Deprecate apps (#700)

* Deprecate Apps Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Fix/add tests Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Add deepedit sample app for backward version support (docs) Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Deprecate Apps Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Deprecate Apps Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Fix readme + disable auto trigger for train Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Fix readme++ Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> * Fix readme++ Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com>
Project-MONAI · Mar 22, 2022 · 823398e · 823398e
1 parent f440212
commit 823398e
Show file tree

Hide file tree

Showing 98 changed files with 482 additions and 3,779 deletions.
diff --git a/README.md b/README.md
@@ -9,8 +9,9 @@
 [![codecov](https://codecov.io/gh/Project-MONAI/MONAILabel/branch/main/graph/badge.svg)](https://codecov.io/gh/Project-MONAI/MONAILabel)
 
 MONAI Label is a server-client system that facilitates interactive medical image annotation by using AI. It is an
-open-source and easy-to-install ecosystem that can run locally on a machine with single or multiple GPUs. Both server and client
-work on the same/different machine. It shares the same principles with [MONAI](https://github.com/Project-MONAI).
+open-source and easy-to-install ecosystem that can run locally on a machine with single or multiple GPUs. Both server
+and client work on the same/different machine. It shares the same principles
+with [MONAI](https://github.com/Project-MONAI).
 
 [MONAI Label Demo](https://youtu.be/o8HipCgSZIw?t=1319)
 
@@ -23,7 +24,7 @@ work on the same/different machine. It shares the same principles with [MONAI](h
 - Framework for developing and deploying MONAI Label Apps to train and infer AI models
 - Compositional & portable APIs for ease of integration in existing workflows
 - Customizable labelling app design for varying user expertise
-- Annotation support via 3DSlicer & OHIF 
+- Annotation support via 3DSlicer & OHIF
 - PACS connectivity via DICOMWeb
 
 ## Installation
@@ -33,27 +34,55 @@ MONAI Label supports following OS with **GPU/CUDA** enabled.
 - Ubuntu
 - [Windows](https://docs.monai.io/projects/label/en/latest/installation.html#windows)
 
+### Development Release
+
+To install the _**latest features**_ using one of the following options:
+```bash
+# option 1: github install (or you can install monailabel-weekly from PyPI)
+pip install git+https://github.com/Project-MONAI/MONAILabel#egg=monailabel
+
+# option 2: using docker
+docker run --gpus all --rm -ti --ipc=host --net=host projectmonai/monailabel:latest
+
+# option 2: git checkout
+git clone https://github.com/Project-MONAI/MONAILabel
+pip install -r MONAILabel/requirements.txt
+export PATH=$PATH:`pwd`/MONAILabel/monailabel/scripts
+
+
+# download radiology app and sample dataset
+monailabel apps --download --name radiology --output apps
+monailabel datasets --download --name Task09_Spleen --output datasets
+
+# start server using radiology app with deepedit model enabled
+monailabel start_server --app apps/radiology --studies datasets/Task09_Spleen/imagesTr --conf models deepedit
+```
+
+### Current Release (3.x)
+
 To install the [current release](https://pypi.org/project/monailabel/), you can simply run:
 
 ```bash
-  pip install monailabel
-
-  # download sample apps/dataset
-  monailabel apps --download --name deepedit --output apps
-  monailabel datasets --download --name Task09_Spleen --output datasets
-
-  # run server
-  monailabel start_server --app apps/deepedit --studies datasets/Task09_Spleen/imagesTr
+pip install monailabel
+
+monailabel apps --download --name deepedit --output apps
+monailabel datasets --download --name Task09_Spleen --output datasets
+
+monailabel start_server --app apps/deepedit --studies datasets/Task09_Spleen/imagesTr
 ```
 
-> If monailabel install path is not automatically determined, then you can provide explicit install path as: 
-> 
+More details refer docs: https://docs.monai.io/projects/label/en/stable/installation.html
+
+
+
+> If monailabel install path is not automatically determined, then you can provide explicit install path as:
+>
 > `monailabel apps --prefix ~/.local`
 
 For **_prerequisites_**, other installation methods (using the default GitHub branch, using Docker, etc.), please refer
 to the [installation guide](https://docs.monai.io/projects/label/en/latest/installation.html).
 
-> Once you start the MONAI Label Server, by default server will be up and serving at http://127.0.0.1:8000/. Open the serving URL in browser. It will provide you the list of Rest APIs available. **For this, please make sure you use the HTTP protocol. HTTPS is not implemented.**
+> Once you start the MONAI Label Server, by default server will be up and serving at http://127.0.0.1:8000/. Open the serving URL in browser. It will provide you the list of Rest APIs available. **For this, please make sure you use the HTTP protocol.** _You can provide ssl arguments to run server in HTTPS mode but this functionality is not fully verified._
 
 ### 3D Slicer
 
@@ -65,15 +94,16 @@ Refer [3D Slicer plugin](plugins/slicer) for other options to install and run MO
 
 ### OHIF
 
-MONAI Label comes with [pre-built plugin](plugins/ohif) for [OHIF Viewer](https://github.com/OHIF/Viewers).  To use OHIF Viewer, you need to provide DICOMWeb instead of FileSystem as _studies_ when you start the server.
+MONAI Label comes with [pre-built plugin](plugins/ohif) for [OHIF Viewer](https://github.com/OHIF/Viewers). To use OHIF
+Viewer, you need to provide DICOMWeb instead of FileSystem as _studies_ when you start the server.
 > Please install [Orthanc](https://www.orthanc-server.com/download.php) before using OHIF Viewer.
 > For Ubuntu 20.x, Orthanc can be installed as `apt-get install orthanc orthanc-dicomweb`. However, you have to **upgrade to latest version** by following steps mentioned [here](https://book.orthanc-server.com/users/debian-packages.html#replacing-the-package-from-the-service-by-the-lsb-binaries)
 >
 > You can use [PlastiMatch](https://plastimatch.org/plastimatch.html#plastimatch-convert) to convert NIFTI to DICOM
 
 ```bash
   # start server using DICOMWeb
-  monailabel start_server --app apps\deepedit --studies http://127.0.0.1:8042/dicom-web
+  monailabel start_server --app apps/radiology --studies http://127.0.0.1:8042/dicom-web
 ```
 
 > OHIF Viewer will be accessible at http://127.0.0.1:8000/ohif/
@@ -83,12 +113,12 @@ MONAI Label comes with [pre-built plugin](plugins/ohif) for [OHIF Viewer](https:
 > **_NOTE:_** OHIF does not yet support Multi-Label interaction for DeepEdit.
 
 ### Pathology using [Digital Slide Archive (DSA)](https://digitalslidearchive.github.io/digital_slide_archive/)
+
 Refer [Pathology](sample-apps/pathology) for running a sample pathology use-case in MONAILabel.
 > **_NOTE:_** The **Pathology App** and *DSA Plugin* are under *active development*.
 
 ![image](https://user-images.githubusercontent.com/7339051/157100606-a281e038-5923-43a8-bb82-8fccae51fcff.png)
 
-
 ## Contributing
 
 For guidance on making a contribution to MONAI Label, see the [contributing guidelines](CONTRIBUTING.md).

diff --git a/docs/source/apis.rst b/docs/source/apis.rst
@@ -61,6 +61,17 @@ Utils
     :noindex:
 
 
+Client
+======
+
+.. currentmodule:: monailabel.client.client
+.. autoclass:: MONAILabelClient
+    :members:
+    :noindex:
+.. autoclass:: MONAILabelError
+    :members:
+    :noindex:
+
 Modules
 =======
 

diff --git a/docs/source/appdeployment.rst b/docs/source/appdeployment.rst
@@ -14,10 +14,10 @@ The MONAI Label Server endpoints are available at startup. The user may download
 .. code-block:: bash
 
   # download a sample app
-  monailabel apps --name deepedit --download --output .
+  monailabel apps --name radiology --download --output .
 
   # start the sample app locally
-  monailabel start_server --app deepedit --studies <path/to/datastore>
+  monailabel start_server --app radiology --studies <path/to/datastore> --conf models (deepedit|deepgrow|segmentation|segmentation_speen|all)
 
 and navigate to `http://127.0.0.1:8000/ <http://127.0.0.1:8000/>`_ on the browser (if the server
 is running on the local machine). The user may choose to use the web UI to invoke the various endpoints

diff --git a/docs/source/installation.rst b/docs/source/installation.rst
@@ -83,7 +83,7 @@ You can download sample apps and datasets from *monailabel* CLI.
 
   # Download Sample Apps
   monailabel apps # List sample apps
-  monailabel apps --download --name deepedit --output apps
+  monailabel apps --download --name radiology --output apps
 
   # Download MSD Datasets
   monailabel datasets # List sample datasets
@@ -95,7 +95,11 @@ Starting Server
 You can start server using *monailabel* CLI
 ::
 
-  monailabel start_server --app apps/deepedit --studies datasets/Task09_Spleen/imagesTr
+  # Run Deepedit Model.
+  # Options can be (deepedit|deepgrow|segmentation|segmentation_spleen|all) in case of radiology app.
+  # You can also pass comma seperated models like --conf models deepedit,segmentation
+
+  monailabel start_server --app apps/radiology --studies datasets/Task09_Spleen/imagesTr --conf models deepedit
 
 
 .. note::
@@ -115,14 +119,14 @@ Deploying MONAI Label server for production use is out of project scope.  Howeve
 ::
 
   # dryrun the MONAI Label CLI for pre-init and dump the env variables to .env or env.bat
-  monailabel start_server --app apps/deepedit --studies datasets/Task09_Spleen/imagesTr --host 0.0.0.0 --port 8000 --dryrun
+  monailabel start_server --app apps/radiology --studies datasets/Task09_Spleen/imagesTr --host 0.0.0.0 --port 8000 --dryrun
 
   # Linux/Ubuntu
   source .env
   uvicorn monailabel.app:app \
     --host 0.0.0.0 \
     --port 8000 \
-    --log-config apps/deepedit/logs/logging.json \
+    --log-config apps/radiology/logs/logging.json \
     --no-access-log
 
 
@@ -131,7 +135,7 @@ Deploying MONAI Label server for production use is out of project scope.  Howeve
   uvicorn monailabel.app:app ^
     --host 0.0.0.0 ^
     --port 8000 ^
-    --log-config apps\deepedit\logs\logging.json ^
+    --log-config apps\radiology\logs\logging.json ^
     --no-access-log
 
 
@@ -153,7 +157,7 @@ MONAI Label comes with `pre-built plugin <https://github.com/Project-MONAI/MONAI
 
 ::
 
-  monailabel start_server --app apps/deepedit --studies http://127.0.0.1:8042/dicom-web
+  monailabel start_server --app apps/radiology --studies http://127.0.0.1:8042/dicom-web --conf models deepedit
 
 
 If you have authentication set for dicom-web then you can pass the credentials using environment `variables <https://github.com/Project-MONAI/MONAILabel/blob/main/monailabel/config.py>`_ while running the server.
@@ -162,7 +166,7 @@ If you have authentication set for dicom-web then you can pass the credentials u
 
   export MONAI_LABEL_DICOMWEB_USERNAME=xyz
   export MONAI_LABEL_DICOMWEB_PASSWORD=abc
-  monailabel start_server --app apps/deepedit --studies http://127.0.0.1:8042/dicom-web
+  monailabel start_server --app apps/radiology --studies http://127.0.0.1:8042/dicom-web --conf models deepedit
 
 
 .. note::

diff --git a/docs/source/modules.rst b/docs/source/modules.rst
@@ -37,17 +37,16 @@ MONAI Label currently provides three template applications which developers
 may start using out of the box, or with few modifications to achieve the desired 
 behavior. Template applications currently available are
 
-- `Automated Segmentation <LINKREF_GITHUB_MONAILABEL/sample-apps/segmentation>`_
-- `DeepGrow AI Annotation <LINKREF_GITHUB_MONAILABEL/sample-apps/deepgrow>`_
-- `DeepEdit AI Annotation <LINKREF_GITHUB_MONAILABEL/sample-apps/deepedit>`_
+- `radiology <LINKREF_GITHUB_MONAILABEL/sample-apps/radiology>`_
+- `pathology <LINKREF_GITHUB_MONAILABEL/sample-apps/pathology>`_
 
 For a quickstart the developer may use
 
 .. code-block:: bash
 
   monailabel apps --name <desired_app> --download --output myapp
 
-where ``desired_app`` may be any of ``segmentation``, ``deepgrow``, or ``deepedit``.
+where ``desired_app`` may be any of ``pathology``, ``radiology``.
 
 To better understand template apps, the next few sections we will go into the details of implementing
 
@@ -71,8 +70,7 @@ discretization.
   :emphasize-lines: 7, 9, 15, 18
 
   from monai.inferers import SimpleInferer
-  from monai.transforms import (LoadImaged, ToNumpyd, Activationsd
-                                AsDiscreted, ToNumpyd)
+  from monai.transforms import (LoadImaged, ToNumpyd, Activationsd AsDiscreted, ToNumpyd)
 
   from monailabel.interfaces.tasks import InferTask
 

diff --git a/docs/source/quickstart.rst b/docs/source/quickstart.rst
@@ -2,7 +2,10 @@
 Quickstart
 ==========
 
-MONAI Label server currently supports the annotation of local datasets via `3DSlicer <https://www.slicer.org/>`_, such as unlabeled images 
+Use Case - Radiology
+====================
+
+This example covers the annotation use-case for radiology using the sample MONAILabel App - **radiology**.  MONAI Label server currently supports the annotation of local datasets via `3DSlicer <https://www.slicer.org/>`_, such as unlabeled images
 residing on disk, and remote data residing on DICOMweb-enabled PACS systems via both `3DSlicer <https://www.slicer.org/>`_ and `OHIF <https://ohif.org/>`_.
 
   * To setup a local dataset for annotation follow the instructions under :ref:`DeepEdit Annotation with 3DSlicer`.
@@ -13,29 +16,29 @@ residing on disk, and remote data residing on DICOMweb-enabled PACS systems via
 DeepEdit Annotation with 3DSlicer
 =================================
 
-.. _Deploy DeepEdit on MONAI Label Server:
+.. _Deploy MONAI Label Server:
 
-Deploy DeepEdit on MONAI Label Server
--------------------------------------
+Deploy MONAI Label Server
+-------------------------
 
 On the local machine follow the commands listed below to install MONAI Label, download
-a sample application (DeepEdit left atrium annotation), download a sample dataset (MSD
+a sample application (Radiology), download a sample dataset (MSD
 heart MRI), and deploy the sample app and standard dataset on the MONAI Label server.
 
 .. code-block:: bash
   
   # install MONAI Label
   pip install monailabel
 
-  # download DeepEdit sample app to local directory
-  monailabel apps --name deepedit --download --output .
+  # download Radiology sample app to local directory
+  monailabel apps --name radiology --download --output .
 
   # download Task 2 MSD dataset
-  monailabel datasets --download --name Task02_Heart --output .
+  monailabel datasets --download --name Task09_Spleen --output .
   
-  # start the DeepEdit app in MONAI label server
-  # and start annotating the downloaded images
-  monailabel start_server --app deepedit --studies Task02_Heart/imagesTr
+  # start the Radiology app in MONAI label server
+  # and start annotating the downloaded images using deepedit model
+  monailabel start_server --app radiology --studies Task09_Spleen/imagesTr --conf models deepedit
 
 
 Install MONAI Label Plugin in 3DSlicer
@@ -126,7 +129,7 @@ label storage location.
   
   # start the DeepEdit app in MONAI label server
   # on the empty dataset folder
-  monailabel start_server --app deepedit --studies my_dataset
+  monailabel start_server --app radiology --studies my_dataset --conf models deepedit
 
 We can follow the instructions in the previous section to install and connect 3DSlicer to MONAI
 Label Server, however, in this scenario we will instead load a file into MONAI Label Server *through*
@@ -153,7 +156,7 @@ the ``username`` and ``password`` for DICOM servers that require them).
 
 If you do not have a DICOM server available for usage but would like to set one up please follow the instructions in the 
 :ref:`next section<Setup Development DICOM Server>`, otherwise skip to 
-:ref:`Deploy DeepEdit for PACS Data Annotation`.
+:ref:`Deploy for PACS Data Annotation`.
 
 .. _Setup Development DICOM Server:
 
@@ -223,21 +226,21 @@ If you do not have access to DICOM data to upload to the DICOM server you can co
   sudo apt-get install plastimatch -y
 
   # download Task 2 MSD dataset
-  monailabel datasets --download --name Task02_Heart --output .
+  monailabel datasets --download --name Task09_Spleen --output .
 
   # convert one of the NIFTI images to DICOM
-  plastimatch convert --patient-id patient1 --input Task02_Heart/imagesTs/la_001.nii.gz --output-dicom la_001_dicom
+  plastimatch convert --patient-id patient1 --input Task09_Spleen/imagesTs/spleen_10.nii.gz --output-dicom dicom_output
 
-Now, we can upload the DICOM series in ``la_001_dicom`` using the `upload <http://127.0.0.1:8042/app/explorer.html#upload>`_ link in Orthanc.
+Now, we can upload the DICOM series in ``dicom_output`` using the `upload <http://127.0.0.1:8042/app/explorer.html#upload>`_ link in Orthanc.
 
 You may use ``plastimatch`` to convert more NIFTI files to DICOM to keep populating the development DICOM server.
 
-.. _Deploy DeepEdit for PACS Data Annotation:
+.. _Deploy for PACS Data Annotation:
 
 DeepEdit Annotation in OHIF
 ---------------------------
 
-We follow a very similar ser of commands as in :ref:`Deploy DeepEdit on MONAI Label Server`, however, we use the DICOMweb
+We follow a very similar set of commands as in :ref:`Deploy MONAI Label Server`, however, we use the DICOMweb
 endpoint of our DICOM server, which based on the last section is ``http://locahost:8042/dicom-web``.
 
 .. code-block:: bash
@@ -246,11 +249,11 @@ endpoint of our DICOM server, which based on the last section is ``http://locaho
   pip install monailabel
 
   # download DeepEdit sample app to local directory
-  monailabel apps --name deepedit --download --output .
+  monailabel apps --name radiology --download --output .
 
   # start the DeepEdit app in MONAI label server
   # and start annotating images in our DICOM server
-  monailabel start_server --app deepedit --studies http://locahost:8042/dicom-web --username orthanc --password orthanc
+  monailabel start_server --app radiology --studies http://locahost:8042/dicom-web --conf models deepedit --username orthanc --password orthanc
 
 
 At this point OHIF can be used to annotate the data in the DICOM server via the MONAI Label server ``/ohif`` endpoint