Merge branch 'main' of https://github.com/AdaptiveMotorControlLab/CellSeg3d into v0.0.1rc3

Author: MMathisLab

.gitignore

@@ -8,8 +8,10 @@ __pycache__/
 
 # unwanted results files
 *.tif
+*.tiff
 napari_cellseg3d/_tests/res/*.csv
 *.pth
+*.db
 
 # Distribution / packaging
 .Python
@@ -97,3 +99,4 @@ venv/
 /napari_cellseg3d/models/saved_weights/
 /docs/res/logo/old_logo/
 /reqs/
+

README.md

@@ -23,6 +23,11 @@ A napari plugin for 3D cell segmentation: training, inference, and data review.
 
 ## Installation
 
+Note : we recommend using conda to create a new environment for the plugin.
+
+    conda create --name python=3.8 napari-cellseg3d
+    conda activate napari-cellseg3d
+
 You can install `napari-cellseg3d` via [pip]:  
 
     pip install napari-cellseg3d

docs/conf.py

@@ -70,7 +70,7 @@
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:

docs/res/code/interface.rst

@@ -1,50 +1,75 @@
 interface.py
 =============
 
-Functions
+Classes
 -------------
 
-open_url
+Button
 **************************************
-.. autofunction:: napari_cellseg3d.interface::open_url
+.. autoclass:: napari_cellseg3d.interface::Button
+   :members: __init__, visibility_condition
 
+DropdownMenu
+**************************************
+.. autoclass:: napari_cellseg3d.interface::DropdownMenu
+   :members: __init__
 
-make_scrollable
+CheckBox
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_scrollable
+.. autoclass:: napari_cellseg3d.interface::CheckBox
+   :members: __init__
 
+AnisotropyWidgets
+**************************************
+.. autoclass:: napari_cellseg3d.interface::AnisotropyWidgets
+   :members: __init__, build, get_anisotropy_resolution_xyz, get_anisotropy_resolution_zyx, anisotropy_zoom_factor,is_enabled,toggle_permanent_visibility
 
-make_group
+
+FilePathWidget
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_group
+.. autoclass:: napari_cellseg3d.interface::FilePathWidget
+   :members: __init__, build, get_text_field, get_button, check_ready, set_required, update_field_color, set_description
 
-add_to_group
+ScrollArea
 **************************************
-.. autofunction:: napari_cellseg3d.interface::add_to_group
+.. autoclass:: napari_cellseg3d.interface::ScrollArea
+   :members: __init__, make_scrollable
 
-make_container
+DoubleIncrementCounter
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_container
+.. autoclass:: napari_cellseg3d.interface::DoubleIncrementCounter
+   :members: __init__, set_precision, make_n
+
+IntIncrementCounter
+**************************************
+.. autoclass:: napari_cellseg3d.interface::IntIncrementCounter
+   :members: __init__, make_n
 
 
-make_button
+Functions
+-------------
+
+open_url
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_button
+.. autofunction:: napari_cellseg3d.interface::open_url
+
 
-make_combobox
+make_group
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_combobox
+.. autofunction:: napari_cellseg3d.interface::make_group
 
-make_checkbox
+add_to_group
 **************************************
-.. autofunction:: napari_cellseg3d.interface::make_checkbox
+.. autofunction:: napari_cellseg3d.interface::add_to_group
 
+make_container
+**************************************
+.. autofunction:: napari_cellseg3d.interface::make_container
 
 combine_blocks
 **************************************
 .. autofunction:: napari_cellseg3d.interface::combine_blocks
 
-
 add_blank
 **************************************
 .. autofunction:: napari_cellseg3d.interface::add_blank

docs/res/guides/convert_module_guide.rst

@@ -17,6 +17,12 @@ You can :
 * Remove small objects :
     You can specify a size threshold in pixels; all objects smaller than this size will be removed in the image.
 
+* Resize anisotropic images :
+    Specifiy the resolution of your microscope to remove anisotropy from images.
+
+.. important:: Does not work for instance labels currently.
+
+
 .. figure:: ../images/converted_labels.png
    :scale: 30 %
    :align: center

docs/res/guides/cropping_module_guide.rst

@@ -25,6 +25,12 @@ Folders can be stacks of either .png or .tif files, ideally numbered with the in
 You can then choose the size of the cropped volume, which will be constant throughout the process; make sure it is correct beforehand.
 Setting a larger size than the size of the image will cause issues.
 
+You can also opt to correct the anisotropy if your image is anisotropic :
+simply set the resolution to the one of your microscope.
+
+.. important::
+    This will simply scale the image in the viewer, but saved images will **still be anisotropic.** To resize your image, see :doc:`convert_module_guide`
+
 Once you are ready, you can press **Start** to start the review process.
 
 

docs/res/guides/inference_module_guide.rst

@@ -3,9 +3,13 @@
 Inference module guide
 =================================
 
-This module allows you to use  pre-trained segmentation algorithms (written in Pytorch) on volumes
+This module allows you to use  pre-trained segmentation algorithms (written in Pytorch) on 3D volumes
 to automatically label cells.
 
+.. important::
+    Currently, only inference on **3D volumes is supported**. Your image and label folders should both contain a set of
+    **3D image files**, currently either **.tif** or **.tiff**. Loading a folder of 2D images as a stack is not supported as of yet.
+
 Currently, the following pre-trained models are available :
 
 ==============   ================================================================================================
@@ -31,7 +35,7 @@ Interface and functionalities
 
 * **Loading data** :
 
-  | When launching the module, you will be asked to provide an **image folder** containing all the volumes you'd like to be labeled.
+  | When launching the module, you will be asked to provide an **image folder** containing all the 3D volumes you'd like to be labeled.
   | All images with the chosen extension (**.tif** or **.tiff** currently supported) in this folder will be labeled.
   | You can then choose an **output folder**, where all the results will be saved.
 

docs/res/guides/review_module_guide.rst

@@ -19,6 +19,12 @@ Launching the review process
 .. note::
     Only single 3D **.tif** files or 2D stacks of several **.png** or **.tif** in a folder are currently supported.
 
+* Anisotropic data :
+    This will scale the images to visually remove the anisotropy, so as to make review easier.
+
+.. important::
+    Results will still be saved as anisotropic images. If you wish to resize your images, see the :doc:`convert_module_guide`
+
 * CSV file name :
     You can then provide a model name, which will be used to name the csv file recording the status of each slice.
 

docs/res/guides/training_module_guide.rst

@@ -6,6 +6,11 @@ Training module guide
 This module allows you to train pre-defined Pytorch models for cell segmentation.
 Pre-defined models are stored in napari-cellseg-3d/models.
 
+.. important::
+    Currently, only inference on **3D volumes is supported**. Your image and label folders should both contain a set of
+    **3D image files**, currently either **.tif** or **.tiff**. Loading a folder of 2D images as a stack is not supported as of yet.
+
+
 Currently, the following pre-defined models are available :
 
 ==============   ================================================================================================
@@ -31,8 +36,8 @@ The training module is comprised of several tabs.
 
 1) The first one, **Data**, will let you set :
 
-* The path to the images folder
-* The path to the labels folder
+* The path to the images folder (3D image files)
+* The path to the labels folder (3D image files)
 * The path to the results folder
 
 * Whether to copy results to a zip file (for easier transferability)