Experts develop AI model for early detection of breast cancer
The research, published today in The Journal of Pathology, by Breast Cancer Now funded scientists at King’s, shows that by analysing the immune responses in the lymph nodes of women with triple negative breast cancer, it’s possible to tell how likely the disease is to spread to other parts of the body.
When breast cancer cells spread from the cancer in the breast to other parts of the body it’s called secondary or metastatic breast cancer and although treatable, it can’t be cured.
The team at King’s have developed an AI model to predict how likely a patient is to develop secondary (incurable) breast cancer based on immune responses in the lymph nodes.
Lymph nodes are pea-sized lumps of tissue found throughout the body that help it fight against infection. Breast cancer cells typically first spread to lymph nodes in the armpit (axilla) which are closest to the tumour. If this has happened, patients are usually given more intensive treatment.
However, the scientists discovered that even when the breast cancer cells hadn’t spread in the lymph nodes, it was still possible to predict from their immune responses the likelihood of the cancer spreading elsewhere in the body.
We’ve taken these findings from under the microscope and translated them into a deep-learning framework to create an AI model to potentially help doctors treat and care for patients, providing them with another tool in their arsenal for helping to prevent secondary breast cancer.
Dr Anita Grigoriadis, who led the research at the Breast Cancer Now Unit at the School of Cancer & Pharmaceutical Sciences
The scientists tested their AI model on more than 5,000 lymph nodes donated by 345 patients to biobanks. They confirmed it could establish the likelihood of breast cancer spreading to other organs.
Around 15% of breast cancers are triple negative and there are currently few targeted treatments. Triple negative breast cancer is more likely than most other breast cancers to return or spread during the first years following treatment.
Dr Anita Grigoriadis added: “By demonstrating that lymph node changes can predict if triple negative breast cancer will spread, we’ve built on our growing knowledge of the important role that immune response can play in understanding a patient’s prognosis.
“We’re planning to test the model further at centres across Europe to make it even more robust and precise. The transition from assessing tissue on glass slides under a microscope to using computers in the NHS is gathering pace. We want to leverage this change to develop AI-powered software based on our model for pathologists to use to benefit women with this hard-to-treat breast cancer.”