DeepMind, the Cancer Research UK Imperial Centre and OPTIMAM
Our partnership with the Cancer Research UK Imperial Centre began in November 2017, when we agreed to collaborate with a consortium of leading clinicians and academics led by the Centre, as well as with the AI health research team at Google, to explore the potential benefits that AI technology could have in identifying signs of breast cancer in mammograms (X-rays of the breasts).
Our goal is to use the latest machine learning technology to carefully analyse historic depersonalised mammograms from around 7,500 women provided by the Cancer Research UK-funded OPTIMAM mammography database at the Royal Surrey County Hospital NHS Foundation Trust. These digital images have been stripped of any information which could be used to identify patients and have been available to research groups around the world for a number of years. Through this research, we hope to investigate whether machine learning technology could more accurately identify signs of breast cancer in mammograms, potentially leading to earlier diagnosis and treatment for patients.
If successful, we hope that this research will improve the quality of reporting of screening mammograms, leading to fewer missed cancers, fewer false alarms and, we hope, ultimately saving lives.
You can read more about this project on Imperial's website, here.
Why are we looking at breast cancer research?
Breast cancer is a significant global health problem, with 1.6 million people across the globe diagnosed with the disease every year. In the UK alone, Cancer Research UK estimates that over 150 people are diagnosed with breast cancer every day. While advances in early detection and treatment have improved survival rates, breast cancer still claims the lives of 500,000 people around the world every year, around 11,000 of whom are here in the UK.
Early detection and treatment of breast cancer leads to a much higher chance of a full recovery, saving thousands of lives every year. However, accurately detecting and diagnosing breast cancer still remains challenging.
That is partly because breast screening is not perfect. Thousands of cases are not picked up by mammograms each year, including an estimated 30% of interval cancers – cancers that are diagnosed in between screenings. False alarms and cases of overdiagnosis are also common, leading to significant stress for patients and increased pressure on health services.
We believe machine learning could make screening more accurate, potentially allowing clinicians to treat cancer more effectively.
Data and security with the Cancer Research UK Imperial Centre
Data security and integrity are immensely important to all of our partnerships. Every step is taken by our teams to protect the data we work with, audit its use, and destroy it when it is no longer being used.
As part of this project, DeepMind and its research partners will be carefully analysing historic, depersonalised mammography images from around 7,500 women provided by the Cancer Research UK-funded OPTIMAM mammography database at the Royal Surrey County Hospital NHS Foundation Trust.
All our research projects go through rigorous regulatory and legal approvals, and are governed by agreements. Read more about how we use depersonalised data here.