As analytics tools and machine learning capabilities mature, healthcare innovators are accelerating the development of optimized therapies powered by Azure GPU-enhanced AI infrastructure powered by NVIDIA.
Improving diagnosis and raising the level of patient care
Humankind’s search for cures and cures for common ailments has driven thousands of years of healthcare innovation. From the use of traditional medicine in early history to the rapid medical advances of the past few centuries, health care providers are locked in a constant search for effective solutions for ancient and emerging diseases and conditions.
The pace of healthcare innovation has increased exponentially over the past few decades, with the industry absorbing dramatic changes as it transitions from the health care community to the health treatment community. From telemedicine, personal well-being, and precision medicine to genomics and proteomics, all powered by artificial intelligence and advanced analytics, modern medical researchers have access to more supercomputing capabilities than ever before. Powered by artificial intelligence, this quantum leap in computational power allows healthcare services to be deployed and consumed in ways, and at a pace, not previously imagined.
Today, health and life sciences leaders are leveraging Microsoft Azure high-performance computing (HPC) and purpose-built AI infrastructure to accelerate insights in genomics, precision medicine, medical imaging, and clinical trials, with virtually no limits to the computing power they have at their disposal. These advanced computing capabilities allow healthcare providers to gain deeper insights into medical data by deploying analytics and machine learning tools on top of clinical simulation data, increasing the accuracy of mathematical formulas used for molecular dynamics and enhancing clinical trial simulations.
By leveraging the infrastructure-as-a-service (IaaS) capabilities of Azure HPC and AI, healthcare innovators can solve scale, collaboration, and compliance challenges without adding complexity. And with access to the latest GPU-enabled virtual machines, researchers can power innovation through advanced remote visualization, deep learning, and predictive analytics.
Data scalability provides rapid testing capabilities
Take the example of the National Health Service, where the use of Azure HPC and AI has led to the development of an application that can analyze COVID-19 tests at scale, with a level of accuracy and speed that human readers simply cannot reach. This greatly improved the efficiency and scalability of analysis as well as management capabilities.
Another noteworthy advance is that with Dragon Ambient Experience (DAX), an AI-based clinical solution offered by Nuance, physician and patient experiences are enhanced by turning patient conversations into high-fidelity medical notes, helping to ensure high-quality care. By freeing up time for physicians to engage with their patients in a more direct and personal way, DAX improves the patient experience, reduces patient stress, and saves physicians time.
“Powered by Azure and PyTorch, our solution could fundamentally change how clinicians and patients engage and how clinicians deliver healthcare.—Guido Gallopyn, Vice President of Healthcare Research at Nuance.
Another exciting partnership between Nuance and NVIDIA brings directly into clinical settings medical imaging AI models developed using MONAI, a domain-specific framework for building and deploying imaging AI. By providing healthcare professionals with much-needed AI-based diagnostic tools, across modalities and at scale, medical centers can improve patient care at fractions of the cost compared to traditional healthcare solutions.
“Traditionally, widespread adoption of medical imaging has been constrained by the complexity of clinical workflows and the lack of standards, applications, and publication platforms. Our partnership with Nuance removes these barriers, enabling exceptional AI capabilities to be delivered at the point of care, faster than ever before.—David Niewolny, Director of Healthcare Business Development at NVIDIA.
GPU-accelerated virtual machines are a game-changer in healthcare
In the field of medical imaging, progress relies heavily on the use of the latest tools and technologies to enable rapid iterations. For example, when Microsoft scientists sought to improve a state-of-the-art algorithm used to screen for blinding retinal diseases, they harnessed the power of NVIDIA’s latest GPUs running on Azure virtual machines.
Using Microsoft Azure Machine Learning for computer vision, the scientists reduced misclassification by more than 90 percent, from 3.9 percent to just 0.3 percent. The training of the deep learning model was completed in 10 minutes for more than 83,484 images, which achieved better performance than the state-of-the-art AI system. These are the kinds of improvements that can help clinicians make more robust and objective decisions, leading to better patient outcomes for patients.
For Elekta, the creator of radiation therapy, the use of artificial intelligence can help expand access to life-saving treatments for people around the world. Elekta believes AI technology can help clinicians by freeing them to focus on higher-value activities such as tailoring and personalizing treatments. The company accelerates the overall treatment planning process for patients undergoing radiation therapy by automating time-consuming tasks such as advanced analysis services, target setting, and dose optimization for patients. In addition, they rely heavily on the flexibility and robustness of Microsoft Azure’s on-demand infrastructure and services to develop solutions that help empower their clinicians, and facilitate the next generation of personalized cancer treatments.
Elekta uses Azure HPC powered by NVIDIA GPUs to train its machine learning models with the flexibility to scale storage and compute resources as its research requires. With Azure scalability, Elekta can easily launch experiments in parallel and launch an entire AI project without any investment in on-premises hardware.
“We rely heavily on the Azure cloud infrastructure. With Azure, we can create virtual machines on the fly with specific GPUs, and then scale as per project requirements.Sylvain Periaault, Principal Research Scientist at Elekta.
With Azure’s high-performance AI infrastructure, Elekta can dramatically increase the efficiency and effectiveness of its services, helping to reduce the disparity between the many who need radiation therapy and the few who have access to it.
learn more
Take advantage of Azure HPC and AI infrastructure today or request an Azure HPC trial.
Read more about machine learning in Azure:
(tags for translation) Artificial Intelligence