MICCAI 2021 Daily – Thursday

• MONAI Deploy v0.1 is the very first release of the MONAI Deploy App SDK. It allows users to create complete inference applications from trained MONAI models within minutes. • MONAI Stream is being announced as a work-in-progress library that enables rapid research prototyping for real-time imaging analysis and computer-assisted interventions. MONAI Label MONAI Label version 0.2 enables the AI assisted annotation of medical image data from remote DICOMweb-enabled PACS systems, via both 3D Slicer and OHIF . Additionally, technical previews for 2 new active learning strategies are introduced, which power a more efficient labeling workflow by predicting the next data to be annotated by the user instead of randomly selecting the next data. When starting a MONAI Label server, the user simply needs to specify the URL of the DICOMweb server that is hosting the studies. DICOMweb servers that require password-based user authentication are also supported. Learn More. After your data has been annotated with MONAI Label, you will have labeled data to build your AI model. If further training is desired or your data is already annotated, Project MONAI’s flagship library is an outstanding healthcare imaging-specialized solution. Matthew Jolley , MD at Children’s Hospital of Philadelphia (CHOP) perfectly articulates the need for close collaboration amongst researchers and clinicians with MONAI Label. “ Open-source frameworks like Project MONAI provide a standardized, transparent, and reproducible template for the creation of, and deployment of medical imaged-focused machine learning models, potentiating efforts such as ours. They allow us to focus on investigating novel algorithms and their application, rather than developing and maintaining software infrastructure. This in turn has accelerated research progress which we are actively translating into tools of practical relevance to the pediatric community we serve . ” 17 DAILY MICCAI Thursday Monai Fig 1 - Project MONAI tools for development and deployment of AI-powered algorithms and applications

RkJQdWJsaXNoZXIy NTc3NzU=