Do you have any questions?

Just leave a short message or call us.

CONTACT US

EBM Technologies Adopts NVIDIA Clara

Nov 27, 2019

EBM Technologies Adopts NVIDIA Clara to Bring AI Tools to Physicians 

Deep learning research in medical imaging is booming with continuously improved models to enable AI-assisted diagnosis. However, most of this AI research is being done in isolation and with limited datasets which may lead to overly simplified models. Apart from that, even when a fully validated model is available, it is still a challenge to deploy the algorithm in a local environment with existing settings. On the other hand, creating a new specialized workflow for AI can be  expensive, creates unnecessary silos, and interrupts the existing workflow.  To solve these problems, we introduce the “EBM AI Workflow.” EBM AI Workflow is a software platform for seamless data annotation, training, and advanced visualization and deployment of AI-based medical imaging applications. It includes PACS server capability which can withstand billion-level big data, an automatic process that can do inference and generate AI outputs in the backend, a native unified labeling interface, as well as NVIDIA Clara application framework to leverage its pre-trained models and transfer learning pipeline.

EBM and NVIDIA Clara

NVIDIA Clara is a healthcare domain-specific set of SDKs, libraries, tools and reference applications for AI-assisted annotation, federated learning, and real-time image and video analysis that runs on the NVIDIA EGX platform for AI computing on edge servers and embedded devices.
EBM incorporates the NVIDIA Clara SDK and uses pre-trained models with our solution to develop a workflow for inference and AI-assisted annotation. When receiving images from local enterprise PACS or modalities, our platform will activate and analyze the images automatically in order to call the corresponding model and then encapsulates the output of AI inference as DICOM objects so it can be displayed on EBM PACS viewer or any other PACS viewers. Additionally, we have created a feedback mechanism for model optimization process by using our native labeling tool on EBM PACS viewer. After the annotated data is produced, we integrate the NVIDIA Transfer Learning toolkit to keep improving the performance of AI models over time.
By applying EBM AI workflow and adopting NVIDIA Clara, the combined power of AI and edge computing can retain critical processing tasks on devices at the point of care, enabling healthcare professionals to gather relevant data and also receive real-time analytics that inform physicians and specialists to make instantaneous, life-saving predictions and emergency responses.

Downloads