The Rhino Health Federated Computing Platform (FCP)

Welcome to the Rhino Health Federated Computing Platform (FCP) documentation! The Rhino Health FCP is a cutting-edge software platform designed specifically for distributed computing and federated learning in the healthcare domain. This powerful platform empowers data scientists working with sensitive healthcare data to collaborate securely and efficiently with partners from different institutions while ensuring privacy is preserved.

 

Key Features:

1. Dual User Interfaces

The Rhino Health FCP provides two user interfaces to cater to diverse user preferences. Users can choose between a user-friendly web-based graphical interface and a versatile Python library, both of which are built on top of the same robust backend API. This flexibility allows users to interact with the platform seamlessly according to their specific needs and expertise.

 

2. Privacy-Preserving Collaboration:

With Rhino Health FCP, data scientists can collaborate with external partners located at other institutions without compromising data security. Each participating institution installs a Rhino Health client on their premises, granting them secure access to their data. These clients communicate with the centralized Rhino Health server, acting as the orchestrating hub for distributed computing, ensuring data privacy remains intact within the hospital firewalls.

 

3. Data Accessibility Without Moving Data:

A significant advantage of the FCP is that users can make their data accessible to external collaborators through the platform without the need to move the data outside of their firewall. This data-sharing mechanism fosters efficient multi-institutional research collaborations while adhering to stringent data protection regulations.

 

4. Workflow Enablement:

The Rhino Health FCP is designed to empower users to build customized workflows on top of the platform. By leveraging container images, users can run their custom code on distributed data securely. These container images are uploaded to an online repository, and the Rhino Health server handles the orchestration of these containers across various participating sites.

 

Example Workflows:

The Rhino Health FCP has been instrumental in enabling several groundbreaking workflows within the healthcare domain. Some exemplary use cases include:

 

Data Preprocessing and Harmonization Pipelines for Distributed Registries

The FCP facilitates the seamless aggregation and preprocessing of distributed healthcare data across institutions, enhancing the efficiency and accuracy of distributed registry projects.

 

Distributed Data Annotation Workflows for Multi-Site Annotation Projects

Through federated learning capabilities, the FCP enables collaborative data annotation across multiple sites, aiding in large-scale multi-site annotation projects while maintaining data privacy.

 

Federated ML Model Training and Validation Pipelines

Data scientists can employ the FCP to fine-tune machine learning models using multi-site, distributed healthcare data. This capability ensures the development of robust models while keeping sensitive data securely within the respective institutions.

 

In this documentation, we will explore the Rhino Health FCP's capabilities, guide you through its setup and configuration, and provide comprehensive instructions to maximize your productivity and success in healthcare data collaborations. Let's get started on this exciting journey of secure and privacy-preserving distributed computing!

Was this article helpful?
3 out of 3 found this helpful

Articles in this section