Researchers have developed an artificial intelligence tool that reveals previously unseen patterns inside breast cancers, which they say could help improve treatment and support earlier intervention.
The system analyses images of tumour tissue to identify features that may not be visible to the human eye, potentially offering new insight into how individual cancers behave.
The team behind the work said the patterns could help doctors predict how a tumour is likely to respond to particular treatments, allowing care to be better tailored to each patient.
“This could help us see what makes one cancer different from another, and that is exactly what we need for more personal treatment.”
Breast cancer is one of the most commonly diagnosed cancers worldwide, and outcomes are generally better when the disease is identified and treated early.
Experts not involved in the research welcomed the findings but stressed that the tool would need to be tested in larger groups of patients before it could be used in clinics.
AI is increasingly being explored across healthcare, from reading scans to analysing pathology slides, with the aim of supporting rather than replacing clinicians.
Researchers have also cautioned that such tools must be trained on diverse data so that they work reliably for patients of different backgrounds.
Cancer charities said the work was promising and highlighted the importance of continued investment in research and screening programmes.
The researchers said one of the advantages of the approach was that it could be applied to tissue samples already routinely collected during diagnosis, meaning it would not require additional procedures for patients. That could make it relatively straightforward to introduce into existing hospital workflows if it proves effective in further trials.
The team said it hopes to begin further clinical studies in the coming years.
