Clara Medical Imaging is a collection of developer toolkits built on NVIDIA’s compute platform aimed at accelerating compute, artificial intelligence, and advanced visualization. Medical imaging industry is being transformed. A decade ago, the earliest applications to take advantage of GPU computing were image & signal processing applications.

Today, GPUs are found in almost all imaging modalities, including CT, MRI, X-ray, and Ultrasound bringing more compute capabilities to the edge devices. Deep Learning research in Medical Imaging is also booming with more efficient and improved approaches being developed to enable AI-assisted workflows.Today, most of this AI research is being done in isolation and with limited datasets which may lead to overly simplified models. Even when a fully validated model is available, it is a challenge to deploy the algorithm in a local environment. With the latest release of Clara AI for Medical Imaging now Data Scientists & Software/IT developers have the necessary tools, APIs and development framework to train and deploy artificial intelligence.


Clara Train SDK is available through our Early Access program, please click below to apply to the Early Access Program. Once you are approved, you will be able to download the SDK.



By clicking the "Download" button, you are confirming that you have read and agree to be bound by the SOFTWARE DEVELOPER KITS, SAMPLES AND TOOLS LICENSE AGREEMENT for use of the SDK package. The download will begin immediately after clicking on the "Download"button.



clara

Technology Stack

NVIDIA Clara AI technology stack includes systems software libraries that form the foundation of GPU computing and abstracted software tools, containers, and workflow defining pipelines that allow data scientist and medical imaging developers to build and deploy AI for clinical workflows as well as accelerated research in Medical Imaging.

clara platform


Clara Train SDK enables data scientists and medical researchers with state of the art tools and technologies that accelerate deep learning training for medical imaging.

The Clara Train SDK consists of two components:

  • AI-Assisted Annotation: Client APIs for integrating into DICOM viewers, this technology could enable radiologists to annotate much faster and eliminate the requirement for having to label every slice of CT and MRI data.
  • Domain specific Transfer Learning: Simplifies deep learning tasks such as segmentation of 3D CT/MRI images and enables researchers to train or fine tune models and export to NVIDIA TensorRT based inference with easy to use python wrappers.
  • Also provided are several pre-trained models and applications. The 3-D Brain Tumor segmentation model developed by NVIDIA researchers won first place for Multimodal Brain Tumor Segmentation Challenge 2018. This and several other models developed by NVIDIA researchers are available to use with Clara Train SDK.
clara dgx
Tested on DGX Volta environment internally

"We were able to get our hands on NVIDIA’s AI Assisted Annotation technology and integrate it into our viewer in a couple of days’ time. We currently annotate a lot of images - sometimes on the order of 1000 or more a day, so any technology that can help automate this process could potentially have a significant impact in reducing the time and cost of annotation. We are excited to leverage the AI assisted workflows and work with NVIDIA to solve these critical medical imaging problems."

— Mark Michalski, Executive Director at MGH & BWH Center for Clinical Data Science



Clara Deploy SDK provides a container based development & deployment framework for building AI accelerated medical imaging workflows, it uses Kubernetes under the hood and enables developers and data scientists to define a multi-staged container based pipeline.The modular architecture allows developers to use the offerings of the platform end-end or customize the workflow pipelines with bring-your-own algorithms.

The capabilities forming the Clara Deploy SDK include:

  • Data Ingestion interface to communicate to Hospital PACs system
  • Cores services for orchestrating and managing resources for workflow deployment and development
  • Reference AI applications that can be used as-is with user defined data or can be modified with user-defined-AI algorithms
  • Lastly, Clara Deploy framework also includes Visualization capabilities to monitor progress and view final results
clara deploy


DEEP LEARNING LIBRARIES

The compute Foundation of Clara platform is based off CUDA acceleration and System Software libraries for compute and visualization that expose capabilities of GPUs through SDKs and low level APIs.

CUDNN TensorRT TRTIS




IMAGE & SIGNAL PROCESSING
clara accelerated libraries

RabbitCT---an open platform for benchmarking 3D cone-beam reconstruction algorithms" Christopher Rohkohl, Benjamin Keck, Hannes G. Hofmann and Joachim Hornegger, Med. Phys. 36, 3940 (2009), DOI:10.1118/1.3180956 Download PDF - View BibTeX

  • More cone beam CT research being done using CUDA than any other accelerator technology
  • CUDA outperforms other accelerated technologies by an order of magnitude or more
  • Most recent algorithmic developments being done are all CUDA accelerated


VISUALIZATION and VIDEO

clara partners

Developer Showcase

We specialize in accelerated medical image computing and guided surgery. NVIDIA’s Clara platform gives us the ability to turn 2D medical images into 3D and deploy our technology virtually.

Wolfgang Wein, Founder and CEO
clara

clara

We are using AI to improve workflow for MRI and PET exams. NVIDIA’s Clara platform will enable us to seamlessly scale our technology to reduce risks from contrast and radiation, taking imaging efficiency and safety to the next level.

Enhao Gong, Founder

We would love to showcase your work developed on NVIDIA Clara Platform, send us a notification Here


Get Started With Hands-On Training

The NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers in AI and accelerated computing. Start your hands-on training in AI for Game Development with self-paced courses in Computer Vision, CUDA/C++, and CUDA Python. Plus, check out two-hour electives on Deep Learning for Digital Content Creation and Game Development.

deep learning