Supporting Healthcare AI Development, Research, and Innovation

A hub of technical resources, news, and SDKs for developers and data scientists working in the Healthcare & Life Sciences industry.

New Releases: [Holoscan SDK 0.6] [Parabricks 4.2]

Register Now for the Generative AI Agents Developer Contest by NVIDIA and LangChain   Register Now

What is NVIDIA Clara?

NVIDIA Clara™ is a platform of AI applications and accelerated frameworks for healthcare developers, researchers, and medical device makers creating AI solutions to improve healthcare delivery and accelerate drug discovery. Clara’s domain-specific tools, AI pre-trained models, and accelerated applications are enabling AI breakthroughs in numerous fields, including medical devices, imaging, drug discovery, and genomics.

Build with NVIDIA Clara

Explore the end-to-end pipeline of medical device development and deployment with the Holoscan platform. Build containerized AI apps with the Holoscan SDK and MONAI, and streamline deployment in next-generation AI devices with the NVIDIA IGX developer kits.

Project MONAI

Project MONAI is a domain-optimized, PyTorch-based open source framework to aid researchers developing AI in healthcare.


The NVIDIA Holoscan SDK includes healthcare-specific acceleration libraries, pre-trained AI models, and reference applications for computational medical devices.

NVIDIA IGX Developer Kits

Accelerate edge AI application development with the NVIDIA IGX Orin developer kit.

Learn and Explore

  • GTC Sessions: Medical Devices GTC Playlist
  • Demo: AI Computing for Medical Devices

  • Build and Scale

  • NVIDIA NGC™ Collection: NVIDIA Holoscan
  • User Guide: NVIDIA Holoscan SDK User Guide
  • Developer Forum: NVIDIA Holoscan SDK
  • Reference Architecture: Endoscopy

  • Build Medical AI applications with MONAI. Developers, researchers, and data scientists are building applications including:

  • Classifying medical imaging studies for the presence of a disease
  • Segmenting organs, lesions, and other structures
  • Creating markups to highlight areas of concern with heatmaps
  • Deriving insights for radiologist review for inclusion in a medical report
  • Processing live streams of data to ensure the patient is positioned properly prior to image acquisition
  • Identifying trends in data for population health assessments

  • Project MONAI

    Project MONAI is a domain-optimized, PyTorch-based open source framework to aid researchers developing AI in healthcare.


    NVIDIA MONAI is a comprehensive suite of enterprise-grade containers, AI models, and cloud APIs.

    Learn and Explore

  • GTC Sessions: Medical Imaging GTC Playlist
  • Blog: What is MONAI?
  • MONAI on Medium
  • Playlist: MONAI Bootcamp

  • Build and Scale

  • Github:Project MONAI
  • Documentation: MONAI Toolkit
  • Developer Forum: MONAI

  • Access frameworks, applications, and AI models in genomics, proteomics, microscopy, virtual screening, computational chemistry, visualization, clinical imaging, and natural language processing.

    NVIDIA Clara for Drug Discovery

    NVIDIA Clara™for Drug Discovery enables GPU-accelerated computational drug discovery with a growing collection of frameworks, applications, and AI models that can be applied across the drug discovery process.


    NVIDIA BioNeMo provides domain-specific managed AI services for training and inference that offers customizability of the AI drug discovery pipeline, instant access to state-of-the-art generative AI, and the quickest path to full-stack optimization for scale, speed, and experimentation in early drug discovery.

    Harness accelerated applications for somatic, germline, and structural variant workflows to streamline whole genome, exome, RNA, and cancer sequencing.

    NVIDIA Clara for Genomics

    NVIDIA Parabricks provides GPU-accelerated versions of tools used every day by computational biologists and bioinformaticians - enabling significantly faster runtimes, workflow scalability, and lower compute costs. Download Parabricks for Free.

    Learn and Explore

  • GTC Sessions: Genomics GTC Playlist

  • Build and Scale

  • NVIDIA NGC™ Collection: NVIDIA Parabricks
  • Github: NVIDIA Parabricks
  • Developer Forum: NVIDIA Parabricks
  • Docs: NVIDIA Parabricks Documentation
  • Browse by Resource Type


    The NVIDIA® CUDA® Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.


    The NVIDIA Data Loading Library (NVIDIA DALI®) is a portable, open source library for decoding and augmenting images and videos to accelerate deep learning applications in healthcare. DALI reduces latency and training time, mitigating bottlenecks, by overlapping training and pre-processing.


    NVIDIA FLARE (NVIDIA Federated Learning Application Runtime Environment) is an open source federated learning SDK for distributed, multi-party privacy-preserving collaborative projects.


    NVIDIA Merlin™ is an open source framework for building large-scale deep learning recommender systems.


    Project MONAI is a domain-optimized, PyTorch-based open source framework to aid researchers developing AI in healthcare.


    RAPIDS is a suite of software libraries that enables end-to-end data science and analytics pipelines that provide compute optimization with parallelism and memory speed.


    NVIDIA TAO enables enterprise app developers to fine-tune pretrained models with custom data to produce highly accurate models


    NVIDIA Triton™ Inference Server is open source inference serving software that helps standardize model deployment and execution, and delivers fast and scalable AI in production.

    NVIDIA TensorRT

    NVIDIA TensorRT™ is an open source platform for high-performance deep learning inference, which includes an inference optimizer and runtime that delivers low latency and high throughput for healthcare applications.


    CUCIM is an extensible toolkit that provides GPU-accelerated I/O, computer vision, and image processing primitives for N-Dimensional images.

    NVIDIA DeepStream SDK

    NVIDIA DeepStream SDK enables the rapid development and deployment of Vision AI applications and services with a multi-platform scalable, encrypted security solution that can be deployed anywhere.


    The nvJPEG library provides low-latency decoding, encoding, and transcoding for common JPEG formats used in computer vision applications, such as image classification, object detection, and image segmentation.

    Pull GROMACS

    GROMACS is a molecular dynamics application designed to simulate Newtonian equations of motion for systems with hundreds to millions of particles.

    Pull LAMMPS

    Large-Scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) is a software application designed for molecular dynamics simulations.

    Pull NAMD

    Nanoscale Molecular Dynamics (NAMD) is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems.


    The NVIDIA Isaac SDK™ is a toolkit that includes building blocks and tools that accelerate robot developments that require the increased perception and navigation features enabled by AI.


    NVIDIA Omniverse™ is an extensible, open platform built for virtual collaboration and real-time physically accurate simulation


    NVIDIA NeMo™ is an open source framework for developers to build and train state-of-the-art conversational AI models.


    NVIDIA® Riva is a GPU-accelerated SDK for building speech AI applications that are customized for healthcare use cases and deliver real-time performance.

    BioMegatron & GatorTron

    BioMegatron is a state-of-the-art biomedical language model pre-trained on billions of words of PubMed abstracts and full text documents with its own custom biomedical vocabulary. Similarly, Gatortron is a state-of-the-art Megatron model pre-trained on de-identified clinical notes at the University of Florida Health System and includes a large clinical domain vocabulary.


    NVIDIA GRID™ Virtual PC (GRID vPC) and Virtual Apps (GRID vApps) are virtualization solutions that deliver a user experience that’s nearly indistinguishable from a native PC. With server-side graphics and comprehensive management and monitoring capabilities, GRID future-proofs the virtual desktop infrastructure (VDI) environment.


    NVIDIA virtual GPU (vGPU) technology uses the power of NVIDIA GPUs and NVIDIA virtual GPU software products to offer a consistent user experience for every virtual workflow.

    NVIDIA Quadro Virtual Workstation

    With workloads becoming increasingly compute-intensive, and a constantly growing need for mobility and collaboration, more workloads are being migrated to the cloud. Cloud-based workstations, paired with traditional on-premises infrastructure, give an enterprise the flexibility and business agility to stay competitive.

    Healthcare News and Blogs

    Programs for You

    Developer Resources

    The NVIDIA Developer Program provides the advanced tools and training needed to successfully build applications on all NVIDIA technology platforms. This includes access to hundreds of SDKs, a network of like-minded developers through our community forums, and more.

    Join Today

    Technical Training

    NVIDIA Deep Learning Institute (DLI) offers hands-on training in AI, accelerated computing, and accelerated data science to solve real-world problems. Powered by GPUs in the cloud, training is available as self-paced, online courses or live, instructor-led workshops.

    View Courses

    Startup Acceleration

    NVIDIA Inception—an acceleration platform for AI, data science, and high performance computing (HPC) startups—helps over 7,000 budding businesses worldwide with go-to-market support, expertise, and technology. Startups get access to training through the DLI, preferred pricing on hardware, and invitations to exclusive networking events.

    Learn More