Breast cancer screening has saved countless lives. Now, new research suggests artificial intelligence could help doctors spot a woman’s risk even earlier – before anything appears on a scan.
A new Australian study, published in The Lancet Digital Health, found the AI tool could identify women with a higher likelihood of developing breast cancer, including some whose mammograms initially show no signs of the disease.
Breast cancer remains one of the most common cancers affecting Australian women, with more than 20,000 women diagnosed each year and over 3,300 deaths. Early detection is crucial, with screening mammograms already shown to halve a woman’s risk of dying from the disease.
How AI is helping
The Australian-built tool, called BRAIx, analyses mammograms using artificial intelligence to detect patterns linked to future cancer risk that the human eye may not be able to see.
Researchers trained the system using mammogram data from nearly 400,000 women, then tested it on 96,000 women to see how accurately it could predict breast cancer risk.
The AI produces a personalised risk score estimating a woman’s likelihood of developing breast cancer over the next four years.
The study found nearly one in 10 women in the top two per cent of risk scores went on to develop breast cancer, despite initially receiving a clear mammogram.
Researchers say this shows the tool can predict risk more accurately than methods doctors currently rely on, such as age and family history.
It may also help address one of the biggest challenges in breast screening: dense breast tissue.
Women with dense breasts face a higher risk of developing breast cancer but detecting tumours can be more difficult because both dense tissue and cancer appear white on a mammogram. The AI tool was able to distinguish between the two.
What this could mean for breast screening
Experts hope advances such as AI will help improve early detection and ensure more women receive the screening and follow-up care they need.
Artificial intelligence is already being trialled to help read mammograms but tools like BRAIx represent the next step, predicting risk before cancer develops.
“We believe the use of AI models will be a significant step in the transformation of screening enabling more accurate detection when used in conjunction with a radiologist examining every mammogram,” said lead investigator Associate Professor Helen Frazer, of St Vincent’s BreastScreen Melbourne.
The Breast Cancer Network Australia’s director of policy and advocacy Vicki Durston said the research was a timely reminder that screening must keep pace with science.
“The study’s findings show how quickly the evidence around AI-supported risk assessment is advancing – and why Australia must now look beyond a one-size-fits-all model,” she said.
“AI is not the whole answer, but the emerging evidence shows real potential to strengthen how we understand risk and support earlier detection for every woman.”
What are the breast cancer screening guidelines?
In Australia, women aged 50 to 74 are invited to have a free screening mammogram every two years through the BreastScreen Australia program. Women aged 40 to 49, as well as those 75 and over, can also access free mammograms.
If you have a strong family history of breast or ovarian cancer, it’s worth speaking with your GP about when you should start screening and how often you may need it. You can also contact BreastScreen Australia directly on 13 20 50 to discuss your options.
