RadDeploy: A framework for integrating in-house developed software and artificial intelligence models seamlessly into radiotherapy workflows

• Published in: Physics and imaging in radiation oncology 2024-07, Vol.31, p.100607, Article 100607
• Main Authors: Ersted Rasmussen, Mathis, Dueholm Vestergaard, Casper, Folsted Kallehauge, Jesper, Ren, Jintao, Haislund Guldberg, Maiken, Nørrevang, Ole, Vindelev Elstrøm, Ulrik, Sofia Korreman, Stine
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Container; DAG; Deploy; In-house; Radiotherapy
• ISSN: 2405-6316; 2405-6316
• DOI: 10.1016/j.phro.2024.100607

•RadDeploy is a deployment platform for in-house containerized software and AI-models.•RadDeploy offers a comprehensive DICOM-based triggering of flows.•Flows can have multiple DICOM series as input.•Flows can be designed as directed acyclic graphs of docker containers.•RadDeploy scales across multiple GPUs and computers. The use of and research in automation and artificial intelligence (AI) in radiotherapy is moving with incredible pace. Many innovations do, however, not make it into the clinic. One technical reason for this may be the lack of a platform to deploy such software into clinical practice. We suggest RadDeploy as a framework for integrating containerized software in clinical workflows outside of treatment planning systems. RadDeploy supports multiple DICOM as input for model containers and can run model containers asynchronously across GPUs and computers. This technical note summarizes the inner workings of RadDeploy and demonstrates three use-cases with varying complexity.