Feedback fixes

.github/workflows/test_and_deploy.yml

@@ -52,7 +52,7 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           python -m pip install setuptools tox tox-gh-actions
-#         pip install git+https://github.com/kodalli/pydensecrf.git@master#egg=pydensecrf
+#         pip install git+https://github.com/lucasb-eyer/pydensecrf.git@master#egg=pydensecrf
 
 # this runs the platform-specific tests declared in tox.ini
       - name: Test with tox

.gitignore

@@ -115,6 +115,8 @@ notebooks/instance_test.ipynb
 *.prof
 /docs/_build/
 /docs/source/code/_autosummary/*.rst
+cov.syspath.txt
+napari_cellseg3d/dev_scripts/wandb
 
 #include test data
 !napari_cellseg3d/_tests/res/test.tif
@@ -123,9 +125,7 @@ notebooks/instance_test.ipynb
 !napari_cellseg3d/_tests/res/wnet_test/*.tif
 !napari_cellseg3d/_tests/res/wnet_test/lab/*.tif
 !napari_cellseg3d/_tests/res/wnet_test/vol/*.tif
-cov.syspath.txt
 
 #include docs images
 !docs/source/logo/*
 !docs/source/images/*
-napari_cellseg3d/dev_scripts/wandb

README.md

@@ -1,6 +1,5 @@
 # napari-cellseg3D: a napari plug-in for direct 3D cell segmentation with deep learning
 
-
 <img src="https://images.squarespace-cdn.com/content/v1/57f6d51c9f74566f55ecf271/838605d0-9723-4e43-83cd-6dbfe4adf36b/cellseg-logo.png?format=1500w" title="cellseg3d" alt="cellseg3d logo" width="350" align="right" vspace = "80"/>
 
 <a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
@@ -10,23 +9,34 @@
 [![codecov](https://codecov.io/gh/AdaptiveMotorControlLab/CellSeg3d/branch/main/graph/badge.svg?token=hzUcn3XN8F)](https://codecov.io/gh/AdaptiveMotorControlLab/CellSeg3d)
 [![napari hub](https://img.shields.io/endpoint?url=https://api.napari-hub.org/shields/napari-cellseg3d)](https://www.napari-hub.org/plugins/napari-cellseg3d)
 
-
 A napari plugin for 3D cell segmentation: training, inference, and data review. In particular, this project was developed for analysis of mesoSPIM-acquired (cleared tissue + lightsheet) datasets.
 
+**Help us make the code better by reporting issues and adding your feature requests!**
+
 ----------------------------------
 
 ## News
 
-*April 2023: New version with interface overhaul published ! New model and utilities coming soon*
+**New version : v1.0**
 
+Added :
 
-**This is an alpha version, please expect bugs and issues, and help us make the code better by reporting them as an issue!**
+- Improved training interface
+- Unsupervised model : WNet
+  - Generate labels directly from raw data !
+  - Can be trained in napari directly or in Colab
+  - Pretrained weights for mesoSPIM whole-brain cell segmentation
+- WandB support (install wandb and login to use automatically when training)
+- Remade and improved documentation
+  - Moved to Jupyter Book
+  - Dedicated installation page, and working ARM64 install for macOS Silicon users
+- New utilities
+- Many small improvements and many bug fixes
 
 ## Demo
 
 ![demo](https://images.squarespace-cdn.com/content/v1/57f6d51c9f74566f55ecf271/0d16a71b-3ff2-477a-9d83-18d96cb1ce28/full_demo.gif?format=500w)
 
-
 ## Installation
 
 **Note** : we recommend using conda to create a new environment for the plugin.
@@ -58,14 +68,15 @@ To avoid issues when installing on the ARM64 architecture, please follow these s
         conda env create -f conda/napari_cellseg3d_m1.yml
         conda activate napari_cellseg3d_m1
 
-2) Then install PyQt5 from conda separately :
+2) Install the plugin.
+   From repository root folder, run :
 
-        conda install -c anaconda pyqt
-
-3) And install the plugin :
+        pip install -e .
+   OR directly via PyPi :
 
         pip install napari-cellseg3d
 
+   OR directly via [napari-hub] (see Installation section above)
 
 ## Documentation
 
@@ -86,21 +97,21 @@ Then go into Plugins > napari-cellseg3d, and choose which tool to use.
 - **Train**:  This module allows you to train segmentation algorithms from labeled volumes.
 - **Utilities**: This module allows you to perform several actions like cropping your volumes and labels dynamically, by selecting a fixed size volume and moving it around the image; computing prediction scores from ground truth and predicition labels; or converting labels from instance to segmentation and the opposite.
 
-
 ## Requirements
-**Python >= 3.8 required**
 
-Requires **pytorch** and **MONAI**.
-For PyTorch, please see [PyTorch's website for installation instructions].
+**Python 3.8 or 3.9 required.**
+Requires **[napari]**, **[PyTorch]** and **[MONAI]**.
+
+For PyTorch, please see [the PyTorch website for installation instructions].
+
 A CUDA-capable GPU is not needed but very strongly recommended, especially for training.
-If you get errors from MONAI regarding missing readers, please see [MONAI's optional dependencies] page for instructions on getting the readers required by your images.
 
+If you get errors from MONAI regarding missing readers, please see [MONAI's optional dependencies] page for instructions on getting the readers required by your images.
 
 ## Issues
 
 If you encounter any problems, please [file an issue] along with a detailed description.
 
-
 ## Testing
 
 To run tests locally:
@@ -134,20 +145,15 @@ Distributed under the terms of the [MIT] license.
 [Cookiecutter]: https://github.com/audreyr/cookiecutter
 [@napari]: https://github.com/napari
 [MIT]: http://opensource.org/licenses/MIT
-[BSD-3]: http://opensource.org/licenses/BSD-3-Clause
-[GNU GPL v3.0]: http://www.gnu.org/licenses/gpl-3.0.txt
-[GNU LGPL v3.0]: http://www.gnu.org/licenses/lgpl-3.0.txt
-[Apache Software License 2.0]: http://www.apache.org/licenses/LICENSE-2.0
-[Mozilla Public License 2.0]: https://www.mozilla.org/media/MPL/2.0/index.txt
 [cookiecutter-napari-plugin]: https://github.com/napari/cookiecutter-napari-plugin
-
-[napari]: https://github.com/napari/napari
 [tox]: https://tox.readthedocs.io/en/latest/
 [pip]: https://pypi.org/project/pip/
 [PyPI]: https://pypi.org/
 
-[PyTorch's website for installation instructions]: https://pytorch.org/get-started/locally/
+[the PyTorch website for installation instructions]: https://pytorch.org/get-started/locally/
+[PyTorch]: https://pytorch.org/get-started/locally/
 [MONAI's optional dependencies]: https://docs.monai.io/en/stable/installation.html#installing-the-recommended-dependencies
+[MONAI]: https://docs.monai.io/en/stable/installation.html#installing-the-recommended-dependencies
 
 ## Acknowledgements
 
@@ -156,12 +162,5 @@ This work was funded, in part, from the Wyss Center to the [Mathis Laboratory of
 Please refer to the documentation for full acknowledgements.
 
 ## Plugin base
-This [napari] plugin was generated with [Cookiecutter] using [@napari]'s [cookiecutter-napari-plugin] template.
 
-<!--
-Don't miss the full getting started guide to set up your new package:
-https://github.com/napari/cookiecutter-napari-plugin#getting-started
-
-and review the napari docs for plugin developers:
-https://napari.org/plugins/stable/index.html
--->
+This [napari] plugin was generated with [Cookiecutter] using [@napari]'s [cookiecutter-napari-plugin] template.

conda/napari_cellseg3d_m1.yml

@@ -4,23 +4,25 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-    - python=3.8
+    - python=3.9
     - pip
+    - pyqt
+    - imagecodecs
     - pip:
         - numpy
         - napari>=0.4.14
-        - QtPy
         - opencv-python>=4.5.5
         - scikit-image>=0.19.2
         - matplotlib>=3.4.1
         - tifffile>=2022.2.9
         - imageio-ffmpeg>=0.4.5
         - torch>=1.11
-        - monai>=0.9.0
+        - monai[nibabel, einops]>=0.9.0
         - tqdm
         - nibabel
         - scikit-image
         - pillow
+        - pyclesperanto-prototype
         - tqdm
         - matplotlib
         - vispy>=0.9.6

docs/_config.yml

@@ -8,7 +8,7 @@ logo: source/logo/logo_alpha.png
 # Force re-execution of notebooks on each build.
 # See https://jupyterbook.org/content/execute.html
 execute:
-  execute_notebooks: force
+  execute_notebooks: 'off'
 
 # Define the name of the latex output file for PDF builds
 latex:

docs/source/guides/installation_guide.rst

@@ -90,6 +90,7 @@ In the terminal, navigate to the CellSeg3D folder:
 
 .. code-block::
 
+    cd CellSeg3D
     conda env create -f conda/napari_cellseg3d_m1.yml
 
 3. **Activate the environment** :
@@ -98,14 +99,14 @@ In the terminal, navigate to the CellSeg3D folder:
 
     conda activate napari_cellseg3d_m1
 
-4. **Install PyQt5 via conda** :
+4. **Install the plugin** :
 
 .. code-block::
 
-    conda install -c anaconda pyqt
+    pip install napari-cellseg3d
 
-5. **Install the plugin** :
+OR to install from source:
 
 .. code-block::
 
-    pip install napari-cellseg3d
+    pip install -e .

docs/welcome.rst

@@ -11,10 +11,11 @@ Use CellSeg3D to:
 * Review labeled cell volumes from whole-brain samples of mice imaged by mesoSPIM microscopy [1]_
 * Train and use segmentation models from the MONAI project [2]_ or implement your own custom 3D segmentation models using PyTorch.
 
-No labeled data? Try our unsupervised model to automate your data labelling.
+No labeled data? Try our unsupervised model, based on the `WNet`_ model, to automate your data labelling.
 
 The models provided should be adaptable to other tasks related to detection of 3D objects,
 outside of whole-brain light-sheet microscopy.
+This applies to the unsupervised model as well, feel free to try to generate labels for your own data!
 
 .. figure:: https://images.squarespace-cdn.com/content/v1/57f6d51c9f74566f55ecf271/0d16a71b-3ff2-477a-9d83-18d96cb1ce28/full_demo.gif?format=500w
    :alt: CellSeg3D demo
@@ -52,6 +53,7 @@ you need further assistance, please see below.
 Installation
 --------------------------------------------
 CellSeg3D can be run on Windows, Linux, or MacOS.
+
 For detailed installation instructions, including installing pre-requisites,
 please see :ref:`source/guides/installation_guide:Installation guide ⚙`
 
@@ -72,8 +74,6 @@ For local installation after cloning from GitHub, please run the following in th
 
 If the installation was successful, you will find the napari-cellseg3D plugin in the Plugins section of napari.
 
-
-
 Usage
 --------------------------------------------
 
@@ -160,7 +160,7 @@ This plugin mainly uses the following libraries and software:
 
 * `pyclEsperanto`_ (for the Voronoi Otsu labeling) by Robert Haase
 
-* A custom re-implementation of the `WNet model`_ by Xia and Kulis [3]_
+* A custom re-implementation of the `WNet`_ by Xia and Kulis [3]_
 
 .. _Mathis Laboratory of Adaptive Motor Control: http://www.mackenziemathislab.org/
 .. _Wyss Center: https://wysscenter.ch/
@@ -170,7 +170,7 @@ This plugin mainly uses the following libraries and software:
 .. _MONAI project: https://monai.io/
 .. _on their website: https://docs.monai.io/en/stable/networks.html#nets
 .. _pyclEsperanto: https://github.com/clEsperanto/pyclesperanto_prototype
-.. _WNet model: https://arxiv.org/abs/1711.08506
+.. _WNet: https://arxiv.org/abs/1711.08506
 
 .. rubric:: References
 

napari_cellseg3d/_tests/test_inference.py

@@ -90,15 +90,18 @@ def __call__(self, x):
         post_process_transforms=mock_work(),
     )
     assert isinstance(res, InferenceResult)
-    assert res.result is not None
+    assert res.semantic_segmentation is not None
 
 
 def test_post_processing():
-    config = InferenceWorkerConfig()
-    worker = InferenceWorker(worker_config=config)
-
     image = rand_gen.random((1, 1, 64, 64, 64))
     labels = rand_gen.random((1, 2, 64, 64, 64))
+    mock_layer = napari.layers.Image(data=image)
+    mock_layer.name = "test"
+
+    config = InferenceWorkerConfig()
+    config.layer = mock_layer
+    worker = InferenceWorker(worker_config=config)
 
     results = worker.run_crf(image, labels, lambda x: x)
     assert results.shape == (2, 64, 64, 64)

napari_cellseg3d/_tests/test_plugin_inference.py

@@ -25,23 +25,23 @@ def test_inference(make_napari_viewer_proxy, qtbot):
 
     assert len(viewer.layers) == 1
 
-    widget.window_infer_box.setChecked(True)
+    widget.use_window_choice.setChecked(True)
     widget.window_overlap_slider.setValue(0)
     widget.keep_data_on_cpu_box.setChecked(True)
 
     assert widget.check_ready()
 
     widget.model_choice.setCurrentText("WNet")
     widget._restrict_window_size_for_model()
-    assert widget.window_infer_box.isChecked()
+    assert widget.use_window_choice.isChecked()
     assert widget.window_size_choice.currentText() == "64"
 
     test_model_name = "test"
     MODEL_LIST[test_model_name] = TestModel
     widget.model_choice.addItem(test_model_name)
     widget.model_choice.setCurrentText(test_model_name)
 
-    widget.window_infer_box.setChecked(False)
+    widget.use_window_choice.setChecked(False)
     widget.worker_config = widget._set_worker_config()
     assert widget.worker_config is not None
     assert widget.model_info is not None
@@ -50,7 +50,7 @@ def test_inference(make_napari_viewer_proxy, qtbot):
     assert worker.config is not None
     assert worker.config.model_info is not None
     assert worker.config.sliding_window_config.is_enabled() is False
-    worker.config.layer = viewer.layers[0].data
+    worker.config.layer = viewer.layers[0]
     worker.config.post_process_config.instance.enabled = True
     worker.config.post_process_config.instance.method = (
         INSTANCE_SEGMENTATION_METHOD_LIST["Watershed"]()
@@ -61,7 +61,7 @@ def test_inference(make_napari_viewer_proxy, qtbot):
 
     res = next(worker.inference())
     assert isinstance(res, InferenceResult)
-    assert res.result.shape == (8, 8, 8)
+    assert res.semantic_segmentation.shape == (8, 8, 8)
     assert res.instance_labels.shape == (8, 8, 8)
     widget.on_yield(res)
 
@@ -73,7 +73,7 @@ def test_inference(make_napari_viewer_proxy, qtbot):
         instance_labels=mock_labels,
         crf_results=mock_image,
         stats=[volume_stats(mock_labels)],
-        result=mock_image,
+        semantic_segmentation=mock_image,
         model_name="test",
     )
     num_layers = len(viewer.layers)

napari_cellseg3d/_tests/test_plugin_training.py

@@ -44,7 +44,7 @@ def test_worker_configs(make_napari_viewer_proxy):
                 worker.config, attr
             )
     widget.unsupervised_images_filewidget.text_field.setText(
-        str(im_path.parent)
+        str((im_path.parent / "wnet_test").resolve())
     )
     widget.data = widget.create_dataset_dict_no_labs()
     worker = widget._create_worker(additional_results_description="TEST_2")

napari_cellseg3d/_tests/test_plugin_utils.py

@@ -1,5 +1,6 @@
 import numpy as np
 
+from napari_cellseg3d.code_plugins.plugin_convert import StatsUtils
 from napari_cellseg3d.code_plugins.plugin_crop import Cropping
 from napari_cellseg3d.code_plugins.plugin_utilities import (
     UTILITIES_WIDGETS,
@@ -57,3 +58,15 @@ def test_crop_widget(make_napari_viewer_proxy):
     widget.sliders[2].setValue(2)
 
     widget._start()
+
+
+def test_stats_plugin(make_napari_viewer_proxy):
+    view = make_napari_viewer_proxy()
+    widget = StatsUtils(view)
+
+    labels = rand_gen.random((10, 10, 10)).astype(np.uint8)
+    view.add_labels(labels, name="labels")
+
+    view.window.add_dock_widget(widget)
+    widget.csv_name.setText("test.csv")
+    widget._start()

napari_cellseg3d/_tests/test_review.py

@@ -10,10 +10,11 @@ def test_launch_review(make_napari_viewer_proxy):
     # widget.filetype_choice.setCurrentIndex(0)
 
     im_path = str(Path(__file__).resolve().parent / "res/test.tif")
+    lab_path = str(Path(__file__).resolve().parent / "res/test_labels.tif")
 
     widget.folder_choice.setChecked(True)
     widget.image_filewidget.text_field = im_path
-    widget.labels_filewidget.text_field = im_path
+    widget.labels_filewidget.text_field = lab_path
     widget.results_filewidget.text_field = str(
         Path(__file__).resolve().parent / "res"
     )