Edit documentation

docs2/api.rst

@@ -1,70 +1,5 @@
-NiChart\_DLMUSE source code
+Developers - API
 ===========================
 
 Submodules
 ----------
-
-DLMUSE pipeline
---------------------------------------------
-
-.. automodule:: NiChart_DLMUSE.dlmuse_pipeline
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Calculate ROI Volume module
------------------------------------------
-
-.. automodule:: NiChart_DLMUSE.CalcROIVol
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-
-Mask Image
---------------------------------
-
-.. automodule:: NiChart_DLMUSE.MaskImage
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Relabel ROI
---------------------------------
-
-.. automodule:: NiChart_DLMUSE.RelabelROI
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Reorient Image
-------------------------------------------
-
-.. automodule:: NiChart_DLMUSE.ReorientImage
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Segment Image
----------------------------------------------
-
-.. automodule:: NiChart_DLMUSE.SegmentImage
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-util functions
-----------------------------
-
-.. automodule:: NiChart_DLMUSE.utils
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-Module contents
----------------
-
-.. automodule:: NiChart_DLMUSE
-   :members:
-   :undoc-members:
-   :show-inheritance:

docs2/components.rst

@@ -0,0 +1,35 @@
+##########
+Components
+##########
+
+NiChart is designed as a framework that integrates independent image processing and analysis pipelines. The following sections describe NiChart pipelines.
+
+*****************
+Active Pipelines
+*****************
+
+These pipelines are currently active and running within the NiChart Project
+
+------------------------------------
+A1. sMRI Biomarkers of Disease and Aging
+------------------------------------
+
+Neuroimaging pipeline for computing AI biomarkers of disease and aging from T1-weighted MRI scans
+
+----------------------
+A2. WM Lesion Segmentation
+----------------------
+
+****************
+Work in Progress
+****************
+
+These pipelines will be integrated into NiChart Project in the next releases
+
+------------------------------------
+B1. DTI Biomarkers of Disease and Aging
+------------------------------------
+
+------------------------------------
+B2. fMRI Biomarkers of Disease and Aging
+------------------------------------

docs2/help.rst

@@ -2,7 +2,7 @@
 Getting help
 ############
 
-If you have a problem or would like to ask a question about the inner workings of **NiChart DLMUSE** you can directly
+If you have a question about **NiChart Project** you can directly
 message our maintaners via email.
 
 .. note::

docs2/index.rst

@@ -9,6 +9,8 @@ Contents
 
    installation
    usage
+   components
    contributors
    api
    help
+   license

docs2/installation.rst

@@ -2,16 +2,48 @@
 Installation
 ############
 
-To install **NiChart Project** with pip, just do: ::
+Users can install **NiChart Project** with pip: ::
 
-    $ pip install NiChart_Project
+    pip install NiChart_Project
 
-We always have our latest stable version on PyPI, so we highly suggest you to install it this way.
+Alternatively, the package can be installed from source: ::
 
-You can manually build the package from source by running: ::
+    git clone https://github.com/CBICA/NiChart_Project
+    cd NiChart_Project && python3 -m pip install -e .
 
-    $ git clone https://github.com/CBICA/NiChart_Project
+We release our latest stable version on PyPI; accordingly, **we strongly recommend pip installation**.
+
+.. warning::
+    PyTorch and NumPy have known compatibility issues across different platforms. To avoid potential conflicts, please follow the installation instructions below.
+
+- After installing all other necessary packages, uninstall any existing Torch installations:   
+
+   $ pip uninstall torch
+
+- Reinstall PyTorch:
+
+    - **Linux:** PyTorch version 2.3.1
+    - **Windows:** PyTorch version 2.5.1
+
+- Users can select the correct index URL for their CUDA version based on the `PyTorch getting started page <https://pytorch.org/get-started/locally>`
+
+**Example on a Linux x86 system:**
+
+    $ pip install torch==2.3.1 --index-url https://download.pytorch.org/whl/cu121
+
+*************************
+Managing your environment
+*************************
+
+We recommend installing NiChart Project within a dedicated environment. Users can create an environment using Mamba (please see `Mamba Installation Guide <https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html>`).
+
+**Example on a Linux x86 system:** ::
+
+    wget https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-Linux-x86_64.sh
+    bash Mambaforge-Linux-x86_64.sh
+    mamba create -c conda-forge -c bioconda -n NCP_env python=3.12 
+    mamba activate NCP_env
+    git clone https://github.com/CBICA/NiChart_Project.git
+    pip install -r requirements.txt
 
-    $ cd NiChart_Project && python3 -m pip install -e .
 
-We **do not** recomment installing the package directly from source as the repository is under development and this can cause crashes and bugs.

docs2/license.rst

@@ -0,0 +1,5 @@
+#######
+License
+#######
+
+NiChart application, web site, the content and the logo of NiChart are intellectual property of CBICA, UPENN. For details, please see `the licence <https://github.com/CBICA/NiChart_Project/blob/main/LICENSE>`.

docs2/modules.rst

@@ -1,7 +1,7 @@
-NiChart_DLMUSE
+NiChart_Project
 ==============
 
 .. toctree::
-   :maxdepth: 4
+   :maxdepth: 2
 
-   NiChart_DLMUSE
+   NiChart_Project

docs2/usage.rst

@@ -1,74 +1,27 @@
-#####
-Usage
-#####
-
-Pre-trained nnUNet models for the skull-stripping can be found in `HuggingFace nichart/DLICV <https://huggingface.co/nichart/DLICV/tree/main>`_ and
-segmentation tasks can be found in `HuggingFace nichart/DLMUSE <https://huggingface.co/nichart/DLMUSE/tree/main>`_. Feel free to use it under the package's license.
-
-*********
-Using CLI
-*********
-
-Our CLI is simply to use as it just takes 2 required parameters: ::
-
-    $ NiChart_DLMUSE -i <input path> -o <output path>
-
-By default, our CLI runs on CPU. You can run it on GPU with CUDA or MPS just by specifying the device: ::
+###########
+Quick Start
+###########
 
-    $ NiChart_DLMUSE -i <input path> -o <output path> -d cuda
+*******
+Desktop
+*******
 
+The following steps describe how to run NiChart after installation: ::
 
+    $ cd src/viewer
+    $ streamlit run NiChartProject.py
+    
 .. note::
+    The app will start running at http://localhost:8501. If your browser doesn't automatically open, please copy and paste this address into your browser. 
 
-    **MPS** Can be used if your chip supports 3d convolution(M1 chips do not support 3d convolution, thus, you can't use MPS with M1 macbooks)
-
-
-We use batch splitting and paralellization to accelerate the procedure. By default, we split the input data into
-4 subfolders. You can specify the number of subfolders with the ``-c`` or ``--cores`` option: ::
-
-    $ NiChart_DLMUSE ... -c 6
-
-This will create 6 subfolders instead of the default 4.
-
-We also support ``BIDS`` I/O in our latest stable release. In order to run NiChart DLMUSE with a BIDS folder as the input you
-need to have one T1 image under the anat subfolder. After the run NiChart DLMUSE will return the segmented images in the same
-subfolders. If you have a `BIDS` input folder you have to specify it at the CLI command: ::
+*****
+Cloud
+*****
 
-    $ NiChart_DLMUSE ... --bids 1
+The cloud app can be launched at https://cloud.neuroimagingchart.com . Users need to create an account to access the cloud app.
 
-For further explanation please refer to the complete CLI documentation: ::
-
-    $ NiChart_DLMUSE -h
-
-
-**************************
-Using the docker container
-**************************
-
-Using the file structure explained above, an example command using the `docker container <https://hub.docker.com/r/cbica/nichart_dlmuse/tags>`_
-is the following: ::
-
-    # For GPU
-    $ CUDA_VERSION=11.8 docker pull cbica/nichart_dlmuse:1.0.1-cuda${CUDA_VERSION}
-
-    # For CPU
-    docker pull cbica/nichart_dlmuse:1.0.4-default
-
-    $ # Run the container with proper mounts, GPU enabled
-      # Place input in /path/to/input/on/host.
-      # Replace "-d cuda" with "-d mps" or "-d cpu" as needed...
-      # or don't pass at all to automatically use CPU.
-      # Each "/path/to/.../on/host" is a placeholder, use your actual paths!
-      docker run -it --name DLMUSE_inference --rm
-          --mount type=bind,source=/path/to/input/on/host,target=/input,readonly
-          --mount type=bind,source=/path/to/output/on/host,target=/output
-          --gpus all cbica/nichart_dlmuse -d cuda
-
-
-*******************************
-Using the singularity container
-*******************************
-
-We do not recommend using the singularity container as is currently outdated and not maintaned: ::
+*****
+Usage
+*****
 
-    $ singularity run --nv --containall --bind /path/to/.\:/workspace/ nichart_dlmuse.simg NiChart_DLMUSE -i /workspace/temp/nnUNet_raw_data_base/nnUNet_raw_data/ -o /workspace/temp/nnUNet_out -p structural --derived_ROI_mappings_file /NiChart_DLMUSE/shared/dicts/MUSE_mapping_derived_rois.csv --MUSE_ROI_mappings_file /NiChart_DLMUSE/shared/dicts/MUSE_mapping_consecutive_indices.csv --nnUNet_raw_data_base /workspace/temp/nnUNet_raw_data_base/ --nnUNet_preprocessed /workspace/temp/nnUNet_preprocessed/ --model_folder /workspace/temp/nnUNet_model/ --all_in_gpu True --mode fastest --disable_tta
+After launching the application, users can select a pipeline and apply it to their data. For detailed instructions on each pipeline, please refer to the **Overview** and **Tutorial** pages accessible from the left-hand menu.