
Truveta
Saving lives with data by providing regulatory-grade safety and effectiveness data.

The industry-standard open-source medical imaging platform for web-based DICOM visualization and AI-assisted workflows.

The OHIF Framework is a robust, production-ready, open-source medical imaging platform built with React and the Cornerstone.js library. In 2026, it stands as the foundational architecture for modern web-based DICOM visualization, utilized by both academic researchers and commercial OEM vendors to build custom PACS and RIS solutions. The viewer leverages high-performance rendering engines like VTK.js for 3D volume rendering and multi-planar reformatting (MPR). Its highly modular extension system allows for the seamless integration of AI inferencing, enabling clinicians to visualize segmentations, bounding boxes, and heatmaps directly in the browser. Technically, OHIF adheres to DICOMweb standards (QIDO-RS, WADO-RS, STOW-RS), ensuring interoperability with cloud-native storage solutions such as Google Cloud Healthcare API and AWS HealthImaging. Its architecture is designed for scalability, supporting high-throughput clinical environments while maintaining a zero-footprint web client, eliminating the need for local software installation and facilitating secure, cross-platform access for telemedicine and clinical research.
The OHIF Framework is a robust, production-ready, open-source medical imaging platform built with React and the Cornerstone.
Explore all tools that specialize in 3d volume rendering. This domain focus ensures OHIF Viewer delivers optimized results for this specific requirement.
Allows developers to add new data sources, UI components, and modes without altering the core codebase.
Real-time reconstruction of 2D slices from 3D volumes across axial, sagittal, and coronal planes.
Full support for RESTful DICOM services including WADO-RS for image retrieval.
Pre-built components for displaying AI-generated segmentations (DICOM-SEG) and structured reports (DICOM-SR).
Programmable logic to automatically arrange images and series on the screen based on metadata.
GPU-accelerated rendering engine for heavy medical datasets within the browser context.
Leverages SharedArrayBuffer for high-speed multi-threaded image decoding.
Clone the official OHIF/Viewers repository from GitHub.
Install Node.js version 18.x or higher and Yarn package manager.
Run 'yarn install' to install dependencies across the monorepo.
Configure the 'default.js' config file to point to your DICOMweb server (e.g., Orthanc or dcm4chee).
Define your Study List and Viewer extensions in the app config.
Execute 'yarn run dev' to launch the development server on localhost:3000.
Validate connectivity using a QIDO-RS request to fetch study metadata.
Customize the UI theme and toolbars using the React-based component library.
Build the production-ready static assets using 'yarn run build'.
Deploy the build folder to an NGINX or S3-backed hosting environment.
All Set
Ready to go
Verified feedback from other users.
"Highly praised for its extensibility and compliance with standards, though the learning curve for configuration can be steep for non-developers."
Post questions, share tips, and help other users.

Saving lives with data by providing regulatory-grade safety and effectiveness data.

Breast AI trusted for better workflow and higher confidence in mammography screening.

Assistive communication solutions for people with disabilities.

Turn your diabetes data points into accessible, actionable, and meaningful insights.

Science-backed supplements for personalized wellness.

Hear everything in a heartbeat with advanced digital stethoscope technology.