Dr Helen Frazer named Innovator of the Year at Women in AI Awards


Pictured: Dr Helen Frazer at the 2022 WAI Awards Australia and New Zealand 

A research study exploring the use of artificial intelligence (AI) to analyse mammograms has earned the Clinical Director of St Vincent’s BreastScreen this year’s top accolade as Innovator of the Year at the Women in AI Awards Australia and New Zealand. 

Adjunct Associate Professor Helen Frazer was honoured to receive the prestigious award, along with also winning the Health Category, for globally unique research she is leading that aims to improve the accuracy of breast cancer screening.    

The project, known as BRAIx, is being jointly developed by St Vincent’s Hospital Melbourne, St Vincent’s Institute of Medical Research, BreastScreen Victoria, University of Melbourne and the Australian Institute of Machine Learning at the University of Adelaide, in partnership with the Aikenhead Centre for Medical Discovery (ACMD).   

“The use of AI models may be a significant step in transforming screening, enabling more accurate detection when used in conjunction with a radiologist examining every mammogram,” says Dr Frazer, who has worked in breast cancer screening for over 20 years.  

Research path  

The new AI-based models being investigated aim to better detect cancer, lower unnecessary recalls to assessment, and improve timeliness, efficiency and participation, explains Dr Frazer. Ultimately, it is hoped this can provide a more effective and personalised breast screening service to women.    

Through this research, the team hopes to also demonstrate that using AI models will help reduce the occurrence of interval cancers that were not able to be detected at the time of screening and reduce the number of women recalled for assessment who are subsequently determined to not have cancer.  

“We are examining the use of AI algorithms to address the challenges radiologists face in reading mammograms. AI holds promise to recognise patterns in mammograms and other client data that will assist radiologists in better decision making,” says Dr Frazer.   

The research is also looking into the potential to use AI models to better predict risk of breast cancer and enable tailoring of the screening program to women at higher risk.    

Next-step testing  

Since its inception in 2020, the BRAIx project has moved from working in cancer-enriched data to testing AI algorithms in retrospective and prospective studies in real-world breast screening services.    

“This is a really important requirement for testing artificial intelligence solutions for wider use and implementation in a healthcare setting,” explains Dr Frazer. 

“The algorithms we are investigating are at an early stage and there is still more research work to do but we are hopeful they will transform the women’s experience of breast cancer screening and save more lives.”