University College London Hospitals NHS Foundation Trust

fullscreen fullscreen_mobile
The team behind Streams - our secure mobile app for clinicians - is joining Google.

DeepMind and University College London Hospitals NHS Foundation Trust  

Our partnership with University College London Hospitals NHS Foundation Trust (UCLH) began in mid-2016 when we agreed to work on a collaborative research programme to explore the potential benefits that AI technology could have in planning treatment for patients suffering from head and neck cancers.

To do this, UCLH has supplied DeepMind with permission to access a set of up to 800 scans from former patients who have consented to their data being used for medical research.

Our goal is to use the latest AI technology to analyse CT from UCLH patients with cancer of the head and neck in order to improve the efficiency of the complex process of planning treatment, called segmentation. Segmentation is a highly detailed process that involves delineating exactly where radiation needs to be applied to minimise damage to healthy tissue. This can take up to 4 hours per task, and we want to reduce this to 1 hour with the assistance of machine learning.

Further details of this work can be found in our published research protocol and our latest findings can be found here.

fullscreen fullscreen_mobile

Why are we researching radiotherapy planning?

1 in 75 men and 1 in 150 women will be diagnosed with oral cancer in their lifetime, and head and neck cancers affect over 11,000 people in the UK every year. Yet these and other cancers in the head and neck are particularly difficult to treat with radiotherapy.

The high number of delicate structures and nerves concentrated in this area of the body, as well as their proximity to the brain, means that radiotherapy must be painstakingly planned to ensure no healthy structures are damaged, in a process called segmentation. This involves producing a detailed map of the area to be treated, isolating cancerous tissue to be treated from healthy tissue.

Our research project investigates whether machine learning could speed up the segmentation process while maintaining its accuracy. Cutting-edge machine learning algorithms allow the creation of sophisticated image recognition tools designed to improve the efficiency of the complex treatment planning that is required to ensure enough radiation is given to the tumour.

Currently, segmentation can take up to four hours for head and neck cancers. We believe machine learning could reduce this considerably and in so doing, we hope clinicians’ time could be freed up to focus on patient care, education, and research.

You can read about our latest progress on our blog here.

Head and neck cancer is rare and is one of the most complex tumour sites to treat. Therefore, if we can develop technology to assist in planning radiotherapy treatment for these tumours, we would expect that such a breakthrough would be transferrable to other types of cancer.”

Professor Kathy Pritchard-Jones, Chief Medical Officer of London Cancer

Data & security with UCLH

We're working with UCLH to analyse up to 800 scans from 500 former patients who have consented to their data being used for medical research.

The data comprises de-personalised scans dating back to 2008 of head and neck cancer patients who have since completed radiotherapy treatment and who consented to their data being used for medical research purposes. Scans of patients currently undergoing radiotherapy treatment were not included in the research.

Read more about how we use de-personalised data.

Discover more from DeepMind Health