Project Summary


We can get rid of many prostate cancers, but sometimes cancer returns


Unfortunately, doctors cannot predict which will return


If we could predict this, we could change the treatment of those cancers to reduce the chance of them returning


For those unlikely to return, we could avoid treatment that might lead to side effects


Certain features around prostate cancer cells mean the cancer is more likely to return


Currently, finding these features requires highly trained staff and can be time-consuming


Anna and Erik have developed computer software to do this automatically and quickly


The software can also ‘learn’ and become better with more use

About the Researchers

Francis Crick Institute, London

Dr Anna Wilkins

Principal Investigator

Anna is a Clinician Scientist at the Institute of Cancer Research and an Honorary Consultant Clinical Oncologist at the Royal Marsden Hospital where she treats prostate and bladder cancer with radiotherapy and drugs. She is also a Visiting Scientist at the Francis Crick Institute in the Sahai laboratory. Her research focuses on the impact of radiotherapy on different aspects of the tumour microenvironment.

Dr Erik Sahai

Principal Investigator

Erik is the head of the Tumour Cell Biology laboratory at the Francis Crick Institute in London. His research is focused on the spread of cancer through the body and responses to cancer therapy. To study these problems his group uses a wide range of techniques from computational modelling of cell migration, through conventional cell and molecular biology, to intravital imaging of mouse tumours and live analysis of patient derived material.

AI transforming cancer research

It is not just new drugs and treatments that will change the future for those with prostate cancer, computers and new technology are going to play a crucial role.


Artificial intelligence or AI is a type of technology that mimics behaviours usually associated with human intelligence such as learning, problem-solving and planning. AI techniques have already revolutionised cancer research, enabling scientists to analyse large datasets quickly and precisely to uncover new methods of screening and treating cancer. This means we can begin to untangle prostate cancer in ways that weren’t possible previously: finding new ways to classify an individual’s cancer and predicting which cancers will return.

Why does cancer return?

We can treat and get rid of many prostate cancers, but sometimes the cancer comes back.


This happens when a very tiny amount of cancer cells are left in the body after treatment. The cancer may return in the same area of the body, or it may return in a different area. For most prostate cancers, we cannot predict which will return, this makes it difficult to know how to treat an individual’s cancer.

Research has found features around prostate cancer cells that mean the cancer is more likely to return. Unfortunately, finding these features requires highly trained staff and a great deal of time.

Anna and Erik hope that their research will enable doctors to quickly predict which prostate cancers are likely to return. This would enable doctors to change the treatment of those cancers to reduce the chance of them coming back. They could also avoid over treatment of those patients whose cancer is unlikely to return, meaning that more people could avoid side effects such as incontinence, erectile dysfunction, and body changes such as the growth of breast tissue.

The research project


Recent advances in artificial intelligence have enabled Anna and Erik to develop computer software to find the features that indicate prostate cancer will return automatically and quickly. The software can also ‘learn’ and become better with more use.

Anna and Erik will use their software to analyse tissue samples collected from patients with prostate cancer during the CHHiP clinical trial, which aimed to find out whether people could be treated effectively with fewer radiotherapy doses. Anna is currently chairperson of the subcommittee responsible for translating the results from the trial into the clinic. Analysing these tissue samples will enable them to build models of the disease to classify prostate tumours based on different cell features.

This approach is new to prostate cancer and if they succeed, the research will have great benefit to patients, their family members and carers, and to the NHS.

The future


This project is still in the early stages and Anna and Erik will soon begin analysing the tissue samples collected from prostate cancer patients.

They hope that their software can be implemented in the clinic which will lead to more personalised treatment for those diagnosed with prostate cancer.

In the longer term, their software can be used across different stages of prostate cancer to gain a better understanding of the biology that underpins aggressive disease and hormone therapy resistance.

Collaborations and partnerships


This is a highly collaborative research project. Anna and Erik are working with other researchers from the Francis Crick Institute, the Institute of Cancer Research, Royal Marsden Hospitals NHS Trust and University College London. They will be bringing expertise in machine learning, statistics, and clinical trials to the project.

“We’ve known for many years that specific patterns of non-cancerous cells, and the surrounding scaffolding that supports tumours, can drive more aggressive prostate cancer behaviour. However, we haven’t had the computational tools to find these “bad biology” tumour patterns. Recent advances in artificial intelligence mean there is now the potential to identify them. We’re very excited that our PCR award means we can apply powerful computational approaches to digital images of tumours, with the goal of enabling better treatment decisions for individual patients - maximising cure rates and minimising side effects.”

Dr Anna Wilkins and Dr Erik Sahai
Francis Crick Institute, London
Press enter or esc to cancel