home.md

 # Documentation
+Sonador is an open source platform for medical data and research. it helps researchers and developers solve clinical and scientific challegnes by providing tools to create real-time, secure, and scalable solutions.
 
 
 ## [What Is Sonador?](https://sonador.oak-tree.tech)
 <img align="right" src="uploads/img/sonador.platform-overview.svg">
 
-* Artificial Intelligence in Medical Imaging
-  - [AI in Medical Imaging, Part 1: Improving Diagnosis and Care](https://www.oak-tree.tech/articles/medical-ai-imaging01a). The promise of medical AI is a future where "the wisdom contained in the decisions made by nearly all clinicians and outcomes of billions of patients should inform the care of each patient." How do we get there?
-* [Digital Imaging and Communications in Medicine](https://www.dicomstandard.org/)
-  - [What Is DICOM?](https://www.oak-tree.tech/blog/dicom-primer) DICOM is a file format and network protocol used to store and transport medical images. All modern medical imaging systems such as x-ray, ultrasound, CT, and MRI use it for their data. This article provides an introduction to DICOM for software developers working with medical imaging resources within the Sonador imaging platform.
-* Components
-  - [Orthanc](https://www.orthanc-server.com/static.php?page=documentation). Orthanc is an open source, light-weight DICOMm server.
-  - [OHIF](https://ohif.org/). OHIF is an extensible web imaging platform to create custom DICOM viewers quickly and efficiently.
-  - [Slicer](https://www.slicer.org/). Sonador IO integrates with 3D Slicer to perform advanced biomedical image analysis. Using Slicer, it is possible to create segmentations for surgical planning, generate training sets for AI, or perform advanced simulation.
-  - [Airflow](https://airflow.apache.org/). Airflow is a platform to create, schedule, and monitor workflows. Airflow is used within the Sonador project for scheduling data pipelines, training machine learning models, and performing batch tasks on medical imaging data.
-* Integrations
-  - Python
-    + [Sonador IO](https://code.oak-tree.tech/oak-tree/medical-imaging/sonador-client). Sonador IO includes a Python software library for the Orthanc REST API which allows developers to work with imaging resoruces using an object-relational mapping (ORM) interface similar to those provided by the poular web development framework [Django](https://docs.djangoproject.com/en/4.0/topics/db/models/) or [SQLAlchemy](https://www.sqlalchemy.org/). This greatly simplifies the implementation of complex systems and allows for data stored in Orthanc to be integrated with popular Python libraries for machine learning, [Artificial Intelligence](https://pytorch.org/), and [3D processing](https://docs.pyvista.org/).
-    + [Medical Open Network for Artificial Intelligence](https://monai.io/index.html). MONAI is a collection of components and programs designed to build end-to-end AI systems based on medical imaging standards and best practices. Built on top of [PyTorch](https://pytorch.org/), MONAI provides a framework for multi-dimensional medical imaging pipelines; implementations of networks, losses, and evaluation metrics; and support for multi-GPU training.
-
-
-## Development
-* [Sonador Development Quickstart](https://www.oak-tree.tech/blog/sonador-quickstart). Sonador is an open source cloud platform for medical imaging visualization and research. This article shows you how to get started using the Sonador Development Environment.
+Artificial Intelligence in Medical Imaging
+* [AI in Medical Imaging, Part 1: Improving Diagnosis and Care](https://www.oak-tree.tech/articles/medical-ai-imaging01a). The promise of medical AI is a future where "the wisdom contained in the decisions made by nearly all clinicians and outcomes of billions of patients should inform the care of each patient." How do we get there?
+
+[Digital Imaging and Communications in Medicine](https://www.dicomstandard.org/)
+* [What Is DICOM?](https://www.oak-tree.tech/blog/dicom-primer) DICOM is a file format and network protocol used to store and transport medical images. All modern medical imaging systems such as x-ray, ultrasound, CT, and MRI use it for their data. This article provides an introduction to DICOM for software developers working with medical imaging resources within the Sonador imaging platform.
+
+**Components**
+* [Sonador Web Application]()
+* [Orthanc](https://www.orthanc-server.com/static.php?page=documentation). Orthanc is an open source, light-weight DICOMm server.
+* [OHIF](https://ohif.org/). OHIF is an extensible web imaging platform to create custom DICOM viewers quickly and efficiently.
+* [Slicer](https://www.slicer.org/). Sonador IO integrates with 3D Slicer to perform advanced biomedical image analysis. Using Slicer, it is possible to create segmentations for surgical planning, generate training sets for AI, or perform advanced simulation.
+* [Airflow](https://airflow.apache.org/). Airflow is a platform to create, schedule, and monitor workflows. Airflow is used within the Sonador project for scheduling data pipelines, training machine learning models, and performing batch tasks on medical imaging data.
+
+**Integrations**
+* Python
+  - [Sonador IO](https://code.oak-tree.tech/oak-tree/medical-imaging/sonador-client). Sonador IO includes a Python software library for the Orthanc REST API which allows developers to work with imaging resoruces using an object-relational mapping (ORM) interface similar to those provided by the poular web development framework [Django](https://docs.djangoproject.com/en/4.0/topics/db/models/) or [SQLAlchemy](https://www.sqlalchemy.org/). This greatly simplifies the implementation of complex systems and allows for data stored in Orthanc to be integrated with popular Python libraries for machine learning, [Artificial Intelligence](https://pytorch.org/), and [3D processing](https://docs.pyvista.org/).
+  - [Sonador AI](https://code.oak-tree.tech/oak-tree/medical-imaging/sonadorai). Sonador AI provides an end-to-end suite of tools and best practice guidance for medical imaging based machine learning. It includes a framework for implementing machine learning moels on top of [PyTorch](https://pytorch.org/), tools for creating annotated datasets, tracking experiments, and model versions, deploying to production, and integrating AI into clinical workflows.
+  - [Medical Open Network for Artificial Intelligence](https://monai.io/index.html). MONAI is a collection of components and programs designed to build end-to-end AI systems based on medical imaging standards and best practices. Built on top of [PyTorch](https://pytorch.org/), MONAI provides a framework for multi-dimensional medical imaging pipelines; implementations of networks, losses, and evaluation metrics; and support for multi-GPU training.
+  - [Sonador 3D](https://code.oak-tree.tech/oak-tree/medical-imaging/sonador3d). Sonador 3D provides tools for working with medical imaging and volumetric data from Sonador/Orthanc.
+* [MLflow](https://mlflow.org/). Within [Sonador AI](https://sonador.oak-tree.tech/ai), MLflow is used for tracking model training runs, managing models, hosting binary artifacts centrally to ease deployment, and coordinating MLOps workflows.
+* [JupyterLab](https://jupyter.org/). Sonador provides pre-built Docker images with JupyterLab and Python libraries which can be used to prototype complex workflows, visualize data, and document design decisions.
+
+
+
+## [Development](dev.index)
+[Sonador Development Quickstart](https://www.oak-tree.tech/blog/sonador-quickstart). Sonador is an open source cloud platform for medical imaging visualization and research. This article shows you how to get started using the Sonador Development Environment.
 * Frontend Development
   - [Configuring Sonador to Allow for Remote OHIF Development](https://www.oak-tree.tech/blog/sonador-ohif-config). While Sonador includes a version of OHIF integrated into the platform, it is also possible to configure it allow a remote OHIF instance.
 
 
-## Production
+
+
+## [Deployment](prod.deployment-guide)
 <img width="100%" src="uploads/img/sonador.production-deployment.svg">
 
 Cluster configuration: storage, networking, and other resources