Image source: Carestream
News • AI-as-a-service
Carestream accelerates development and delivery of AI applications for medical imaging
Carestream Health is transforming and accelerating the way it develops and delivers AI applications for medical imaging that help improve patient care.
The state-of-the-art initiative is based on Hewlett Packard Enterprise’s (HPE) GreenLake for Machine Learning Operations (ML Ops). The machine-learning-optimized cloud service infrastructure makes it easier and faster to get started with ML/AI projects, and seamlessly scale them to production deployments. “Carestream has been a leader in leveraging powerful AI technology to help improve image quality, optimize dose and increase workflow efficiency in medical imaging,” said Dharmendu Damany, Chief Technology Officer at Carestream. “Now we are accelerating the pace of our development by providing our industry-leading medical imaging scientists with the optimal AI platform/framework for their research. Our partnership with HPE and their industry leadership with HPE GreenLake Cloud Services gives us the framework to support the operationalization of AI to deliver more solutions that can help improve diagnosis and patient care.”
Delivering AI services and software updates through the cloud will allow medical imaging facilities and their patients to benefit from enhancements more quickly. In the futureDharmendu Damany
HPE GreenLake cloud services provide customers with a powerful foundation to drive digital transformation through an elastic as-a-service platform that can run on premises, at the edge or in a colocation facility. HPE GreenLake for ML Ops, one of a suite of cloud services offered by HPE, enables customers to deploy AI/ML workloads on HPE's ML-optimized cloud services infrastructure. This HPE cloud service, powered by HPE Ezmeral and HPE Pointnext AI Services, is designed to address all aspects of the ML lifecycle from data preparation to model building, training, deployment, monitoring and collaboration.
Carestream’s partnership with HPE paves the way for time-consuming local software updates to eventually be replaced by cloud hardware and service upgrades, enabling imaging facilities to evolve their medical imaging capabilities more quickly. When it becomes available in the future, artificial intelligence-as-a-service also has the potential to reduce the cost-of-entry to new features; and reduce solution costs. Carestream’s collaboration with HPE will impact medical imaging technology on a global scale, as Carestream’s X-ray platforms are in use across 140 countries, spanning over 100,000 pieces of equipment and 35 different hardware configurations. “Delivering AI services and software updates through the cloud will allow medical imaging facilities and their patients to benefit from enhancements more quickly. In the future, they can seamlessly deploy them where their data resides and where they care for patients—whether it is at the micro edge, edge or cloud,” said Mr. Damany.
“Our partnership with Carestream, one of the worldwide leaders in the critical medical imaging space, closely aligns with HPE’s vision for innovation from edge-to-cloud, and provides cloud services to achieve outcome-driven digital transformations,” said Keith White, Senior Vice President and General Manager, HPE GreenLake Cloud Services. “It’s been so exciting working with Carestream to develop a scalable, next generation AI as a service platform that enables their continued leadership in helping to improve patient outcomes and provide impactful insights to their customers.”
The HPE servers include graphic processing units (GPUs) developed by NVIDIA, a key AI hardware partner in the project, enabling each server to tackle multiple imaging and analysis tasks simultaneously. HPE and NVIDIA technology also will facilitate federated learning—the aggregation of anonymized machine learning data across multiple provider facilities. Federated learning is expected to revolutionize healthcare research and development over the next decade, enabling researchers to increase diagnostic intelligence and automation without compromising patient privacy.
Source: Carestream Health