Introducing MONAI Physio at #MICCAI2026. 3D and 4D medical images ➡️ personalized cardiac and respiratory digital twins. This open-source Project MONAI toolkit lets researchers model how the heart beats and lungs move for simulation, visualization, and reproducible research. Explore the project 👉 nvda.ws/3VLmJFq

With @GoogleDeepMind, @emblebi, and research partners, we’re making AI-predicted protein complex structures for 2,800+ viruses openly available. This gives scientists a head start in preparing for potential outbreaks.

"When the next pandemic happens, there may be something that comes out of the blue, and we’ll be lacking the knowledge we had for COVID. What we’re trying to do is stockpile some of that knowledge ahead of time.” - Joe Grove, @UofGlasgow A new open dataset adds predicted protein-complex structures from more than 2,800 viruses to the AlphaFold Database. 📃 nvda.ws/47laLF2

🎙️ Building clinical speech AI for the real world? Join experts from @jpmorgan, @nebiusai, and NVIDIA to explore how to build and evaluate accurate, scalable healthcare speech AI. 🔗 Register now to save your spot 👇 nvda.ws/4dOdXN5

We’re using #AI to understand toxicity, a difficult problem in #drugdevelopment. With @LynxKite, using @NVIDIA Nemotron open models, we’re building a Toxicity Knowledge Graph to connect complex evidence and prioritize questions for development. bit.ly/3SZd6lT

This is why I love AI: A 3D model of a child's heart used to take four hours of manual work. CHOP (Children's Hospital of Philadelphia) says AI can now generate it in seconds. The Children's Hospital of Philadelphia built an open-source cardiac modeling platform using NVIDIA MONAI. It turns CT, MRI and ultrasound images into detailed models of a child's own heart. Doctors can study the anatomy and assess how a device will fit before a procedure. For children born with heart defects, those details can shape the treatment plan. The video shows the next step CHOP is exploring: simulating how different stents behave inside a heart model, with the goal of bringing those simulations close to real time. A cardiologist or radiologist still reviews and signs off on every model. For babies facing heart surgery, CHOP's Dr. Matthew Jolley told us, "the goal is always to do fewer of them, and to get each one right." A pretty compelling use of AI. I love it!

This is a fantastic news from @NVIDIAAI @NVIDIAHealth ! blogs.nvidia.com/blog/childr…

Some of the world's largest biopharma companies are running NVIDIA-powered AI factories to transform drug discovery and healthcare. ✅ @bmsnews: Expanding its existing infrastructure with NVIDIA Vera Rubin for proprietary models, oncology research, and clinical imaging ✅ @EliLillyandCo: LillyPod, an #NVIDIADGX SuperPOD with Blackwell Ultra GPUs to support training protein diffusion and foundational models ✅ @Roche: 3,500+ NVIDIA Blackwell GPUs across a distributed hybrid-cloud deployment, with NVIDIA BioNeMo and Omniverse for AI-driven biology and digital-twin workflows Read @RandDWorld's article to learn more. nvda.ws/47d60NP

Together with @ucsc, we introduce AutoMedBench, an open benchmark for evaluating medical AI agents across the full workflow. An agent can produce a final result even when intermediate steps fail. AutoMedBench examines planning, setup, validation, inference, and submission to help researchers identify those failures and compare systems. 6,300+ runs. 96 task combinations. 7 tracks. See how agents compare on the #MICCAI2026 benchmark 👉 nvda.ws/4zdJy3p

Photon-counting CT offers higher resolution and lower noise, but access remains limited. SUMI, an AI method selected for a #MICCAI2026 spotlight, uses radiologist-validated simulations to enhance conventional CT scans toward that quality without requiring paired patient scans. On external data, SUMI outperformed state-of-the-art methods: ➡️ 15% higher structural similarity ➡️ 20% higher peak signal-to-noise ratio 📄💻⚖️ nvda.ws/3V3uVRd

Models across the AI ecosystem run on NVIDIA. New models and AI labs are emerging all the time. Our CEO @JensenHuang shares the idea behind NVIDIA’s platform: build what the ecosystem needs and help everyone succeed. #AllInSummit

AI at its most meaningful - helping doctors personalize care for every child, in seconds. 💚 Inspiring innovation from @ChildrensPhila.

AI is becoming the infrastructure of modern medicine. Across imaging, drug discovery, and clinical systems, accelerated computing is helping turn research into real-world impact faster. At #NVIDIAGTC Berlin, Kimberly Powell, VP and GM of Healthcare at NVIDIA, will explore how AI is advancing human health and what comes next. 🎙️ Turning AI Into the Infrastructure Advancing Human Health: nvda.ws/4cPkDKH 📍 #NVIDIAGTC Berlin | October 20–22, 2026 🔗 Register with code GTC-NV8637P1 for 25% off: nvda.ws/4j297iN

⏱️ AI should give time back. NVIDIA’s @kpowgerade joins @jaredpiano and @IsmailZain on @healthcarerap to explore what that could mean for clinicians, patients, families, and researchers. Bringing that future to life takes an ecosystem - including partners like @AbridgeHQ and @OpenEvidence - putting AI and clinical intelligence into the flow of care. 🎧 Episode #531 nvda.ws/3UZvOKB

The bottleneck in RNA modeling is not architecture. It is that the data is thin, narrow and rarely dynamic. Chronos was @thernabio's answer. Tens of thousands of synthetic mRNAs across a pool of around 50 human cell lines, followed over time, in a single experiment. Analyzing data of that size needed a matching computational approach. We got roughly a 200x speedup using rapids-singlecell, an open-source scverse package built on NVIDIA CUDA-X Data Science from @NVIDIAHealth . In collaboration with @LightningAI, we are also releasing a Lightning Studio so users can interact with the data directly.

The ESMC and ESMFold2 models are now on Huggingface! You can now install it directly from PyPi or from huggingface/transformers v5.16.0. As a part of this, we officially are releasing support for our fused Triton kernels and FoldCP in partnership with @nvidia!

Across Europe, AI communities have been moving the field forward for years. This October, Berlin becomes a meeting point for the people building what comes next. 🤝 Join researchers, developers, engineers, and industry leaders at #NVIDIAGTC Berlin, October 20-22. Register today: nvda.ws/4iHZQMz

⚡️ Healthcare AI moves faster when founders can pair breakthrough research with accelerated computing and production-ready infrastructure. Join us alongside Google Cloud, Google Research, and leading healthcare VCs for a five-part virtual series built for digital health and biotech founders. Check it out 👇

Calling the next generation of healthtech leaders! 📣 Startup School: HealthTech is here to help you reach your highest impact potential. Join us for a customizable five-part series exploring the future of healthcare with industry leaders from @NVIDIA, @GoogleCloud, @FlareCapital, and Pamir Ventures. Register now: goo.gle/hcls-virtual-series

The leather jacket returns to Washington, D.C. 👀 December 1, 2026. 🔗 nvda.ws/46lj6bA