NHS hospitals join with NVIDIA, using AI to interpret radiology scans

Graphics card specialist NVIDIA and King’s College London have announced they are partnering to build an artificial intelligence (AI) platform that could allow specialists in the NHS to train computers to automate the most time-consuming part of radiology interpretation.

The collaboration is part of King’s London Medical Imaging and AI Centre for Value-Based Healthcare, an ongoing project intended to transform 12 clinical pathways in oncology, cardiology and neurology, as well as improve diagnoses and patient care in the NHS.

NVIDIA hopes the work could lead to breakthroughs in classifying stroke and neurological impairments, determining the underlying causes of cancers and recommending the best treatments for patients.

King’s is installing NVIDIA systems providing 2-petaflops of graphics card-powered supercomputers for AI research, as part of the first phase of the project.

It will also use an NVIDIA toolkit along with its own imaging technologies as well as those from partners such as Kheiron Medical, Mirada and Scan.

The toolkit from NVIDIA will consist of libraries for data and image processing, AI model processing, and visualisation.

Researchers and engineers from NVIDIA and King’s will also join clinicians from major London hospitals onsite at King’s College Hospital, Guy’s and St Thomas’, and South London and Maudsley.

This combination of research, technology and clinicians will accelerate the discovery of data strategies, resolve targeted AI problems and speed up deployment in clinics.

Federated learning

Under the plans the NHS will apply “federated learning” to its algorithms for the first time - where each hospital system will independently compute changes to algorithm settings and share it with a central server on a regular basis.

Each system’s updates are then amalgamated at regular intervals into a new global model by the central server.

NVIDIA said this approach is crucial in the NHS and other clinical environments where security and governance of data is of the highest importance and constant contact between the AI systems is undesirable.

Professor Sebastien Ourselin, head of the School of Biomedical Engineering and Imaging Sciences at King’s College London, said the arrangements will allow the NHS to share and analyse data at a scale that has not previously been possible.

Ourselin said: “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.”

The collaboration between NVIDIA and King’s College London is part of the UKRI programme for Radiology and Pathology, an innovation fund that has supported the growing community looking to integrate AI workflows into the NHS.

Last year, the government’s life sciences tsar, Sir John Bell, said the NHS could save billions by using AI to diagnose scans for heart disease and lung cancer at a time when it faces mounting financial pressure.