Nvidia and King's College London will train AI tech to help tackle cancer

The two organisations will work to build machine learning algorithms to spot underlying cancer causes in radiology scans

Nvidia has announced a partnership with King's College to build an AI platform that will allow NHS specialists to train computers to automate radiology workflows.

KCL will use Nvidia's DGX-2TM system, which has the potential to classify stroke and neurological impairments, to determine the underlying causes of cancers, as well as recommend the best treatment for patients.

The university will also use Nvidia's Clara AI toolkit with their own imaging technologies, such as NiftyNet, as well as those from partners including Kheiron Medical, Mirada and Scan Computers.

It's the first time in the NHS that federated learning will be applied to algorithm development, which is a concept in machine learning that allows AI algorithms to be developed collaboratively, without needing to share training data. It means algorithms can be developed on site using data from each individual hospital, without the need for data to travel outside of its own domain.

Currently, the security and governance of data is a hot topic, but according to King's, federated learning is crucial for the development and implementation of AI in clinical environments. Potentially, it can be used to develop AI models in different NHS Trusts across the UK, built on data from different patient demographics and clinical attributes.

The reason they want to develop the models at individual NHS trusts is so that the data will give a more accurate and representative insight into patients from that particular area. The NHS will also be able to combine these trust specific models to build a larger and demographically richer overall model.

"This centre marks a significant chapter in the future of AI-enabled NHS hospitals, and the infrastructure is an essential part of building new AI tools which will benefit patients and the healthcare system as a whole," said professor Sebastien Ourselin, head of the school of biomedical engineering and imaging science at KCL.

"The Nvidia DGX-2 AI system's large memory and massive computing power make it possible for us to tackle training of large, 3D datasets in minutes instead of days while keeping the data secure on the premises of the hospital."

Researchers and engineers from King's and Nvidia will work together with clinicians on-site at King's College Hospital, Guy's and St Thomas, and South London and Maudsley. The combination of research, technology and clinicians will streamline the discovery of critical data strategies, targeted AI problems and fast-track deployment in clinics.

It's part of King's ongoing London Medical Imaging and AI Centre for Value-Based Healthcare project which aims to disrupt twelve clinical pathways in oncology, cardiology, and neurology, as well as improve diagnoses and patient care in the NHS.

Featured Resources

Digital document processes in 2020: A spotlight on Western Europe

The shift from best practice to business necessity

Download now

Four security considerations for cloud migration

The good, the bad, and the ugly of cloud computing

Download now

VR leads the way in manufacturing

How VR is digitally transforming our world

Download now

Deeper than digital

Top-performing modern enterprises show why more perfect software is fundamental to success

Download now

Recommended

What is digital transformation?
Business strategy

What is digital transformation?

6 Mar 2020
Building a digital nervous system for your business
Business strategy

Building a digital nervous system for your business

7 Mar 2020

Most Popular

The top 12 password-cracking techniques used by hackers
Security

The top 12 password-cracking techniques used by hackers

5 Oct 2020
iPhone 12 lineup official with A14 Bionic chip and 5G support
Mobile Phones

iPhone 12 lineup official with A14 Bionic chip and 5G support

13 Oct 2020
Google blocked record-breaking 2.5Tbps DDoS attack in 2017
Security

Google blocked record-breaking 2.5Tbps DDoS attack in 2017

19 Oct 2020