MONAI Imaging Framework Fast-Tracked to Production to Accelerate AI in Healthcare

DKFZ, King’s College London, Mass General, NVIDIA, Stanford and Vanderbilt adopt MONAI open-source AI framework for imaging.
by Raghav Mani

MONAI — the Medical Open Network for AI, a domain-optimized, open-source framework for healthcare — is now ready for production with the upcoming release of the NVIDIA Clara application framework for AI-powered healthcare and life sciences.

Introduced in April and already adopted by leading healthcare research institutions, MONAI is a PyTorch-based framework that enables the development of AI for medical imaging with industry-specific data handling, high-performance training workflows and reproducible reference implementations of state-of-the-art approaches.

As part of the updated Clara offering, MONAI will come with over 20 pre-trained models, including ones recently developed for COVID-19, as well as the latest training optimizations on NVIDIA DGX A100 GPUs that provide up to a sixfold acceleration in training turnaround time.

“MONAI is becoming the PyTorch of healthcare, paving the way for closer collaboration between data scientists and clinicians,” said Dr. Jayashree Kalpathy-Cramer, director of the QTIM lab at the Athinoula A. Martinos Center for Biomedical Imaging at MGH. “Global adoption of MONAI is fostering collaboration across the globe facilitated by federated learning.”

Adoption by the healthcare ecosystem of MONAI has been tremendous. DKFZ, King’s College London, Mass General, Stanford and Vanderbilt are among those to adopt the AI framework for imaging. MONAI is being used in everything from industry-leading imaging competitions to the first boot camp focused on the framework, held in September, which drew over 550 registrants from 40 countries, including undergraduate university students.

“MONAI is quickly becoming the go-to deep learning framework for healthcare. Getting from research to production is critical for the integration of AI applications into clinical care,” said Dr. Bennett Landman of Vanderbilt University. “NVIDIA’s commitment to community-driven science and allowing the academic community to contribute to a framework that is production-ready will allow for further innovation to build enterprise-ready features.”

New Features

NVIDIA Clara brings the latest breakthroughs in AI-assisted annotation, federated learning and production deployment to the MONAI community.

The latest version introduces a game-changer to AI-assisted annotation that allows radiologists to label complex 3D CT data in one-tenth of the clicks with a new model called DeepGrow 3D. Instead of the traditional time-consuming method of segmenting an organ or lesion image by image or slice by slice, which can be up to 250 clicks for a large organ like the liver, users can segment with far fewer clicks.

Integrated with Fovia Ai’s F.A.S.T. AI Annotation software, NVIDIA Clara’s AI-assisted annotation tools and the new DeepGrow 3D feature can be used for labeling training data as well as assisting radiologists when reading. Fovia offers the XStream HDVR SDK suite to review DICOM images that’s integrated into industry-leading PACS viewers.

AI-assisted annotation is the key to unlocking rich radiology datasets and was recently used to label the public COVID-19 CT dataset published by The Cancer Imaging Archive at the U.S. National Institutes of Health. This labeled dataset was then used in the MICCAI-endorsed COVID-19 Lung CT Lesion Segmentation Challenge.

Clara Federated Learning made possible the recent research collaboration of 20 hospitals around the world to develop a generalized AI model for COVID-19 patients. The EXAM model predicts oxygen requirements in COVID-19 patients, is available on the NGC software registry, and is being evaluated for clinical validation at Mount Sinai Health System in New York, Diagnósticos da America SA in Brazil, NIHR Cambridge Biomedical Research Centre in the U.K. and the NIH.

“The MONAI software framework provides key components for training and evaluating imaging-based deep learning models, and its open-source approach is fostering a growing community that is contributing exciting advances, such as federated learning,” said Dr. Daniel Rubin, professor of biomedical data science, radiology and medicine at Stanford University.

NVIDIA is additionally expanding its release of NVIDIA Clara to digital pathology applications, where the sheer sizes of images would choke off-the-shelf open-source AI tools. Clara for pathology early access contains reference pipelines for both training and deployment of AI applications.

“Healthcare data interoperability, model deployment and clinical pathway integration are an increasingly complex and intertwined topic, with significant field-specific expertise,” said Jorge Cardoso, CTO of the London Medical Imaging and AI Centre for Value-based Healthcare. “Project MONAI, jointly with the rest of the NVIDIA Clara ecosystem, will help deliver improvements to patient care and optimize hospital operations.”

Learn more about NVIDIA Clara Train 4.0 and subscribe to NVIDIA healthcare news.