King’s College London

Implementation of AI technology in imaging diagnostics to develop federated learning and improve patient outcomes

Published 11 JAN 2022


London Medical Imaging & AI Centre for Value-Based Healthcare

The London Medical Imaging & AI Centre for Value-Based Healthcare is a consortium of academic, NHS and industry partners led by King’s College London (KCL) and based at St Thomas’ Hospital. The diverse research teams are training sophisticated artificial intelligence algorithms from a vast wealth of NHS medical images and patient pathway data to create new healthcare tools. For patients, these will provide faster diagnosis, personalised therapies and effective screening across a range of conditions and procedures. Through a focus and experience in value-based healthcare the centre is examining how AI can be used to optimise triage and target resources to deliver significant financial savings for the NHS and healthcare systems overall. The centre has been established as part of the UK Government’s Industrial Strategy Challenge Fund, delivered through UK Research and Innovation.

Phase One - NVIDIA DGX Infrastructure

On the 23rd July 2019, Scan AI, NVIDIA, Mellanox and NetApp came together at Kings College London to reveal the collaborative deep learning & AI solution that had been deployed in KCL's Medical Imaging & AI Centre. The projects aim was to bring artificial intelligence in medical imaging to the point of care. In contrast to traditional medical testing, which involves sending scans for further analysis by specialists, point of care testing allows the results gained from X-rays, CT scans or MRI to be delivered immediately at the time of the patient-doctor interaction.

The collaborative partners deployed the NVIDIA DGX-2 AI supercomputer as part a cluster that powers the first phase of the project. The system’s large memory and two petaflops of compute prowess enables the KCL team to tackle the training of large, 3D datasets in minutes instead of days. The work aims to discover breakthroughs in classifying stroke and neurological impairments, determining the underlying causes of cancers, as well as recommending the best treatment for patients.

Phase Two - Run:AI Implementation

To further increase GPU utilisation within the NVIDIA DGX-1 and DGX-2 appliances, the AI Centre recently installed Run:AI, the world’s first orchestration and virtualisation platform for AI infrastructure. Run:AI pools computing resources to optimise GPU utilisation and elastically allocates hardware to the tasks that need it. It allows data scientists to use massive amounts of GPU power to accelerate their research while giving IT teams control and real-time visibility over resource provisioning, queuing and utilisation.

The Run:AI platform has helped the AI Centre to run important research into the progression of neurological conditions and image-guided interventions for cancer patients. It has also allowed the team to quickly pivot research activities towards COVID-19, where time to results is critical.

Phase Three - Introduction of Federated Learning

Patient data, by its nature, is required to be kept anonymised at every stage of the deep learning process, so the challenge is to ensure maximum learning is gained from the data but without compromising its integrity. Federated Learning is a machine learning technique that trains an algorithm across multiple decentralised edge devices or servers holding local data samples, without exchanging them. In practice this means a centralised AI algorithm can learn from locally stored anonymised data at multiple NHS Trusts by building a consensus model, from multiple data sources, without any patient data leaving the secure data enclaves at each hospital.

The AI Centre at KCL is now in partnership with eleven other NHS Trusts, and in the process of deploying an ambitious Federated Learning Interoperability Platform (FLIP), to support pioneering artificial intelligence systems across the NHS. This will be supported by the role out of AI-optimised POD architectures at multiple sites.

Phase Four - DGX POD Installation

In order to establish federated learning model across multiple sites, there is a need for the hardware capability to be standardised across all the participating sites so no performance bottlenecks are generated in the system. This has been achieved by the role out of ‘POD’ infrastructures in each location. These pods consist of GPU-accelerated server hardware, storage hardware to handle local data and high throughput networking to keep data rapidly available to the compute nodes.

A combination of NVIDIA DGX and 3XS EGX servers were used to get the required compute performance whilst remaining cost-effective enough that multiple units can be installed within a short time frame for maximum efficacy of the federated learning platform.

Phase Five - Update of KCL Cluster

Following the successful launch of DGX PODs across the multiple federated learning sites, it was decided that the master KCL DGX cluster should be relocated to a London datacentre for improved management and monitoring. The Scan AI team undertook a project to transport and install the high availability DGX cluster hardware into new racking, configure the NetApp A800 storage system and update the NVIDIA network switches.

Once the hardware was in position and tested, further work was undertaken to reconfigure the Kubernetes software and deploy a new install of the Run:ai Atlas GPU virtualisation platform.

The Scan Partnership

Throughout the multiple phases of this project - from design and initial deployment through to the subsequent installations and developments - the Scan AI team has been the glue between the collaborative partners of KCL, NVIDIA, NetApp and Run:ai. This oversight and project management has delivered a complex multi-layered process through the various stages of proof of concept trials, testing and system configuration, technical and data science support, finally through to installation, deployment and ongoing maintenance.

"It has been fantastic working with these companies, especially through the guidance of Scan, who have been not only supporting the decisions of what solutions we should embed in our NHS Trust, but to put them together to build a turnkey solution."

– Sebastien Ourselin - Head of Biomedical Engineering & imaging Sciences, KCL

"With Run:AI we’ve seen great improvements in speed of experimentation and GPU hardware utilisation. Reducing time to results ensures we can ask and answer more critical questions about people’s health and lives. "

– Dr M. Jorge Cardoso - Chief Technology Officer of the AI Centre and Associate Professor & Senior Lecturer in AI, KCL

"Many thanks to the whole Scan team, for the support and help during the planning and deployment of the expanded cluster. Special thanks to Eyal for the preparation work on the switches and the precious info provided before, during and after the deployment. "

– Davide Poccecai, IT Manager School of Biomedical Engineering and Imaging Sciences, KCL

Related content

Feature Page
KCL AI Centre

Learn more about the London Medical Imaging and AI Centre for Value Based Healthcare

Read more
Feature Page
Funding AI for the NHS

£16m grant for the London Medical Imaging and AI Centre for Value Based Healthcare

Read more
Feature Page
KCL and Cambridge-1 Collaboration

Discover how KCL accelerates synthetic brain 3D image creation powered by the Cambridge-1 supercomputer

Read more