Lead researcher
CIA Dr Linh Nguyen, CIB Prof John Hopper, CIC Dr Gillian Dite, CID Dr Shuai Li, CIE Prof Pam Bell, CIF Mrs Gerda Evans and CIG Prof Joohon Sung
Institution
Melbourne School of Population & Global Health, University of Melbourne
Tumour type:
Breast
Years funded
2021-2023
Project description
It’s well known that breast density, the white areas on a mammogram, creates a major problem for screening by hiding existing cancers from the radiologist’s view. This project will develop an accurate and automated personalised screening tool incorporating our new measures of risk based on mammograms.
What is the need?
The major outcome of this project will be the demonstration of how automated risk measurements could be generated by breast screening services to enable a move to more effective, tailored screening, which is based on risk. By quantifying how strong new mammogram-based risk measures are when used alone and combined, we will produce clinical models which can inform screening services of the potential of tailored screening.
I am motivated to implement our new measures of breast cancer risk to improve outcomes, with a realistic goal of making an impact on breast cancer control in Australia and for all women across the world.
What are you trying to achieve?
By learning about breast cancer risk and developing automated clinical tools, we propose to better use mammography in a way that improves detection, lowers harm, reduces costs and can be quickly put into practice, to prevent women dying from breast cancer.
How important is this funding?
Like so many who have recently started an early-career in research, I quickly learnt that it is becoming more and more difficult to obtain research grants. My research team and I therefore are humble and grateful to get such generous funding from donors to Cancer Council Victoria.
Project timeline
Timeline |
2021 |
2022 |
2023 |
Develop automated and better risk measures based on mammogram and test how well they apply. |
|
|
|
Use three large Australian cohort studies to determine how our new risk factors combine with each other, and with established epidemiological risk factors, to predict risk. |
|
|
|
Develop automated clinical tools based on combinations of risk factors so health professionals can decide what data to collect and how to use it to improve screening and prevention. |
|
|
|
Award / Duration
3 years