New consortium to use AI for breast cancer diagnosis

28 November 2017 (Last Updated November 28th, 2017 10:06)

Imperial College London (ICL) is set to lead a new consortium of breast cancer experts, clinicians, academics and AI experts to explore the use of artificial intelligence (AI) for improved detection and diagnosis of breast cancer.

New consortium to use AI for breast cancer diagnosis
A mammogram. Credit: Imperial College London.

Imperial College London (ICL) is set to lead a new consortium of breast cancer experts, clinicians, academics and AI experts to explore the use of artificial intelligence (AI) for improved detection and diagnosis of breast cancer.

To be based at Cancer Research UK Imperial Centre, the consortium aims to establish the potential of machine learning tools in enhancing the accuracy of breast screening interpretation in order to improve the detection of breast cancers on mammograms.

It is expected that the research will also provide better risk estimate of cancer, allowing women to take necessary preventive measures.

Clinicians and radiologists from the Centre, DeepMind Health technical partners and Google’s AI health research team are set to work with the CancerResearch UK-funded OPTIMAM mammography database.

Available at the Royal Surrey County Hospital NHS Foundation Trust, the database includes de-identified mammograms from approximately 7,500 women.

The digital images are said to not contain any information that could be used to identify patients.

“Harnessing the power of artificial intelligence could enable us to address some of the biggest challenges in breast cancer research.”

During the 12-month project, the research team will work on training computer algorithms to analyse these images, identify any signs of cancerous tissue, and alert radiologists more accurately than existing techniques.

Cancer Research UK Research and Innovation executive director Dr Iain Foulkes said: “Harnessing the power of artificial intelligence could enable us to address some of the biggest challenges in breast cancer research, including improving the accuracy of detection.

“Too many cancers are detected at a late stage when they are more difficult to treat.

“This is why Cancer Research UK is building capacity, forging new partnerships, and supporting a community for early detection research so that more people might survive their disease.”