh5TYciUogUasza5vZ_QSshaiHsskQK23mh9vQS8,34735
-small_fish_gui/gui/prompts.py,sha256=mlw9NT5k3I8kTMB7w6W6QETbSIav_A7RhCmMVD7NFV0,12279
+small_fish_gui/gui/prompts.py,sha256=74JPsGGtGMcHNdNQFjjHEN5XwdSd7hZKog_DTIcYaJ8,12389
 small_fish_gui/gui/segmentation_help_screenshot.png,sha256=rbSgIydT0gZtfMh1qk4mdMbEIyCaakvHmxa2eOrLwO0,118944
 small_fish_gui/gui/test.py,sha256=Pf-GW9AgW-0VL1mFbYtqRvPAaa8DgwCThv2dDUHCcmU,156
 small_fish_gui/interface/__init__.py,sha256=PB86R4Y9kV80aGZ-vP0ZW2KeaCwGbBbCtFCmbN2yl28,275
@@ -20,17 +20,17 @@ small_fish_gui/interface/image.py,sha256=X1L7S5svxUwdoDcI3QM1PbN-c4Nz5w30hixq3Ig
 small_fish_gui/interface/output.py,sha256=wqXJHk-PzqZwYr8NHLg9jcEJlZQXZk8R76aeWcTxsEw,1337
 small_fish_gui/interface/parameters.py,sha256=lUugD-4W2TZyJF3TH1q70TlktEYhhPtcPCrvxm5Dk50,36
 small_fish_gui/interface/testing.py,sha256=MY5-GcPOUHagcrwR8A7QOjAmjZIDVC8Wz3NibLe3KQw,321
-small_fish_gui/pipeline/_colocalisation.py,sha256=-zz_kvghpMSaBhQT0moHvwC6ee92S-oq-j9qZWqgZMY,9677
+small_fish_gui/pipeline/_colocalisation.py,sha256=peBw2Qz5m6wSejDkDz240UgvWl8ohNelrnmEgznbEsw,9635
 small_fish_gui/pipeline/_custom_errors.py,sha256=tQ-AUhgzIFpK30AZiQQrtHCHyGVRDdAoIjzL0Fk-1pA,43
 small_fish_gui/pipeline/_detection_visualisation.py,sha256=CNxCQpiCzC9Uk-2RqSuTp55Glf1URCL_s8zidwljY9Y,5774
-small_fish_gui/pipeline/_preprocess.py,sha256=AlB86KuCA0UKA0XbTgXTJbg92Az34hzba_hsVs-uZl0,10035
-small_fish_gui/pipeline/_segmentation.py,sha256=IaeqsjwIweKH9LEm6qbDqssGW7R0MRZSh7PtF4etIEI,12772
+small_fish_gui/pipeline/_preprocess.py,sha256=RHbMeYG6GPYyPJzxksgCQ8bs2O3qSXU0V-z4NZWQhrA,10487
+small_fish_gui/pipeline/_segmentation.py,sha256=0f8M2Ujczm0tU5AVwxhfOyzRCi_P_gg1393S4RAvDFs,12968
 small_fish_gui/pipeline/_signaltonoise.py,sha256=7A9t7xu7zghI6cr201Ldm-LjJ5NOuP56VSeJ8KIzcUo,8497
-small_fish_gui/pipeline/actions.py,sha256=n6lr_LqV4PT5uw6KfovehUuUK-yTJ66G-IhY2uhHF_k,5472
-small_fish_gui/pipeline/detection.py,sha256=l4G2UHJmrzIg_alAge2GY0h5D34N_oqWzfgjfe2SI04,26032
-small_fish_gui/pipeline/main.py,sha256=4_Qk-NRhjOEsgN7T35NXOHj4OdDmZGS5kVeKde-yCiI,2593
+small_fish_gui/pipeline/actions.py,sha256=eKKmT3SSDYKQz-zU8HKz9h0PPgqyYrj4qHbrw1hfpRQ,7118
+small_fish_gui/pipeline/detection.py,sha256=n-uuk2cP9Ls3WaZnuQfNHWyPoJWZNh8k9yW_8ZDC3fA,27484
+small_fish_gui/pipeline/main.py,sha256=AAW-zK3b7Ece9cdHn9y6QG8lTa1HXG-8JtnvJ3m0HwA,3149
 small_fish_gui/pipeline/test.py,sha256=w4ZMGDmUDXxVgWTlZ2TKw19W8q5gcE9gLMKe0SWnRrw,2827
-small_fish_gui-1.0.4.dist-info/METADATA,sha256=Ts0ZLtdXghljsj3JiBpsQcDsCtwUu76gvZhY91kd5pA,2567
-small_fish_gui-1.0.4.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-small_fish_gui-1.0.4.dist-info/licenses/LICENSE,sha256=-iFy8VGBYs5VsHglKpk4D-hxqQ2jMJaqmfq_ulIzDks,1303
-small_fish_gui-1.0.4.dist-info/RECORD,,
+small_fish_gui-1.2.0.dist-info/METADATA,sha256=ayA13aIDIc9K64nQLNlxWcTNNM7tO17BaK3kEycGiQw,2567
+small_fish_gui-1.2.0.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+small_fish_gui-1.2.0.dist-info/licenses/LICENSE,sha256=-iFy8VGBYs5VsHglKpk4D-hxqQ2jMJaqmfq_ulIzDks,1303
+small_fish_gui-1.2.0.dist-info/RECORD,,