New version of annotator

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/_static/custom.css

@@ -0,0 +1,11 @@
+.wy-nav-content {
+    max-width: none;
+}
+
+.wy-table-responsive table td, .wy-table-responsive table th {
+    white-space: normal;
+}
+
+table caption {
+    caption-side: bottom;
+}

docs/analyze_microglia.rst

@@ -0,0 +1,3 @@
+=================
+Analyze Microglia
+=================

docs/annotate_patches.rst

@@ -0,0 +1,96 @@
+===========================
+Annotate your data for YOLO
+===========================
+
+- The goal of this widget is to help you annotate your data for the YOLO model.
+- YOLO is a deep learning model that can detect objects in images.
+- Detections are composed of bounding-boxes around objects and a class label.
+- To train the model, you need to provide a dataset of annotated images.
+- The widget "YOLO Annotator" will help you to create this dataset.
+
+.. image:: _images/yolo/banner.jpg
+   :align: center
+   :width: 800px
+
+1. Prepare your data
+====================
+
+- First of all, the data that you will annotate must be ready.
+- Your images must all be the same size in pixels.
+- You can use TIF, PNG, JPG, ... but no proprietary format (CZI, LIF, ...).
+- You can use the "Tiles creator" widget to create patches from your images. A common size is 512x512 pixels.
+- All the images that you want to annotate must be in the same folder.
+- Before you start, you should have a folder structure like this:
+
+.. code-block:: bash
+
+   📁 some-folder
+   ├── 📁 my-experiment
+   │   ├── 14-25-23.336.tif
+   │   ├── 14-25-23.379.tif
+   │   ├── ...
+   │   └── 14-25-36.949.tif
+
+
+2. Initialize the widget
+========================
+
+- Open the widget located in: Plugins > Microglia Analyzer > YOLO Annotator.
+- Click the "Root folder" button and choose the folder named "some-folder" in the previous example. It is the folder containing the folder in which your images are located.
+- In the "Inputs sub-folder" dropdown menu, choose the folder named "my-experiment" in the previous example. It is the folder containing your images.
+- The first image of your experiment will be displayed.
+- You can navigate through the images using the dropdown menu in the "Annotations management" section.
+
+
+3. Create your classes
+======================
+
+- The first thing to do is to create new classes. Each one corresponds to a different type of object that you want to detect.
+- Simply fill the text field in the "Classes management" section and click the "New class" button.
+- You can add as many classes as you want.
+- The classes that you add should appear in the layers stack of Napari (on the left side of the window).
+
+
+4. Annotate your data
+=====================
+
+- To annotate an object, you have to draw a bounding-box around it. You are limited to rectangles. Do not use ellipses or polygons or anything else.
+- You can choose the rectangle tool in the upper-left section of the Napari's window.
+- Your boxes should contain the whole object and a few pixels around it.
+- It is not a problem if the boxes overlap.
+- If you failed a box, don't edit it: delete it and draw a new one.
+- If you don't plan to annotate many images, you should really be careful not to forget any object on your images.
+- When you are happy with the annotations you made, click the "Save annotations" button in the "Annotations management" section.
+- In the "Classes management" section, a table should have appeared to show you global statistics about your annotations. 
+- A new folder with the "-labels" suffix should have appeared in the root folder. It contains the annotations you made.
+- A new file with the "-classes.txt" suffix should have appeared in the root folder. It contains the classes you created.
+- Your files architecture should now look like this:
+
+.. code-block:: bash
+
+   📁 some-folder
+   ├── 📁 my-experiment
+   │   ├── 14-25-23.336.tif
+   │   ├── 14-25-23.379.tif
+   │   ├── ...
+   │   └── 14-25-36.949.tif
+   ├── 📁 my-experiment-labels
+   │   ├── 14-25-23.336.txt
+   │   ├── 14-25-23.379.txt
+   │   ├── ...
+   │   └── 14-25-36.949.txt
+   ├── 📃 my-experiment-classes.txt
+
+
+Notes
+=====
+
+- If you are working on RGB images, they will be converted to grayscale.
+- If you already annotated some images, your annotations will be loaded when you open the widget.
+- Whenever it is possible, try to have a balanced dataset. It means that you should have the same number of annotations for each class.
+- In the ".txt" files generated for each image by the widget, the content is as follows:
+   - [integer]: the class index (starting from 0).
+   - [float]: the x-coordinate of the center of the bounding-box, in percentage of the image width.
+   - [float]: the y-coordinate of the center of the bounding-box, in percentage of the image height.
+   - [float]: the width of the bounding-box, in percentage of the image width.
+   - [float]: the height of the bounding-box, in percentage of the image height.

docs/conf.py

@@ -0,0 +1,72 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+
+import os
+import sys
+
+mod_path = os.path.abspath('../src')
+print(mod_path)
+sys.path.insert(0, mod_path)
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'Protoplasts swelling analyzer'
+copyright = '2024, Clément H. Benedetti'
+author = 'Clément H. BENEDETTI'
+
+# The full version, including alpha/beta/rc tags
+release = '1.0.0'
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.napoleon',
+    'sphinx_tabs.tabs',
+    'myst_parser',
+    'sphinx_rtd_theme',
+]
+
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+html_css_files = ['custom.css']
+
+html_favicon = 'icon.png'
+
+autosummary_generate = True

docs/index.rst

@@ -0,0 +1,20 @@
+Microglia Analyzer
+==================
+
+.. toctree::
+   :maxdepth: 3
+   :caption: Contents:
+
+   user_guide
+   make_patches
+   annotate_patches
+   analyze_microglia
+   modules
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/make_patches.rst

@@ -0,0 +1,62 @@
+.. _make_patches: 
+
+==============================
+Patches from calibrated images
+==============================
+
+
+1. Detect the protoplasts
+=========================
+
+A single experiment is 20 GB of size in average. We would like not to waste processing time to launch the segmentation of traps that are actually empty.
+To do so, we implemented a way to detect the presence of protoplasts (find their centroïd).
+
+The first step of the algorithm consists in processing the "activity map" of this experiment. By this, we mean the areas where protoplasts are spinning on themselves. 
+
+This is achieved by summing the absolute difference between each contiguous pairs of frame.
+
+Then, we apply a sequence of filters (Median blur, Laplacian of Gaussian, threshold et connected components labeling) to find a little spot of pixels per protoplast. We finish this step with a points-set containing one point on each protoplast.
+
+
+.. image:: _images/patches/activity-map-building.png
+   :align: center
+
+
+
+
+2. Create the patches
+=====================
+
+For a model to predict correctly objects, the patches you feed it must be similar to the ones it was trained with.
+
+The model we trained requires patches that are exactly 128×128 pixels of size.
+It sounds like a big constraint as it implies that your pixel size should always be the same.
+Indeed, if we cut a patch of 128×128 pixels, those 128 pixels are 115.2 µm if the size of a pixel is 0.9 µm and they are only 76.8 µm if a pixel is 0.65 µm.
+
+We addressed this problem by doing a two-step patches extraction.
+
+Instead of cutting patches of 128×128 pixels in the main image, we cut patches of 130×130 µm, whatever size in pixels it is.
+Once we have those patches, we re-sample them by scaling them so they can fit in a 128×128 pixels image.
+
+.. table:: An object of 20µm of diameter with different pixel sizes
+   :align: center
+
+   +----------------------------------------------------+-------------------------------------------------------------+--------------------------------------------------------------+
+   | .. image:: _images/calibration/calibration-1.png   | .. image:: _images/calibration/calibration-1-psize0_9.png   | .. image:: _images/calibration/calibration-1-psize0_65.png   |
+   |   :height: 250px                                   |   :height: 250px                                            |   :height: 250px                                             |
+   |   :width: 250px                                    |   :width: 250px                                             |   :width: 250px                                              |
+   |   :align: center                                   |   :align: center                                            |   :align: center                                             |
+   +----------------------------------------------------+-------------------------------------------------------------+--------------------------------------------------------------+
+   | The object is always 20µm of diameter              | Pixel size = 0.9µm                                          | Pixel size = 0.65µm                                          |
+   +----------------------------------------------------+-------------------------------------------------------------+--------------------------------------------------------------+
+
+
+.. image:: _images/patches/physical-size.png
+   :align: center
+   :width: 400px
+
+
+3. Export the patches
+=====================
+
+The patches are exported in 128×128 pixels, on 32 bits, normalized between 0 and 1.

docs/microglia_analyzer.custom-loss.rst

@@ -0,0 +1,7 @@
+microglia\_analyzer.custom\-loss module
+=======================================
+
+.. automodule:: microglia_analyzer.custom-loss
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/microglia_analyzer.microglia_analyzer.rst

@@ -0,0 +1,7 @@
+microglia\_analyzer.microglia\_analyzer module
+==============================================
+
+.. automodule:: microglia_analyzer.microglia_analyzer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/microglia_analyzer.rst

@@ -0,0 +1,27 @@
+microglia\_analyzer package
+===========================
+
+Subpackages
+-----------
+
+.. toctree::
+   :maxdepth: 4
+
+   microglia_analyzer.tiles
+
+Submodules
+----------
+
+.. toctree::
+   :maxdepth: 4
+
+   microglia_analyzer.custom-loss
+   microglia_analyzer.microglia_analyzer
+
+Module contents
+---------------
+
+.. automodule:: microglia_analyzer
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/microglia_analyzer.tiles.patch.rst

@@ -0,0 +1,7 @@
+microglia\_analyzer.tiles.patch module
+======================================
+
+.. automodule:: microglia_analyzer.tiles.patch
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/microglia_analyzer.tiles.plot.rst

@@ -0,0 +1,7 @@
+microglia\_analyzer.tiles.plot module
+=====================================
+
+.. automodule:: microglia_analyzer.tiles.plot
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/microglia_analyzer.tiles.recalibrate.rst

@@ -0,0 +1,7 @@
+microglia\_analyzer.tiles.recalibrate module
+============================================
+
+.. automodule:: microglia_analyzer.tiles.recalibrate
+   :members:
+   :undoc-members:
+   :show-inheritance: