2 min Analytics

Nvidia works on supercomputer platform and AI-driven diagnostics

Nvidia works on supercomputer platform and AI-driven diagnostics

Nvidia, manufacturer of GPUs and computers, states that Artificial Intelligence (AI) has come so far that it is reliable enough to be used to diagnose diseases and discover new medication. In order to make this possible, it is now working with two health organisations.

Specifically, the company is working with the American College of Radiology on an open AI architecture and a reference implementation, writes Silicon Angle. It is also working with the Accelerating Therapeutics for Opportunities in Medicine (ATOM) organisation on a new supercomputer platform.

The open AI architecture and reference implementation is aimed at radiologists who specialise in the use of medical imaging to diagnose and treat diseases. The reference implementation uses the Nvidia Clara AI toolkit, which offers three key AI capabilities. These include AI-assisted annotation, transfer learning and federated learning.

Radiologists can create new algorithms, validate them, share them with colleagues and adapt them for a range of diagnostic purposes, while also ensuring that the data used for training remains secure.

The toolkit is included in the new ACR AI-LAB software platform that is available free of charge to radiologists to use and develop AI algorithms based on their own patient data. The AI models are brought to the patient data instead of the other way around, in contrast to previous programs. As a result, the data used remains confidential. In addition, it helps to improve the diversity of AI training and to validate the algorithms, says Nvidia.

Discovery of medication

Nvidia also wants to help achieve better patient results by discovering new medicines. To this end, it is working with ATOM on a new AI-based platform designed to speed up the process.

ATOM was founded in 2017 to accelerate the long process of making new medications. According to them, the new platform processes a variety of complex data, including anonymised human clinical data. Doctors can use data-driven models and general molecular design to help them design new medication. The effects of that medication can be simulated within a computer environment.

ATOM’s platform runs on a supercomputer powered by Nvidia’s GPUs. The organization states that it makes this available to the medical research community to help them find new medication more quickly.

This news article was automatically translated from Dutch to give Techzine.eu a head start. All news articles after September 1, 2019 are written in native English and NOT translated. All our background stories are written in native English as well. For more information read our launch article.