MICCAI 2021 Daily – Thursday

20 DAILY MICCAI Thursday MONAI Deploy Project MONAI is very excited to release the first version of the MONAI Deploy Application SDK that bridges the gap from innovative research to clinical production. The MONAI Deploy SDK offers a framework and associated tools to design, develop, and verify AI-driven applications in the healthcare imaging domain. Key features include: ● Flexible, extensible & usable Pythonic APIs to build healthcare imaging inference applications ● Easy management of inference applications via programmable Directed Acyclic Graphs ● Out-of-the-box support for in-proc PyTorch based inference ● Seamless integration with of MONAI based pre and post transformations in the inference application ● Locally run and debug your inference application using App Runner Jorge Cardoso , CTO at the London AI Centre for Value-Based Healthcare remarks, “ Until now, most AI models would remain in an R&D loop, rarely reaching patient care. MONAI Deploy will help break that loop, making clinical impactful AI a more frequent reality. ” Bennett Landman from Vanderbilt University shares, “ Reproducible assessment is essential for validation and trust in medical imaging AI. We commonly recognize that training AI algorithms is hard work, but, perhaps surprisingly, even running these procedures in a consistent manner has caused problems. We need community supported architecture and platforms to integrate AI into workflows and perform scalable validation. Project MONAI’s latest efforts with MONAI Deploy provide these essential capabilities and promise to more efficiently bring medical imaging AI to the communities who need it. ” MONAI Stream Project MONAI has extended beyond traditional radiological image tasks to pathology images and non-image patient data as well. At MICCAI 2021, we are pleased Medical Imaging Technology Fig 6.0: MONAI Deploy Application SDK Flow