Smart work

20 December, 2018

Harnessing the power of big data and artificial intelligence enables us to make earlier diagnoses, provide bespoke treatments and improve our understanding of cancer.

Earlier this year, Prime Minister Theresa May put artificial intelligence (AI) and big data in the spotlight when she called for technology to transform how the UK diagnoses, treats and prevents cancer.

Big data is often described as the fuel that powers AI, and partnerships between research institutions and healthcare providers are ideally placed to make use of the large amounts of data from patients to enhance our understanding of disease. At The Royal Marsden and the ICR, our experts are exploring the latest advances in technology to help diagnose cancer earlier, personalise treatment, and improve patients' quality of life.

Using AI, we hope to predict how a cancer will evolve in order to intervene at an earlier stage.

Dr Andrea Sottovira

Processing Big Data

Professor Bissan Al-Lazikani, Head of Data Science at the ICR, is leading the development of software tools to help in the discovery of new cancer drugs. Her team is processing large volumes of data obtained through biomedical research and in the clinic, including genetic, radiotherapy, chemical and pharmacological data; images of cells, tissues and the whole body; and clinical notes.

Professor Al-Lazikani's team has built a huge database on cancer known as canSAR, which already has more than 10 billion data points. It is one of a range of computational approaches that are increasingly allowing us to share and integrate diverse sets of data, uncovering knowledge that could not be observed by working on smaller, individual subsets. For example, researchers at the ICR have used canSAR to identify 46 potentially 'druggable' cancer proteins that had previously been overlooked.

Professor Al-Lazikani says:

We are starting to see results where computational research, innovative machine learning and big data re not only exciting developments, but are beginning to have a huge impact on our understanding of cancer.

Analysing MRI scans

Researchers at the ICR and The Royal Marsden are also working at the cutting edge of AI, which involves creating intelligence systems that can 'think' like people. One of the most exciting areas in AI is machine learning - developing artificial intelligences that are able to learn for themselves.

Researchers like Professor Al-Lazikani are creating programs that can learn, through trial and error, and then apply that learning to the growing set of data available, analysing it over and over again to give progressively more accurate and reliable results.

As part of a groundbreaking project, Dr Christina Messiou, Consultant Radiologist at The Royal Marsden and Reader in the Division of Radiotherapy and Imaging at the ICR, is working with Imperial College London to develop machine learning that will assist radiologists in reporting whole-body magnetic resonance imaging (MRI) scans in patients with myeloma. The aim is to develop a computer that can independently indetify scans that show evidence of cancer.

 

If we truly want to understand a patient's cancer, we often need to assimilate vast amounts of information, drawing on huge and complex datasets. We're developing state-of-the-art technology that will enable us to analyse this information much faster.

Predicting cancer's evolution

Scientists at the ICR are also using AI to predict how cancers will evolve. Together with colleagues at the University of Edinburgh, they have developed a powerful AI tool called REVOLVER (repeated evolution of cancer), which picks out patterns in DNA mutation within cancers and uses this information to predicts the disease's next move.

Dr Andrea Sottoriva, Team Leader in Evolutionary Genomics and Modelling at the ICR and Leader of the REVOLVER project, says:

With this tool, we hope to remove one of cancer's trump cards - the fact that it evolves unpredictably, without us knowing what will happen next. By giving us a peek into the future, we could potentially use this AI tool to intervene at an earlier stage.

Thanks to advances in computing power and the sheer volume of data available, AI has captured imaginations. The possibilities for harnessing big data and AI in cancer care are endless, and we are just beginning to explore them at The Royal Marsden and the ICR.