Researchers develop AI tool able to predict cancer relapse

A team of computer scientists and pathologists have trained an artificial intelligence (AI) tool to identify lung cancer patients who have a higher risk of disease recurrence following treatment.

As part of Cancer Research UK’s TRACERx study, researchers found that they were able to determine with the help of AI how lung cancers evolve in response to the immune system in individual patients.

The charity is hopeful that this 'ground-breaking approach' could accelerate the prediction of which patients are more at risk of their disease returning, so they can be closely monitored with tailored treatment plans.

The AI tool - developed by researchers at The Institute of Cancer Research, London, in collaboration with scientists at University College London Cancer Institute and the Francis Crick Institute - was trained to differentiate between immune and cancer cells, which enabled it to map out areas in tumours where the number of immune cells were high compared to the number of cancer cells.

Using the AI tool, the team found that while some parts of the tumour were packed with immune cells, described as ‘hot’ regions, other parts of the tumour appeared to be completely devoid of them, which they described as ‘cold’ regions.

The researchers then followed the progress of patients who had a higher number of ‘cold’ regions and found they were at a higher risk of relapse.

They also found that cancer cells in the immune cold regions might have evolved more recently than those in immune hot regions packed with immune cells, which they suggest could indicate the development of a ‘cloaking’ mechanism allowing them to hide from the body’s natural defences.

The AI tool is able to assess how many cold regions with this cloaking mechanism exist within a tumour, and thus the likelihood of cancer relapse.

“We’ve gained new insight into how lung cancers can cloak themselves to escape the attention of the immune system – and in doing so can continue to evolve and develop. Cancer’s ability to evolve and to come back after treatment is one of the biggest challenges facing cancer researchers and doctors today,” said Dr Yinyin Yuan, team leader in Computational Pathology at The ICR, London.

“Our research has revealed fresh insights into why some lung cancers are so difficult to treat, and we wouldn’t have been able to do this without the scale and scope of the TRACERx project.”

The TRACERx (Tracking Cancer Evolution through therapy [Rx]) lung study is a £14 million, nine-year study funded by Cancer Research UK.