{"id":3023,"date":"2023-05-11T08:00:00","date_gmt":"2023-05-11T15:00:00","guid":{"rendered":""},"modified":"2026-04-11T13:48:44","modified_gmt":"2026-04-11T20:48:44","slug":"bringing-medical-imaging-ai-models-directly-into-clinical-settings-at-scale","status":"publish","type":"ms-industry","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/microsoft-cloud\/blog\/healthcare\/2023\/05\/11\/bringing-medical-imaging-ai-models-directly-into-clinical-settings-at-scale\/","title":{"rendered":"Bringing medical imaging AI models directly into clinical settings at scale\u00a0"},"content":{"rendered":"\n

Medical imaging is a critical aspect of modern healthcare. Radiologists, physicians, and other healthcare professionals rely on imaging data to diagnose and treat various diseases and conditions. With the increasing volume of medical imaging data being generated every day, the need for automated tools<\/a> to help analyze and interpret this data has become more pressing. This is where AI comes in. AI has the potential to revolutionize medical imaging by enabling faster and more accurate analysis of imaging data, leading to better patient outcomes. <\/p>\n\n\n\n

However, despite more than USD2.7 billion invested<\/a> in companies designing AI for medical imaging in the past decade, the technology has not yet gained widespread adoption in clinical practice. Bringing medical imaging AI models directly into clinical settings at scale is a complex task. This requires addressing several challenges, such as a lack of standardized healthcare systems and technical integration with existing clinical workflows, making it difficult to share patient data and coordinate care between providers. <\/p>\n\n\n\n

But that\u2019s about to change.     <\/p>\n\n\n\n

Microsoft + Nuance and NVIDIA are working together to equip more clinicians with medical imaging AI <\/h2>\n\n\n\n

Our partnership with NVIDIA combines two powerful solutions<\/a> in the healthcare and technology markets: <\/p>\n\n\n\n

    \n
  1. Nuance Precision Imaging Network (PIN)<\/a>: A cloud platform, powered by Microsoft Azure<\/a>, that provides a secure and scalable infrastructure for deploying and managing AI models in clinical settings. The platform is designed to handle large volumes of medical imaging data, making it an ideal solution for healthcare providers who need to process large volumes of medical imaging data quickly and efficiently. <\/li>\n\n\n\n
  2. MONAI<\/a>: An open-source framework for developing AI models for medical imaging, co-founded and accelerated by NVIDIA. The framework is designed to be modular and flexible, making it easy to integrate with other tools and technologies.  <\/li>\n<\/ol>\n\n\n\n

    These solutions help healthcare organizations simplify the translation of imaging AI models into existing and trusted clinical applications that can deliver genuine benefits for everyday patient care without requiring providers to change their workflows or their underlying IT systems. Together, Nuance + Microsoft and NVIDIA are helping solve the problem of getting innovations from the \u201cbench to the bedside\u201d in a much more accelerated manner. <\/p>\n\n\n\n

    These two integrated solutions are designed to help developers focus on their innovative applications\u2014in key areas such as radiology<\/a>\u2014without the burden of deployment challenges. And for health systems, the solutions enable teams to develop, deploy, and fine-tune AI models and applications suited to their specific needs and patient populations.   <\/p>\n\n\n\n

    Ultimately, the value of Nuance PIN and MONAI will be in the improvements that help drive patient outcomes and business performance, and for many healthcare organizations, this value is being delivered today. <\/p>\n\n\n\n

    \"AI
    Figure 1: AI application lifecycle, from research to clinical production<\/em>.<\/figcaption><\/figure>\n\n\n\n

    How Mass General Brigham is using MONAI and PIN <\/h2>\n\n\n\n

    One of the healthcare organizations that is bridging the gap between research and clinical practice is Mass General Brigham (MGB), a Boston-based non-profit hospital and physician network. <\/p>\n\n\n\n

    MGB uses MONAI and PIN to define a unique workflow that links medical imaging AI model development, application packaging, deployment, and clinical feedback for model refinement. The workflow means there\u2019s a much more streamlined connection between the research teams developing AI models and the clinical teams using them. And it\u2019s enabled MGB to start utilizing AI models in everyday patient care. <\/p>\n\n\n\n

    One of the models used at MGB is its AI model for breast density analysis. Using this model, MGB has accelerated turnaround times for mammography readings\u2014reducing the waiting period for results from several days to just 15 minutes.1<\/sup> It means time saved for clinicians and less wait time for patients. The patients can talk to their clinicians about the results of their scan in the same appointment and discuss their next steps before they leave the facility.   <\/p>\n\n\n\n

    Fast deployment of AI models has also been particularly useful for MGB as it\u2019s managing the aftermath of COVID-19. Using an AI model that analyzes lung function, MGB\u2019s clinicians can easily spot indicators of whether a COVID-19 patient\u2019s condition is declining or whether they\u2019re safe to be sent home.   <\/p>\n\n\n\n

    Bridging the gap between research and clinical adoption  <\/h2>\n\n\n\n

    MGB is an example of what\u2019s possible when there\u2019s a closer link between the research and developer communities and clinical practice. As more healthcare organizations begin to accelerate the translation of trained AI models into deployable applications, we\u2019re excited to see how it\u2019s going to benefit patient care delivery far into the future. <\/p>\n\n\n\n

    Discover more<\/h2>\n\n\n\n