VinBrain, a Vietnamese artificial intelligence (AI)-powered healthcare company, has tied up with Microsoft to improve its AI products and solutions.
Founded in 2019, VinBrain specialises in research and development (R&D) in healthcare using AI. The company is funded by Vingroup – one of the largest conglomerates in Vietnam.
The collaboration will see VinBrain's developers using the Azure cloud to improve the development and delivery of its AI-powered healthcare solutions, thereby providing a better experience for end users.
VinBrain said this would also ensure data security for DrAid – its AI software for X-ray diagnostics.
The company’s AI software has a dataset of over 2.3 million medical images from multiple sources including the USA, Europe and Asia.
Trained on a dataset of more than 2.5 million images, DrAid is deployed in more than 100 hospitals in Vietnam, Myanmar, New Zealand and the US.
The software applies AI analysis to medical images for more than 120,000 patients each month. VinBrain is also building a host of other AI applications, including a telehealth product that analyses lab test results, medical reports and other electronic health records.
VinBrain’s CEO, Steven Truong, said nearly 2,000 doctors are currently using DrAid. The datasets are updated and enlarged on a daily basis, which benefits the progress of data assessment.
“Using the latest foundation of AI technology and evaluation, this collaboration with Microsoft will directly impact billions of people through early detection and workflow productivity,” Truong said.
Additionally, VinBrain will perform cross-validation to test its deep learning models and analyse the impact of AI on health outcomes.
Microsoft's Azure Cognitive Services for Vision and its latest foundation model for computer vision, Florence, will help VinBrain improve its productivity and efficiency, the company.
This will result in faster development and potentially lower R&D costs.
Developer teams will be able to access AI capabilities for processing uploaded images and returning information and building, deploying, and improving image classifiers, VinBrain said.
This will increase the accuracy rate of medical imaging for DrAid, the company added.
Using Nvidia infrastructure
VinBrain trains its AI models — which include medical imaging, intelligent video analytics, automatic speech recognition, natural language processing and text-to-speech — using NVIDIA DGX SuperPOD.
NVIDIA DGX SuperPOD is an AI data centre infrastructure platform
The company said adopting DGX SuperPOD enabled VinBrain to achieve near-linear-level speedups for model training, achieving 100x faster training compared with CPU-only training and significantly shortening the turnaround time for model development.
The team is using software from NVIDIA AI Enterprise, an end-to-end solution for production AI, which includes the NVIDIA Clara platform, the MONAI open-source framework for medical imaging development and the NVIDIA NeMo conversational AI toolkit for its transcription model.