Google Deepmind trial to improve cancer treatment

The artificial intelligence offshoot of Google has paired up with University College London Hospitals NHS Foundation Trust for a research project.

DeepMind Health announced that it will be receiving anonymised data from the trust for a research partnership into head and neck cancer.

The five-year collaboration will use around 700 anonymised CT and MRI scans of former patients, dating back to 2008, and additional data relating to approximate age, anatomy location, cancer type and radiotherapy received.

Currently before radiotherapy can be administered, clinicians take up to four hours to identify and differentiate between cancerous and healthy tissues on CT and MRI scans of head and neck cancer patients. This process is called segmentation.

In a statement, Yen-Ching Chang, clinical lead for radiotherapy at the trust, said: “Developing machine learning which can automatically differentiate between cancerous and healthy tissue on radiotherapy scans will assist clinicians in planning radiotherapy treatment.”

“This collaboration also means our patients continue to benefit from the most cutting-edge developments in healthcare technology.”

Segmentation is particularly tricky for these types of cancer because the tumours are situated in extremely close proximity to health structures such as eyes and nerves.

The research intends to develop artificial intelligence technology which would cut the segmentation process from four hours to one.

Another hoped for benefit is the development of a radiotherapy segmentation algorithm that can potentially be applied to other areas of the body.

While anonymised data that is used in research does not require consent, the trust said in a published post, that when radiotherapy patients begin treatment a consent form is signed. Only patients who gave their consent will be used in the study.

The data will be destroyed once the project is over.

Head and neck cancer affects over 11,000 patients in the UK each year.

DeepMind’s collaborations with the NHS have not been without incident. In May, its first project with the Royal Free London NHS Foundation Trust to create an iPhone app designed to identify patients at risk of dangerous complications, was widely criticised for its use of patient data.

In a statement to Digital Health News an ICO spokesperson said: “We are in contact with the National Data Guardian about this matter and we continue to make enquiries of the Royal Free in relation to the data shared with Google DeepMind.”

The Royal Free confirmed in a statement to Digital Health News the app is still in development, and has only been used during three user tests aimed at improving the functionality of the app.

The statement added that the trust would give notice before carrying out further testing or before deploying the app.

On 4 July, Moorfields Eye Hospital NHS Foundation Trust, also announced it was partnering with DeepMind to apply machine learning algorithms to automatically detect and segment eye scans.

The five-year research project involves one million anonymised digital eye scans, alongside anonymous clinical diagnoses, information on the treatment of eye diseases, the model of the machine used to acquire the images and demographic information on age.

Digital Health News understands that DeepMind is in conversations with clinicians working in different parts of the NHS about possible future research projects.

DeepMind is a London-based AI company that Google brought for £360 million in 2014.