AI Medical Imaging: Why Siemens is Adopting Nvidia's Monai

Healthcare systems worldwide face unprecedented challenges - from aging populations to workforce shortages - presenting opportunities for AI to be a transformative force in medical technology.

Against this backdrop, the collaboration between Siemens Healthineers and Nvidia marks a significant milestone in the democratisation of AI-powered medical imaging, the technique for visualising internal body structures for diagnosis.

According to Nvidia, 3.6 billion medical imaging tests are performed every year worldwide to diagnose, monitor and treat various conditions.

This means that the adoption of AI in medical imaging comes at a crucial moment in healthcare evolution.

While early AI applications in healthcare were often siloed and difficult to integrate into clinical workflows, the industry has reached a tipping point where standardisation and interoperability have become paramount.

Therefore, Siemens Healthineers decision to adopt Nvidia's tools could represent more than just a technological upgrade; but a fundamental shift in how medical imaging AI can be developed, deployed and scaled across healthcare systems globally.

Nvidia has introduced Monai, which is an open-source platform that connects doctors and data scientists, enabling the development of AI-powered deep learning models and applications for medical imaging workflows.

The integration of Nvidia's advanced AI tools with Siemens Healthineers' extensive clinical expertise promises to uplift healthcare operations while setting new standards for AI adoption in healthcare.

Streamlining AI integration in clinical settings

Monai Deploy is a module built to accelerate the integration of AI workflows for medical imaging into clinical settings.
It streamlines the development and deployment of medical AI applications.

According to Nvidia, the tool allows developers to build AI applications that can run in various environments with minimal coding.

Siemens Healthineers' adoption of Monai Deploy is expected to significantly accelerate the AI integration process.

The company reports that users can now port trained AI models into real-world clinical settings with just a few clicks, a process that previously took months.

Axel Heitland, Head of Digital Technologies and Research at Siemens Healthineers, says: "By accelerating AI model deployment, we empower healthcare institutions to harness and benefit from the latest advancements in AI-based medical imaging faster than ever.”

Expanding the Monai ecosystem

Monai, now in its fifth year, has seen significant adoption and growth.

Nvidia reports that the platform has been downloaded over 3.5 million times and has contributions from 220 individuals worldwide.

It has also been acknowledged in over 3,000 publications and used in numerous clinical products.

Monai v1.4

The latest release, Monai v1.4, introduces new features including foundation models for medical imaging.

These models can be customised and deployed as Nvidia NIM microservices.

Two notable models now available are MAISI (Medical AI for Synthetic Imaging) and VISTA-3D.

“With Monai Deploy, researchers can quickly tailor AI models and transition innovations from the lab to clinical practice, providing thousands of clinical researchers worldwide access to AI-driven advancements directly on their syngo.via and Syngo Carbon imaging platforms”, Axel tells Nvidia.

MAISI

Additionally, MAISI is a Gen AI model capable of simulating high-resolution, full-format 3D CT images and their anatomic segmentations.

VISTA-3D

Meanwhile, VISTA-3D is a foundation model for CT image segmentation, offering accurate performance for over 120 major organ classes.

Global adoption and collaboration

The Monai platform has attracted interest from various healthcare institutions, academic centres and software providers globally.

For instance, the German Cancer Research Center is leading Monai's benchmark and metrics working group, while the Nadeem Lab from Memorial Sloan Kettering Cancer Center has pioneered cloud-based deployment of AI-assisted annotation pipelines for pathology data using Monai.

Commercial entities are also leveraging Monai.

MathWorks has integrated Monai Label with its Medical Imaging Toolbox, while GSK is exploring Monai foundation models for image segmentation.

Nvidia reports that cloud service providers, including AWS HealthImaging, Google Cloud and Microsoft Cloud for Healthcare, are also offering access to Monai for scalable AI applications.

In the broader context of global health equity, this partnership has implications that extend beyond technological advancement.

By simplifying the deployment of AI models and making sophisticated imaging analysis more accessible, this collaboration has the potential to address healthcare disparities in regions with limited access to specialist expertise.

This is particularly relevant given that approximately two-thirds of the world's population has limited access to diagnostic imaging technologies and expertise.

Explore the latest edition of Technology Magazine and be part of the conversation at our global conference series, Tech & AI LIVE.

Discover all our upcoming events and secure your tickets today.

Technology Magazine is a BizClik brand