1 IN 2
IS TOO MANY

1 in 2 of us will be diagnosed with cancer by age 85.
Donate now

Striving for a cancer-free future

Automated measures that predict risk and masking of breast cancer

Lead researcher

Prof John Hopper, Dr Daniel Schmidt, Dr Enes Makalic, Dr Louise Keogh, Dr Helen Frazer, Dr Pierre-Antoine Dugue, Dr Ralph Highnam, Mr Kevin Nguyen, Dr Jill Evans

Institution
The University of Melbourne

Tumour type:
Breast

Years funded
2017-2019

What is the project?

This project will develop automated measures from mammograms that predict masking and risk, and pilot its implementation into a BreastScreen service.

What are you trying to achieve?

We will try to minimise the negative aspects to mammographic screening by developing new, improved and automated measures of a woman’s risk (a) of having a breast tumour missed due to having dense breasts, and (b) of breast cancer itself. This will allow women attending mammographic screening at BreastScreen to be given, at the time of their screening, more appropriate management and screening advice to achieve better outcomes.

Mammographic density is one of the strongest predictors of breast cancer risk but its impractical measurement prevents its use in a clinical setting. An automated procedure that determines which aspects of a mammogram best predict cancer would allow screening programs to identify and target women at higher risk of breast cancer, which in turn could lead to earlier diagnoses and better breast cancer outcomes.

Funding Body

Cancer Council Victoria Research Grant