Reference design supports x-ray deep learning model
Adaptive computing company, Xilinx has partnered with Spline.AI, which created the conversational medical user interface for healthcare, to develop a x-ray classification deep learning model and reference design on Amazon Web Services (AWS).
The adaptive model enables medical equipment makers and healthcare service providers to develop trained models for clinical and radiological applications.
The model is deployed on the ZCI104, which is based on Xilinx’s Zynq UltraScale+ MPSoC. It leverages the Xilinx deep learning processor unit (DPU), and uses a soft-IP tensor accelerator to run a variety of neural networks, including classification and detection of diseases.
An open source model runs on a Python programming platform on a Xilinx Zynq UltraScale+ MPSoC, and can therefore be adapted by researchers to suit different application specific requirements. Medical diagnostic, clinical equipment makers and healthcare service providers can use the open source design to quickly develop and deploy trained models for clinical and radiological applications in a mobile, portable or point-of-care edge device with the option to scale using the cloud.
“AI is one of the fastest growing and high demand application areas of healthcare, so we’re excited to share this adaptable, open-source solution with the industry,” said Kapil Shankar, vice president of marketing and business development, Core Markets Group at Xilinx. The collaborative model is characterised by low latency, power efficiency, and scalability. It can also be easily adapted to similar clinical and diagnostic applications, medical equipment makers and healthcare providers are empowered to swiftly develop future clinical and radiological applications using the reference design kit, added Shankar.
The artificial intelligence (AI) model is trained using Amazon SageMaker and is deployed from cloud to edge using AWS IoT Greengrass. This enables remote machine learning (ML) model updates, geographically distributed inference, and the ability to scale across remote networks and large geographies.
“Amazon SageMaker enabled Xilinx and Spline.AI to develop a high-quality solution that can support highly accurate clinical diagnostics using low cost medical appliances. The integration of AWS IoT Greengrass enables physicians to easily upload X-ray images to the cloud without the need of a physical medical device, enabling physicians to extend the delivery care to more remote locations,” explained Dirk Didascalou, vice president of IoT at Amazon Web Services.
The solution has been used for a pneumonia and Covid-19 detection system, with incredibly high levels of accuracy and low inference latency. The development team leveraged over 30,000 curated and labeled pneumonia images and 500 Covid-19 images to train the deep learning models. This data is made available for public research by healthcare and research institutes such as National Institute of Health (NIH), Stanford University, and MIT, as well as other hospitals and clinics around the world.
