Kategorie: Microsoft Azure

Cloud migration for medical imaging data using Azure Health Data Services and IMS

This blog post is co-authored by Vittorio Accomazzi, Chief Technical Officer (CTO) at IMS.

This blog is part of a series in collaboration with our partners and customers leveraging the newly announced Azure Health Data Services. Azure Health Data Services, a platform as a service (PaaS) offering designed to support Protected Health Information (PHI) in the cloud, is a new way of working with unified data—providing care teams with a platform to support both transactional and analytical workloads from the same data store and enabling cloud computing to transform how we develop and deliver AI across the healthcare ecosystem.

The first implementation of digital imaging techniques in clinical use started in the 1970s. Since then, the medical imaging industry has grown exponentially—over the last two and a half decades, there has been a significant development in image acquisition solutions, which has boosted image quality and adoption in different clinical applications. Healthcare is projected to deliver the greatest industry-specific CAGR of 36 percent out to 2025 (Global healthcare data is forecasted to reach 2.3 zettabytes* in this coming year alone) and medical imaging data represents approximately 80 – 90 percent of that growth1.

While the amount of data generated by the medical imaging industry has continued to grow, the solutions for storing and handling this data remain archaic and on-premises due to limited products with insufficient computing power, storage size, and continuously outdated hardware. In addition, the lack of interoperability of these on-premises systems with other types of clinical data solutions and increasing workloads within imaging departments resulted in a big struggle to achieve predictive diagnosis and improved outcomes for patients. Bringing health data into the cloud has been met with challenges ranging from concerns about the security and privacy of the data to a lack of understanding of the opportunities it opens.

For the most part, interoperability in the health industry has also been limited and focused on clinical data. However, other types of health data such as imaging, IoT, and unstructured data also play a critical role in getting a full view of the patient, thereby contributing to better patient diagnosis and care.

This is why Microsoft has released Azure Health Data Services which aims to support the combining clinical, imaging, and MedTech data in the cloud using global interoperability standards like Fast Healthcare Interoperability Resources (FHIR®) and Digital Information Communication in Medicine (DICOM). The DICOM service within Azure Health Data Services allows standards-based communication with any DICOMweb™ enabled systems such as medical imaging systems, vendor-neutral archives (VNAs), picture archiving, and communication systems (PACS), etc. The goal is to fully leverage the power of the cloud infrastructures for medical images, creating a service that is fast, highly reliable, scalable, and designed for security.

Within the DICOM service, QIDO, WADO, and STOW protocols support query, retrieve, and storage of DICOM objects, while custom tags allow for user-defined, searchable tags. You can also use DICOMcast as a single source to query for cross-domain scenarios. The DICOMcast injects DICOM metadata into the FHIR service, or FHIR server, allowing a single source of truth for both clinical data and imaging metadata.

Once imaging data is persisted in the cloud, there is also a need for seamless integration of workloads into the cloud with minimum disruption and without extra investment in devices and software. In order to enable customers currently relying on DICOM DIMSE to be able to smoothly adopt cloud-based imaging storage and solutions powered by our DICOM service.

IMS collaborated with Microsoft to leverage its cloud technologies for IMS to provide a solution for this challenge resulting in a powerful tool that migrates medical imaging data from legacy workstations to the cloud using Azure Health Data Services. IMS selected Microsoft Azure because it has the most comprehensive offering and active road map to support the transition of healthcare to the cloud.

Using CloudSync as a synchronization tool

It was apparent from the beginning that creating a simple protocol converter or gateway to push images from on-premises to the cloud was not an optimal solution: since the data will flow only in one direction (from a healthcare organization to the cloud for storage, archival or advanced analytics). With that, the institution would be missing most of the benefits, such as calling back the image set into the existing on-premises viewer after performing annotations, running cloud-enabled AI models, or advanced analytics. On the other hand, having access to prior imaging studies of the patients during the current visit also plays a vital role in validating abnormal conditions over time for better clinical outcomes.

To bridge this gap, IMS designed and developed CloudSync, which is a software-only DICOM device that actively synchronizes the on-premises archive (or multiple archives) with an Azure DICOMweb endpoint. CloudSync allows the data to flow both ways and furthermore allows the implementation of business logic for the proactive staging of patient historical imaging data for immediate access, thereby reducing the latency experienced by the user.

This synchronization allows integration of organizations’ existing on-prem solutions with Azure Health Data Services and machine learning environments so that they can store, archive, slice-and-dices their data for superior cohort management. With the possibility to conveniently connect to Microsoft Power BI and Azure Synapse Analytics through Azure Health Data Services, institutions can curate their datasets, develop and deploy models, monitor their performance, perform advanced analytics on Azure Machine Learning Pipeline and push results back into their clinical workflow.

Key features of CloudSync include:

Synchronize medical DICOM images from on-premises archives to the cloud using Azure Health Data Services: Enable collaboration among multiple on-prem devices by connecting all of them in one point for ease of access by everyone.
Eliminate network latency while fetching medical imaging data: Proactively push prior medical images of the patient from the cloud to the on-prem devices based on the patient’s schedule and have them ready during the patient’s visit.
Migrate imaging data from legacy workstations to the cloud: Enable seamless and effortless integration of on-premises imaging workstations with the cloud.

CloudVue: A one-stop-shop for medical image viewing

To fully leverage the power of Azure, IMS also provides a zero-footprint diagnostic viewer called CloudVue. CloudVue allows users to safely review the data stored in the Azure DICOMweb archive on any device making it possible to access imaging data from anywhere. On top of the standard security mechanisms, CloudVue also encrypts the data during transmission.

In addition to providing the standard viewing features and tools of a web viewer, CloudVue also provides:

Organizations with the ability to grant granular secure access to specific medical imaging data for distribution such as authorizing users to access specific studies in the archive, and not the entire repository. Therefore, the organization can safely grant access to referring physicians and even patients.
The ability to deliver and improve AI workloads on Azure: CloudVue can store and handle data originating from AI predictions and track user behavior at the same time so it can determine if the prediction is correct. Therefore, CloudVue is implementing a positive feedback loop to monitor and improve AI over time.
Annotation capabilities for images used in AI modeling.

CloudVue is the perfect companion for CloudSync in allowing users to take advantage of storing data in Azure using Azure Health Data Services.

Within the current healthcare market space, one of the biggest challenges facing radiologists, clinicians, and care teams while making the diagnosis is the easy availability of a complete history of the patient—while a radiologist might have access to the medical images, not being able to query and find a patient’s medical history, medications and other lab work in the same place, makes predictive diagnosis difficult and time-consuming. With Azure Health Data Services, all of this data can now be accessed together, and using DICOMcast, a new feature, clinical information can sit alongside metadata from medical images, making them searchable quickly. This technology used alongside IMS’s CloudSync and CloudVue can change how radiologists interact with medical images and give them the ability to use the data they have for diagnosis and research.

The beginning of next-gen medical imaging viewing

IMS has created a solution for the medical imaging industry that allows health organizations to take full advantage of Azure Health Data Services at their own pace while:

Avoiding any disruptions to the current workflow.
Maintaining the current investments in devices and software.

Do more with your data with Microsoft Cloud for Healthcare

With Azure Health Data Services, health organizations are empowered to transform their patient experience, discover new insights with the power of machine learning and AI, and manage PHI data with confidence. Enable your data for the future of healthcare innovation with Microsoft Cloud for Healthcare.

We look forward to being your partner as you build the future of health.

Learn more about Azure Health Data Services.
Learn more about IMS at International Medical Solutions | The Power of Partnering.
Read our recent blog, “Microsoft launches Azure Health Data Services to unify health data and power AI in the cloud.”
Learn more about Microsoft Cloud for Healthcare.

1“Driving Data Growth in Healthcare: Challenges and Opportunities for IT,” IDC
Quelle: Azure

Azure confidential computing with NVIDIA GPUs for trustworthy AI

Many industries such as healthcare, finance, transport, and retail are going through a major AI-led disruption. The exponential growth of datasets has resulted in growing scrutiny of how data is exposed—both from a consumer data privacy and compliance perspective. For example, the use of AI in healthcare has grown rapidly, with hospitals and pharmaceutical companies using AI to improve diagnostics and improve drug discovery and development. In transport, the interaction between humans and vehicles is being re-imagined thanks to AI-powered autonomous driving. However, broader democratization of AI is limited by concerns regarding sharing and use of personal data.1 For example, banks are often unable to collaborate on tasks such as fraud and money laundering detection due to concerns regarding security and privacy of transaction data.

Professor Bryan Williams, Director of Research at University College of London Hospitals acknowledges this challenge; “UCLH and the NHS want to be at the forefront of using AI to transform healthcare. A major obstacle to testing AI algorithms with various partners has been concerned about ensuring the privacy of patient data. Technological solutions that enable the secure sharing of data while protecting patient privacy are a potential game-changer to accelerate the evaluation and adoption of AI in health care.”

In this context, confidential computing becomes an important tool to help organizations meet their privacy and security needs. Confidential computing technology encrypts data in memory and only processes it once the cloud environment is verified, helping protect data from cloud operators, malicious admins, and privileged software such as the hypervisor. It helps keep data protected throughout its lifecycle—in addition to existing solutions of protecting data at rest and in transit, data is now protected while in use.

Microsoft partners with NVIDIA to bring confidential GPUs on Azure

Today, we are excited to announce the next chapter in this journey through a strategic partnership between NVIDIA and Microsoft that brings confidential computing to state-of-the-art NVIDIA GPUs. This partnership is based on a shared vision to empower individuals and organizations to share and collaborate to derive new insights from data without sacrificing security, privacy, or performance. With confidential computing support in Ampere A100 GPUs combined with hardware-protected VMs, enterprises will be able to use sensitive datasets to train and deploy more accurate models without compromising security or performance.

With confidential GPUs, data is encrypted when it is transferred between the CPU and GPU over the PCIe bus with keys that are securely exchanged between NVIDIA’s device driver and the GPU. The only place where data is decrypted is within a hardware-protected, isolated environment within the GPU package where it can be processed to generate models or inference results. Much like other Azure confidential computing solutions, confidential GPUs support cryptographic attestation based on a unique GPU identity provisioned by NVIDIA during manufacturing. Using remote attestation, organizations can independently verify that their data is only processed within genuine and correctly configured confidential GPUs.

Private preview sign up for Azure confidential GPUs

Over the past year, we worked closely with NVIDIA to bring confidential GPUs into the Azure confidential computing ecosystem. Today we are excited to invite you to sign up for the private preview of Azure confidential GPU VMs. In the private preview, confidential GPUs will bring together the security of trusted launch with secure boot and vTPM coupled with up to four NVIDIA Ampere A100 GPUs. With confidential GPUs, you can set up a secure environment in the Azure cloud and run your machine learning workloads utilizing your favorite machine learning frameworks, and remotely verify that your VM boots with trusted code, the NVIDIA device driver for confidential GPUs, and that your data remains encrypted as it is transferred to and from the GPUs.

Confidential computing across industries

We are already partnering with several organizations to accelerate their journey towards confidentiality through confidential GPUs.

Bosch sees confidential computing as a key instrument to help protect data and meet compliance requirements. Dr. Sven Trieflinger, Senior Research Project Manager at Bosch, mentions, “With ever-decreasing cost and performance overheads, confidential computing techniques will be widely adopted in cloud workloads. The new level of security they offer will be instrumental in addressing challenges in the areas of legal compliance, IP protection, and customer trust”.

The impact of confidential computing extends to financial services too, where the Royal Bank of Canada (RBC) is already leveraging Azure confidential computing solutions to innovate. Eddy Ortiz, VP of Solution Acceleration and Innovation at RBC, says, “The confidential computing capabilities available in Azure have enabled us to unlock new business capabilities and materially advance existing product offerings by leveraging data in ways that only a few years ago was impossible. We’ve been able to craft novel applications which satisfy and exceed the Bank's most stringent cybersecurity demands. Through these technological advancements we are well-positioned to continue to offer unique and highly personalized experiences to our clients.”

At Microsoft, we remain committed to the vision of a confidential cloud, a cloud where organizations can share data and derive insights while reducing the need for trust across various aspects of the cloud infrastructure. Along with our hardware partners including NVIDIA, we will continue to innovate and advance AI trustworthiness through confidential computing.

Learn more

Sign up for the private preview of Azure confidential GPU VMs.
Learn more about Azure confidential computing.

References
1How to make AI trustworthy
Quelle: Azure

Azure HBv3 VMs for HPC now generally available with AMD EPYC CPUs with AMD 3D V-Cache

Azure HBv3 virtual machines (VMs) are now upgraded to and generally available with AMD EPYC 3rd Gen AMD EPYC™ processors with AMD 3D V-Cache™ technology, formerly codenamed “Milan-X”, in the Azure East US, South Central, and West Europe regions. In addition, we are announcing that HBv3 VMs will also soon come to Central India, UK South, China North 3, Southeast Asia, and West US 3 Azure regions. Customers can view estimated time of arrival for these new regions at Azure Availability by region.

To access these enhanced CPUs, customers need only deploy new HBv3 VMs, as all VM deployments from today onward will occur on machines featuring the new processors. Existing HBv3 VMs deployed prior to today’s launch will continue to see 3rd Gen AMD EPYC processors, formerly codenamed “Milan”, until they are de-allocated and a customer creates new VMs in their place.

Significant performance upgrade for all HBv3 customers

As previously detailed, EPYC processors with AMD 3D V-Cache can significantly improve the performance, scaling efficiency, and cost-effectiveness of a variety of memory performance-bound workloads such as CFD, explicit finite element analysis, computational geoscience, weather simulation, and silicon design right-to-left (RTL) workflows.

Compared to the performance HBv3-series delivered prior to the upgrade to the new processors, customers will experience up to:

80 percent higher performance for CFD.
60 percent higher performance for EDA RTL.
50 percent higher performance for explicit FEA.
19 percent higher performance for weather simulation.

HBv3-series VMs retain their existing pricing and do not require changes to customer workloads. No other changes are being made to the HBv3-series VM sizes customers already know and rely on for their critical research and business workloads. For more information on the Azure HBv3-series, please see official documentation for the Azure HBv3-series of virtual machines.

The highest performance, most cost-effective cloud HPC

Based on testing of a broad array of customer HPC workloads against the best publicly demonstrated performance from other major cloud providers, Azure HBv3-series VMs with 3rd Gen AMD EPYC processors with AMD 3D V-Cache and InfiniBand from NVIDIA Networking deliver 2.23-3.88 times higher performance.

Figure 1: Relative at-scale workload performance in CFD, molecular dynamics, and weather simulation.

For more performance, scalability, and cost information see our detailed blog here.

Continuous improvement for Azure HPC customers

Microsoft and AMD share a vision for a new era of high-performance computing in the cloud. One defined by continuous improvements to the critical research and business workloads that matter most to our customers. Azure has teamed with AMD to make this vision a reality by raising the bar on the performance, scalability, and value we deliver with every release of Azure HB-series virtual machines.

Figure 2: Azure HB-Series virtual machine generational performance improvement.

“Rescale is excited to see the dedication by Microsoft to continually raise the bar, the new Azure HBv3 VMs featuring AMD EPYC™ CPUs with AMD 3D V-Cache™ technology specifically targets memory bandwidth bottlenecks impacting the most widely used commercial CFD codes on the Rescale platform. Preliminary testing has demonstrated a 25 percent performance boost across three of the most common CFD applications and a positive impact on virtually all software running on the upgraded instances,” said Chris Langel, HPC Engineering Manager at Rescale and Mulyanto Poort, VP of HPC Engineering at Rescale. “We are seeing a strong customer demand for “Milan-X” and are excited to offer the updated Azure HBv3 VMs to our customers,” said Ethan Rasa, Senior Director of Strategic Alliances at Rescale.

“Ansys Fluent is the industry-leading computational fluid dynamics tool and our customers are always looking for ways to run larger problems more quickly, or with more granularity.  The super-linear scaling we are seeing with the AMD Milan-X chip on the Azure HBv3 virtual machines will be received with a lot of excitement by our user base across many industries.”—Jeremy McCaslin, Product Manager, Fluids, Ansys

"Customers who require high-fidelity production simulations in demanding industries rely on Siemens Simcenter STAR-CCM+ software,” said Patrick Niven, Senior Director of Fluid and Thermal Product Management, Siemens Digital Industries Software. “Customers usually need those results quickly, so Siemens and Microsoft collaborate to ensure Azure HB-series instances deliver true HPC-class performance. The new Azure HBv3 instances featuring 3rd Gen AMD EPYC™ CPUs with AMD 3D V-Cache™ technology can accelerate simulations by up to 50 percent, so Microsoft can offer Simcenter STAR-CCM+ users cutting-edge performance on an accessible platform.”

Learn more

Azure Docs—HBv3-series Virtual Machines.
Azure HBv3-series with Milan-X processors launch video.
Watch the announcement at the AMD Acceleration Datacenter Premier.
See additional information on performance, scalability and cost information.
Performance and Scalability of HBv3-series with Milan-X processors.
Find out more about  high-performance computing in Azure.
AMD Launch Hub EPYC 3rd Gen EPYC with AMD 3D V-Cache.
Azure HPC optimized OS images.
Azure HPC virtual machines.

Quelle: Azure

Secure your APIs with Private Link support for Azure API Management

Azure API Management is a fully managed service that enables customers to publish, secure, transform, maintain, and monitor APIs. With a few clicks in the Azure portal, you can create an API facade that acts as a “front door” through which external and internal applications can access data or business logic implemented by your custom-built backend services, running on Azure, for example on Azure App Service or Azure Kubernetes Service, or hosted outside of Azure, in a private datacenter or on-premises. Azure API Management handles all the tasks involved in mediating API calls, including request authentication and authorization, rate limit and quota enforcement, request and response transformation, logging and tracing, and API version management.

Azure API Management helps you in:

Unlocking legacy assets—APIs are used to abstract and modernize legacy backends and make them accessible from new cloud services and modern applications. APIs allow innovation without the risk, cost, and delays of migration.
Create API-centric app integration—APIs are easily consumable, standards-based, and self-describing mechanisms for exposing and accessing data, applications, and processes. They simplify and reduce the cost of app integration.
Enable multi-channel user experiences—APIs are frequently used to enable user experiences such as web, mobile, wearable, or Internet of Things (IoT applications. Reuse APIs to accelerate development and return on investment (ROI).
Business-to-business (B2B) integration—APIs exposed to partners and customers lower the barrier to integrate business processes and exchange data between business entities. APIs eliminate the overhead inherent in point-to-point integration. Especially with self-service discovery and onboarding enabled, APIs are the primary tools for scaling B2B integration.

We are happy to announce the preview of Azure Private Link support for Azure API Management service. If you are not familiar with Azure API Management, when you deploy this service, you get three main components: Azure portal, gateway, and management plane. With Azure Private Link we can create a private endpoint for the gateway component, which will be exposed through a private IP within your virtual network. This will allow inbound traffic coming to the private IP to reach Azure API Management gateway.

Azure Private Link

With Azure Private Link, communications between your virtual network and the Azure API Management gateway travel over the Microsoft backbone network privately and securely, eliminating the need to expose the service to public internet. To learn more about Azure Private Link technology and platform as a service (PaaS) services that support it, you can review our Azure Private Link documentation.

Key benefits of Azure Private Link

Through this functionality we will provide the same consistent experience found in other PaaS services with private endpoints:

Private access from Azure Virtual Network resources, peered networks, and on-premises networks.
Built-in data exfiltration protection for Azure resources.
Predictable private IP addresses for PaaS resources.
Consistent and unified experience across PaaS services.

Private endpoints and public endpoints

Figure 1: Architecture diagram depicting the secure and private connectivity to Azure API Management Gateway—when using Azure Private Link.

Azure Private Link provides private endpoints to be available through private IPs. In the above case, the contoso.azure-api.net gateway has a private IP of 10.0.0.6 which is only available to resources in contoso-apim-eastus-vnet. This allows the resources in this virtual network to securely communicate. The other resources may be restricted to resources only within the virtual network.

At the same time, the public endpoint for the contoso.azure-api.net gateway may still be public for the development team. In this release, Azure Private Link will support disabling the public endpoint, limiting access to only private endpoints, configured under Private Link.

How to decide which networking model to use with Azure API Management?

Azure API Management also supports virtual network injection, allowing all components to be deployed inside a virtual network. With the addition of private endpoints, we have the following options for integrating inside a custom Azure Virtual Network:

 

Network model

Supported tiers

Supported components

Supported traffic

Virtual network—external

Developer and Premium.

Azure portal, gateway, management plane, and Git repository.

Inbound and outbound traffic can be allowed to internet, peered virtual networks, Express Route, and VPN S2S connections.

Virtual network—internal

Developer and Premium.

Developer portal, Gateway, Management Plane, and Git repository.

Inbound and outbound traffic can be allowed to peered virtual networks, Express Route, and VPN S2S connections.

Private endpoint connection (preview)

Developer, Basic, Standard, and Premium.

Gateway only (managed gateway supported, self-hosted gateway not supported).

Only inbound traffic can be allowed to internet, peered virtual networks, Express Route, and VPN S2S connections.

At this moment, these three options are mutually exclusive, you cannot choose a virtual network integration option (external or internal) in combination with private endpoint connections. Also notice that only our managed gateways will support private endpoint connections, the Self-Hosted Gateway does not support private endpoints in Azure.

Preview limitations

During the preview period, we will only support inbound traffic coming to the gateway, instances using STV2 compute platform, all pricing tiers except consumption, and Azure Private Link is limited to instances that are not using virtual network injection (internal or external). The feature will move to general availability as we assess feedback.

With the preview of Azure Private Link for Azure API Management, you are now empowered to bring your Azure API Management instances to a virtual network using the same consistent experience of other Azure PaaS services. You can create and manage private endpoints for the gateway of your Azure API Management instance. We will be sharing more updates and content in the future, so stay tuned for new updates towards the general availability of this feature.

Learn more

About Azure API Management.
Documentation on how to connect privately to API Management using a private endpoint.
Documentation on Azure Private Link.

Quelle: Azure

Microsoft launches Azure Health Data Services to unify health data and power AI in the cloud

Today, we take a giant step toward making the dream of interoperability in healthcare real. Microsoft is announcing the general availability of Azure Health Data Services, a platform as a service (PaaS) offering designed exclusively to support Protected Health Information (PHI) in the cloud. Azure Health Data Services is a new way of working with unified data—providing your team with a platform to support both transactional and analytical workloads from the same data store and enabling cloud computing to transform how we develop and deliver AI across the healthcare ecosystem.

Imagine this scenario:

"Give me all the medications prescribed and connected home health device data with all the CT Scan documents and their associated radiology reports for any patient older than 45 with a diagnosis of osteosarcoma over the last 2 years."

The above statement is a common request to health data managers. It may come from physicians, clinical researchers, or data scientists, but this type of request in today’s systems can often take days or even months as health systems have to query multiple data stores that don’t speak the same language, then extract the data files, and finally work to unify them in batches for the user. Different types of health data are stored in siloed formats and databases—structured data like medications and patient attributes in pharma or EHR databases, CT scans in DICOM format, radiology reports as unstructured text, and medical device data in a separate data estate. By the time all the data is finally organized for use, the information is stale. With Azure Health Data Service, queries like these can be filled in minutes and the data can be connected to the places you need.

Azure Health Data Services is the first of its kind to unify diverse data types in the same data store at the patient level as you bring it into the cloud, which means you can view structured, unstructured, and imaging data together for a holistic, real-time view—in just minutes. With the service, you can search and query across your data using a unified Fast Healthcare Interoperability Resources (FHIR®) structure and deploy a suite of services to connect it rapidly to the technology you need. Whether you’re blending patient data with population health data sets for AI development and analytics, visualizing data for operational efficiencies, deploying patient engagement tools for personalized care, or querying imaging metadata alongside clinical data using our new DICOMcast feature, Azure Health Data Services work with your existing systems to enhance what you’re doing today. It’s also built on open standards to ensure you can support new solutions and innovations yet to come.

Watch the video below to learn more.

Accelerate interoperability and innovation with your data in Azure Health Data Services

Provides a suite of health data APIs enabling you to securely ingest and unify PHI in the cloud and persist it within a compliance boundary in Azure.

FHIR service for management of clinical data.
Tools to enable the transformation of data in HL7v2, CDA, JSON, or CSV formats to FHIR.
Digital Imaging and Communications in Medicine (DICOM) service for management of imaging data.
DICOMcast technology extracts metadata from DICOM instances and integrates it with other clinical data in the FHIR store enabling a single quarriable dataset.
Streaming data from MedTech devices can be ingested and transformed to FHIR, with templates to capture data from Apple HealthKit, Google Fit, and Fitbit.
Unstructured data from clinical notes or health documents can connect and map to FHIR through Text Analytics for health structuring to FHIR for viewing in context with clinical data records at the patient level.

Enables tools for data management, de-identification, event notification, and transformation of data for downstream use. A logical workspace in Azure Health Data Services enables you to manage your FHIR, DICOM, and MedTech services with common configuration across services, and integration with other Azure services. 
Connects your PHI data to powerful technology in the Microsoft Cloud for Healthcare ecosystem. Deep analytics and AI development begin with one click to push PHI data to Azure Synapse Analytics using the Synapse Link for FHIR, where you can send it to Microsoft Power BI for data visualization, or to Microsoft Teams and Microsoft Dynamics 365 for operational and engagement tools.
Enlists trust with layered, in-depth defense and advanced threat protection aligned with strict industry compliance standards and regulatory requirements, including ISO, GDPR, HITRUST CSF, and HIPAA through BAA coverage. Azure Health Data Services helps providers and payors meet the requirements of the 21st Century Cures Act and CMS Interoperability and Patient Access final rules.
Lowers costs in the cloud with a consumption-based pricing model that gives you full transparency with a pay-only-for-what-you-use structure. Azure Health Data Services removes infrastructure costs associated with multiple accounts, only charging for storage, API calls, transformation, and conversion as used, which means you can try the service for smaller workloads and control costs as you add more complex workloads. If you are just getting started, we have also made it developer-friendly by providing monthly entitlements for usage and storage at lower limits, so it is easy to innovate and explore.

Azure Health Data Services sits at the heart of the Microsoft Cloud for Healthcare as your foundation for PHI data in the cloud.

 

How did we build Azure Health Data Services?

We started with the patient. Whether you are working with data in healthcare settings, life sciences, or clinical research, bringing data together in a longitudinal record is powerful, but complex. Too much time is spent trying to unify data, and we wanted to simplify that process so our customers could focus their development dollars on what matters most: improving the delivery of clinical and operational care, fueling precision medicine workflows, and enabling rapid collaboration and research innovation across the health ecosystem.

We listened to our partners and customers in the health industry. The foundation of Azure Health Data Services is about removing barriers to working with health data. It starts with giving organizations trusted security that allows you to apply the security, access, and control you need for PHI so everyone in your organization can move faster. Azure Health Data Services platform allows developers to scale in the cloud quickly, provides tools for data scientists to de-identify and export for research, and allows end users to connect to solutions and apps with SMART on FHIR and Microsoft Power Platform to design and power front end solutions.

We built it for the future. There are a lot of ways to bring data to the cloud. Rather than just create a platform to ‘lift and shift’ data silos into a lake, we wanted a place where our customers could harmonize data around open-source standards like HL7 FHIR and DICOM as it came into the cloud. Organization around these open standards accelerates downstream innovation and interoperability across the entire health ecosystem. And with your PHI data in a compliant boundary in the cloud, you can support both transactional and analytical processing from the same data store. That is important because health data is projected to grow at a compounded annual growth rate (CAGR) of 36 percent through 20251 and building for the future of healthcare means setting up your architecture for efficiency and scale.

We built it with trust. Thousands of developers and customers are already using Azure Health Data Services in production around the world. It is powerful to see our cloud technology bringing together collaboration in clinical research, pharma, healthcare, MedTech, and life sciences. We are honored that they chose Azure for their health data, and we are even more inspired by what they are already doing with our platform to transform the future of health.

“There are several areas where cloud technology like Azure Health Data Services can help enhance healthcare. I believe it will play a critical role between various systems, allowing us to take data from health records and other data sources and combine it together in a centralized place where it can be used to inform and deliver patient-centric care. It also can enable real-time complex deep learning – by normalizing data from different systems in a way that allows complex algorithmic analyses to occur via AI or ML—and integrate research-based insights back into a clinical workflow.”—Matthew Kull, Chief Information Officer, Cleveland Clinic

“Together, SAS and Microsoft Azure are building deep technology integrations that unlock value by making disparate data and advanced analytics more accessible to health and life science organizations. With new capabilities such as the FHIR API within Azure Health Data Services, the embedded AI capabilities of SAS Health are more efficient and secure, expanding the possibilities of patient-centric innovation and trusted collaboration across the health ecosystem.”—Gail Stephens, Vice President, Health Care and Life Sciences, SAS

“When a healthcare company is deciding what technology stack they can rely on, the important topics are data protocols, security and compliance, and ease-of-integration. We chose Azure because it covers all of these topics and then some.”—Sunny Webb, Chief Technology Officer, Veris Health

“Interoperability and secure data sharing are essential in building an open ecosystem to address the fragmentation in the patient journey. The Digital Health Platform is using Azure as the trusted cloud and its Healthcare related service such as FHIR to achieve the goal of a sustainable health system. Through the partnership with Microsoft we will continue to innovate and deliver new services to patients and our DHP partners by embracing Azure Health Data Services.”—Roland Scharrer, Group Chief Data and Emerging Technology Officer, AXA

“As existing providers of clinical decision support software, Capita Healthcare Decisions utilizes the Microsoft FHIR service in the Azure Health Data Services, this enables rapid exchange of data through Fast Healthcare Interoperability Resources (FHIR®) APIs, backed by a managed platform as a service (PaaS) offering in the cloud. This allows our Head Home product to deliver a Hospital at Home experience supporting clinicians to keep patients at home and free up hospital beds.”—Stuart Bailey, Product Director, Capita Healthcare Decisions

“The combination of Sensoria’s remote patient monitoring wearable technology, behavioral feedback enabled mobile apps, and artificial intelligence Microsoft Azure cloud software solutions along with DARCO’s manufacturing, medical footwear design, and diabetic wound offloading expertise will help reduce risk of amputations and improve people’s lives. We are excited about this partnership and look forward to bringing the next generation of diabetic footwear to market.”—Davide Vigano, CEO, Sensoria Health

“ZEISS is able to connect our medical technology to Microsoft’s cloud enabling improved clinical workflows in a secure environment.”—Euan S. Thomson, Ph.D., President, Ophthalmic Devices and Head of Digital Business, ZEISS Medical Technology

“Ksana Health is partnering with Microsoft to digitally transform mental healthcare delivery through continuous, objective behavioral health monitoring and digital interventions. Microsoft’s Cloud for Healthcare and Azure Healthcare APIs accelerate our ability to deliver our full solution with industry-leading end-to-end security, integration, AI services and scalability.”—Tony Scripa, CFO, Ksana Health

Do more with your data with Microsoft Cloud for Healthcare

With Azure Health Data Services, health organizations can transform their patient experience, discover new insights with the power of machine learning and AI, and manage PHI data with confidence. Enable your data for the future of healthcare innovation with Microsoft Cloud for Healthcare.

We look forward to being your partner as you build the future of health.

Learn more about Azure Health Data Services.
Learn more about Microsoft Cloud for Healthcare.
Learn more about how health companies are using Azure to drive better health outcomes.

15 Ways Big Data is Changing the Healthcare Industry, Fingent Blog.

FHIR® is the registered trademark of HL7 and is used with the permission of HL7.
Quelle: Azure

Learn how Microsoft Circular Centers are scaling cloud supply chain sustainability

Aiming at delivering the most sustainable, scalable, and reliable cloud for Azure customers, continued innovation in cloud hardware is a constant priority for Microsoft. This extends beyond server architecture and rack design to include intelligent provisioning, deployment, and ultimately, decommissioning of cloud computing hardware in datacenters.

As we look to deliver upon Microsoft’s commitments towards a net-zero carbon future, our cloud supply chain has integrated a zero-waste philosophy into every stage of the datacenter hardware lifecycle.

For this edition of our Hardware Innovation blog series, I’ve invited Paul Clark, GM, Cloud Engineering and Supply Chain Sustainability, and Anand Narasimhan, GM, Cloud Supply Chain Sustainability to share more about how Microsoft Circular Centers are extending the lifespan of our servers with the goal of increasing component reuse by up to 90 percent.

 

Microsoft team at the opening of the Circular Center in Boydton, Virginia. Pictured from left to right: David Beyer, Anand Narasimhan, Alex Bitiukov, Rani Borkar, Jeff Bertocci, Paul Clark, Kesava Viswanathan, Mo Cruz, Pedro Ramos.

 

In January of 2022, the Microsoft Cloud supply chain achieved significant milestones toward its goal of reusing 90 percent of its cloud computing hardware assets by 2025. We launched two additional Circular Centers, which process decommissioned cloud servers and hardware, sort, and intelligently channel the components and equipment to optimize reuse or repurpose.

Our pilot Circular Center opened in Amsterdam in 2020, and the new centers that went live this year are located at our datacenter campuses in Dublin, Ireland, and Boydton, Virginia. We plan to expand the program at Microsoft datacenters in Quincy, Washington; Chicago, Illinois; Singapore and additional sites over the next few years in Des Moines, Iowa; San Antonio, Texas; Cheyenne, Wyoming; Sydney, Australia; Sweden, and more.

Addressing e-waste is crucial for Microsoft. We have set industry-leading sustainability goals of being carbon negative and water positive by 2030 while ensuring zero waste across our direct operations, products, and packaging. Our cloud supply chain plays a critical role in achieving that target.

The Microsoft Cloud is powered by millions of servers and a range of networking and storage hardware spread across more than 60 datacenter regions across 140 countries. We expect continued expansion of datacenters over the next few years because of the rapid growth in demand for digital services, and are striving to decouple business growth from the impact on natural resources.

So far, the Amsterdam Circular Center has achieved 83 percent reuse and 17 percent recycle of critical parts while contributing to the goal of reducing carbon emissions by 145,000 metric tons CO2 equivalent. This innovative approach to addressing e-waste and the success of the pilot recently resulted in our being named a finalist in the 2022 Gartner Power of the Profession Supply Chain Awards in the Social Impact of the Year category.

Deep history, wide-ranging benefits

Since 2012, Microsoft business units have been charged an internal fee based on the emissions associated with their operations. In 2020, that internal carbon fee was extended to include all Scope 1, Scope 2, and Scope 3 emissions. Scope 1 includes direct emissions from operations that are under a company’s control. Scope 2 is indirect emissions, such as those produced by the generation of electricity that a company uses. Scope 3 is all emissions that a company is indirectly responsible for, up and down its value chain—which is the majority of an organization’s total greenhouse gas emissions.

Those internal fees are deposited into a fund that is then used to drive several of our sustainability initiatives, which incubated technology innovations such as the Circular Center program among many others.

The first Circular Center was launched in March 2020, and we saw in the first year that the center enabled us to react faster to supply chain shortages impacted by COVID-19, by using harvested parts with components from end-of-life assets.

Decommissioned servers processed by Circular Centers are also finding a second life in schools as a resource for skills training programs. We work closely with partners to find new opportunities for end-of-life parts and equipment—like a company in Asia that is repurposing used memory cards in electronic toys and gaming systems. Similarly, through collaboration with suppliers, customers, industry groups, regulators, and other organizations, we’re finding other opportunities to further reduce carbon emissions and waste across the supply chain. For example, we are working with our network device suppliers to evaluate returning network devices to them to maximize reuse.

Decommissioned servers to be processed by Microsoft Circular Center in Boydton, Virginia.

Plan for every part

Microsoft designs a growing portion of its own hardware portfolio, and we make sustainability considerations a key part of the entire Azure hardware design process—including energy efficiency, repairability, upgradability, durability, and an optimized disposition plan for every part and component.

To enact these principles at scale, we developed the Intelligent Disposition and Routing System (IDARS), which establishes and executes a zero-waste plan for every piece of our hardware assets. IDARS is an end-to-end planning system aiming to define the most sustainable path for every part at any point in its lifecycle across the entire supply chain from upstream suppliers to downstream options for circularity.

Paired with Microsoft Dynamics 365 Supply Chain Management and Microsoft Power Platform, IDARS uses AI and machine learning to process and sort a wide range of end-of-life assets, optimize routes for those assets, and provide Circular Center operators precise instructions on how to dispose of the asset. IDARS also ensures compliance and security of the Microsoft Cloud and customer data.

This technology, along with our close collaboration with both upstream and downstream partners, makes the Circular Center program one that we think could revolutionize circular models in the technology industry. We believe it could catalyze sustainable business models everywhere. Taking our learnings and best practices from working with suppliers and partners, we recently made a contribution on “Life Cycle Assessment (LCA) Guidelines for Cloud Providers” to the Open Compute Project (OCP), aiming to encourage the broader cloud hardware community to conduct LCAs to better understand and reduce their environmental impact.

Focusing on suppliers and Scope 3 emissions

As we scale our Circular Center efforts, we will be able to accelerate Microsoft’s progress towards its carbon reduction and broader sustainability goals. In our first year of operations, 7 percent of our servers that were decommissioned globally were routed to the pilot Circular Center in Amsterdam. Over the next 18 months, we expect to increase the decommissioned assets processed and repurposed through Circular Centers to more than 80 percent globally, putting us solidly on the path to our 90 percent goal.

One of the key factors to our success in reducing our Scope 3 emissions through this program—and in turn, our customers’ Scope 3 emissions—is our close collaboration with suppliers. Since 2020, Microsoft’s Supplier Code of Conduct has required that suppliers disclose greenhouse gas emissions as well as plans to reduce those emissions. That affects thousands of suppliers around the world; in fact, the cloud supply chain alone works with hundreds of suppliers, from hardware manufacturers to packaging suppliers to logistics providers.

Learn more

You can learn more about Microsoft’s progress towards our commitments on sustainability in the newly released 2021 Environmental Sustainability Report as well as take a deeper look at the global hardware supply chain that powers Microsoft Cloud.

Learn more about Microsoft’s global infrastructure.
Take a virtual tour of Microsoft’s datacenters.
Discover career opportunities in Azure hardware with Microsoft.

Quelle: Azure

Join Microsoft Azure at NVIDIA GTC developer conference 2022

The convergence of HPC+AI has opened new pathways for companies and developers worldwide to develop innovative, transformative applications. While this presents a plethora of new business opportunities in fields like academic research, climate modeling, and energy sustainability, they also push the boundaries of compute, data, and process capabilities of the underlying infrastructure so they can perform the way they were intended.

Microsoft Azure is committed to providing those capabilities through a continual improvement cycle that incorporates the newest and fastest processors into the cloud. This spring, NVIDIA GTC will illustrate that commitment in detail, showcasing NVIDIA’s accelerated computing capabilities powering resources on Azure that highlight our ongoing commitment to HPC+AI computing across the spectrum of edge, on-premises, and the cloud, while extending data security and privacy capabilities to meet customer and business data needs.

Register for NVIDIA GTC, running March 21 through 24, 2022.

Get a chance to win an NVIDIA Jetson Nano

Two of our sessions give you the chance to win a SWAG box, complete with an HPC t-shirt and Jetson Nano developer kit. Attend these sessions and don’t forget to look for the special link to enter!

Supercomputer Performance, Meet Cloud Versatility.
Nidhi Chappell, Head of Product, Azure HPC/AI Microsoft; John Montgomery, Corporate Vice President Program Management, Azure AI- Microsoft,
Tuesday, March 22, 2022, 11:00 AM PDT.

The Azure HPC+AI platform enables a new era of innovative applications and services that leverage the versatility of the cloud with the power of supercomputing performance. The convergence of HPC and AI is a revolution, bringing dramatic acceleration to every kind of simulation, and advancing fields across science and industry. Whether you need to scale to over 80,000 cores for your message passing interface (MPI)-based workloads, or you are looking for AI supercomputing capabilities, Azure can support your needs with all of the versatility of the cloud. In this session, we will provide an overview of the Azure HPC+AI platform reviewing recent accomplishments, and cover in detail how the Azure HPC+AI portfolio can support your accelerator workload needs ranging from AI inferencing to deep learning and more.

Unlocking New Possibilities for Privacy-Preserving Data Analytics with Azure Confidential Computing.
Mark Russinovich, Azure CTO and Technical Fellow, Microsoft; Ian Buck, Vice President and General Manager of Accelerated Computing, NVIDIA.

In this session, Microsoft Azure CTO and Technical Fellow Mark Russinovich and NVIDIA Data Center VP Ian Buck discuss how Microsoft and NVIDIA are partnering together to integrate the latest GPU technology with Azure confidential computing to help customers process large data workloads such as AI and machine learning, multi-party analytics, and 3D rendering while keeping data private and secure. Currently, there is no comparable offering in the marketplace, and Azure is driving first to market with this game-changing technology in our quest to be the most secure cloud.

Preserving privacy with confidential computing

Organizations across industries are going through a major AI-led disruption. For example, in healthcare, hospitals, pharmaceuticals, and researchers are leveraging AI to accelerate research, refine diagnostics, and improve drug discovery and development. Yet, the democratization of AI is limited by concerns regarding share and use of personal data. For example, banks are often unable to collaborate on critical tasks such as fraud and money laundering detection.

Microsoft has pioneered several privacy-preserving technologies such as homomorphic encryption, confidential computing, and differential privacy to address these challenges.

Join us at NVIDIA GTC to learn more about how to unlock new possibilities for privacy-preserving data analytics with Azure confidential computing to help process large data workloads such as AI and machine learning, multi-party analytics, and 3D rendering, while keeping data private and secure. Learn about how confidential GPUs offer high efficiency and confidentiality and how customers and organizations across the world benefit from it.

For more information about the latest on Azure confidential computing: check out our website, technical documentation, and blogs.

Transforming AI and machine learning at the edge

According to IoT Signals, IoT and AI adoption isn’t slowing down with 90 percent of adopters stating that IoT is critical to their success and 79 percent of businesses indicating they were successfully adopting AI within their IoT solutions with top reasons including predictive maintenance at 67 percent and prescriptive maintenance at 65 percent. Additionally, 56 percent of organizations are combining AI and IoT to create a better user experience.

However, at the same time, 46 percent of businesses with AI strategies are struggling to get their projects past the proof-of-concept stage due to technical challenges and complexity. By shifting AI, analytics, and logic to edge devices, edge computing can help solve speed, latency, security, and reliability challenges within AI and IoT applications.

At NVIDIA GTC, learn more about how Nvidia and Microsoft are working together to Transform AI and machine learning at the Edge leveraging the power of the GPU at the edge combined with Azure AI and IoT services. Learn about accelerating AI and IoT solutions with Azure Percept, Azure Stack HCI, and other Azure IoT services.

For more information check out NVIDIA + Microsoft Accelerated Edge AI webpage.

NVIDIA DLI Training Powered by Azure

We’re proud to host NVIDIA’s Deep Learning Institute (DLI) training at NVIDIA GTC again this year, with instructor-led workshops around accelerated computing, accelerated data science, and deep learning.  Hosted on Microsoft Azure, these sessions enable and empower you to leverage NVIDIA GPUs on the Microsoft Azure platform to solve the world’s most interesting and relevant problems. Register for a DLI workshop today.

Microsoft customers solve complex problems with Azure and NVIDIA GPUs

Sensyne Health aids National Health Service in the COVID-19 struggle with Microsoft HPC and AI technologies.

In the midst of COVID-19 the need for a way to get faster test results, Sensyne Health developed its MagnifEye solution, a mobile app that uses a device’s camera to capture the lateral flow test (LFT) stick image and read it in tenths of seconds with a stunning 99.6 percent accuracy rate.

Learn More

Learn more about Microsoft at NVIDIA GTC.
Register for NVIDIA GTC DLI workshops and training sponsored by Microsoft Azure.
Learn more about our joint Edge to Cloud story with NVIDIA.
Learn more about our recently launched Digital Certification program with Cap Gemini focusing on NIVIDA GPU-powered Azure virtual machines.
Altair ultraFluidX™ on Azure.
Barracuda Virtual Reactor on Azure.
Autodesk VRED on Azure.

Quelle: Azure

5 reasons to attend the Azure VMware Solution digital event

Imagine getting more from your VMware workloads by easily extending them to the cloud—and optimizing your costs in the process. Azure VMware Solution, a jointly engineered Microsoft and VMware service, makes this possible.

Azure VMware Solution lets you run your VMware infrastructure natively on Azure. Migrating your on-premises VMware investments and skills to Azure allows you to:

Quickly scale, automate, and modernize your VMware workloads.
Continue using your favorite VMware tools in the cloud, including VMware vSphere, vSAN, and vCenter.
Improve your disaster recovery, business resiliency, and VMware application performance.
Take advantage of Azure management, security, and compliance services.
Respond more quickly to the needs of your customers.
Reduce your IT infrastructure spending.

To show you how simple transitioning to Azure VMware Solution is and highlight the product’s capabilities, Microsoft and VMware are hosting an Azure VMware Solution digital event on Wednesday, March 23, 2022, from 9:00 AM to 11:30 AM Pacific Time.

Register now for this free event to:

1. Get product insights directly from customers

Find out how organizations significantly enhanced their VMware infrastructure with Azure VMware Solution in these customer interviews during the event keynote:

Learn how the University of Miami—which houses one of the nation’s leading oceanographic institutes and operates in a region known for hurricanes—strengthened its disaster recovery strategy and increased its IT flexibility while reducing costs.
Hear how Carhartt, the global premium workwear brand, increased its workload reliability and delivered easy-to-manage, secure digital workspaces to its employees.

2. See Azure VMware Solution in action

Watch demos of how to migrate your on-premises VMware workloads to the cloud and how to optimize, scale, and automate them there.

3. Take a technical deep dive into the product

Join breakout sessions and instructor-led workshops on topics including:

Learning your way around the Azure VMware Solution architecture.
Understanding the enterprise-scale landing zone considerations.
Deploying and connecting to a private cloud with Azure VMware Solution.
Protecting your data and managing disaster recovery using Azure VMware Solution with VMware Site Recovery Manager.
Simplifying your workload migration to Azure with VMware HCX.

4. Learn about product updates, best practices, and cost-saving programs

Hear from Microsoft and VMware leaders including:

Kathleen Mitford, CVP, Azure Marketing, Microsoft.
Eric Lockard, CVP, Azure Dedicated, Microsoft.
Sumit Dhawan, President, VMware.
Mark Lohmeyer, SVP and GM, Cloud Infrastructure Business Group, VMware.

5. Get answers to your technical questions

Ask the product experts your questions about migrating and operating your VMware infrastructure natively on Azure in the live chat Q and A.

Join us on March 23, 2022, to get to know Azure VMware Solution better, hear advice and insights from customers, engage with product insiders, and explore how to quickly and cost-effectively move your VMware investments to the cloud.

Check out the keynotes and event sessions

Beginning at 9:00 AM Pacific Time:

Keynote featuring Microsoft and VMware leadership and customers.

Join Kathleen Mitford (CVP, Microsoft Azure) and Sumit Dhawan (President, VMware) in conversation with Azure VMware Solution customers.
Special guest speakers from:

University of Miami
Carhartt

Product Update and Real-World Demo

Get insider info from Sue Hartford (Director of Product Marketing, Microsoft Azure), Eric Lockard (CVP, Microsoft Azure), and Mark Lohmeyer (SVP and GM, VMware) and see Azure VMware Solution in action

Beginning at 10:25 AM Pacific Time:

Azure VMware Solution
Session by Ram Gowrishankar (Partner Group Program Manager, Microsoft)

Simple deployment
Session by Trevor Davis (Senior Technical Specialist, Microsoft) and Emad Younis (Director, Multi-Cloud Center of Excellence, VMware)

Disaster recovery with Azure VMware Solution
Session by Saravanan Manickam (Program Manager, Microsoft)

AVS: Offers to accelerate Azure migration and modernization
Session by Vinoo Srinivas Murali (Director of Business Strategy, Microsoft)

Automating onboarding of Azure VMware Solution
Session by Prasad Gandham (Principal Program Manager, Microsoft) and Sapna Jeswani (Principal Program Manager, Microsoft)

Hands-On Workshop: Azure VMware Solution private cloud deployment and connectivity

Hands-On Workshop: Disaster protection with Azure VMware Solution and VMware Site Recovery Manager

Hands-On Workshop: Azure VMware Solution workload migration with VMware HCX

Microsoft Learn Live: Prepare to migrate VMware workloads to Azure by deploying Azure VMware Solution

Microsoft Learn Live: Deploy disaster recovery using VMware Site Recovery Manager and Azure VMware Solution
Tutorials with Microsoft Senior Cloud Advocates Amy Colyer and Pierre Roman

We hope to see you there!

Extend to the Cloud with Azure VMware Solution
Wednesday, March 23, 2022
9:00 AM to 11:30 AM Pacific Time

Delivered in partnership with VMware.

Quelle: Azure