Related Experiment Video
Updated: May 8, 2026
08:17
Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
Published on: June 7, 2015
15.7K
RadDeploy: A framework for integrating in-house developed software and artificial intelligence models seamlessly into
Mathis Ersted Rasmussen1,2,3, Casper Dueholm Vestergaard1,3, Jesper Folsted Kallehauge1
1Danish Centre for Particle Therapy, Aarhus University Hospital, Palle Juul-Jensens Boulevard 25, 8200 Aarhus N, Denmark.
Physics and Imaging in Radiation Oncology
|July 29, 2024
Summary
RadDeploy is a new framework enabling the integration of artificial intelligence (AI) software into clinical radiotherapy workflows. This platform facilitates the deployment of AI innovations beyond treatment planning systems, accelerating their clinical adoption.
Area of Science:
- Radiotherapy
- Medical Imaging
- Artificial Intelligence
Background:
- Automation and AI in radiotherapy are advancing rapidly.
- Clinical adoption of AI innovations is hindered by a lack of deployment platforms.
- Existing systems often lack flexibility for integrating novel software.
Purpose of the Study:
- Introduce RadDeploy, a framework for integrating containerized AI software into clinical workflows.
- Address the technical gap in deploying AI tools outside of traditional treatment planning systems.
- Demonstrate the utility and versatility of RadDeploy through practical use-cases.
Main Methods:
- Developed RadDeploy as a framework for containerized software integration.
- Enabled support for multiple DICOM inputs for AI model containers.
- Implemented asynchronous execution of model containers across GPUs and computers.
Main Results:
- RadDeploy successfully integrates containerized software into clinical workflows.
- The framework supports diverse DICOM inputs and distributed computing.
- Three use-cases of varying complexity demonstrate RadDeploy's capabilities.
Conclusions:
- RadDeploy provides a viable technical solution for deploying AI in radiotherapy.
- The framework enhances the integration of AI tools into clinical practice.
- Facilitates the translation of AI research into tangible clinical benefits.
