Developing and implementing BREAST II as an interactive research and educational platform to transform breast cancer detection.
Early diagnosis of breast cancer results in a 97% survival rate. However, to achieve this survival rate and even more importantly to achieve zero deaths from breast cancer by 2030, we must significantly reduce the 30-40% of breast cancers that fail to be diagnosed. Through BREAST, a world-first research and educational interactive infrastructure that uses the latest technological innovations, over the last 4-5 years, we, with local and international experts have identified reasons for mis-diagnoses and presented exciting translational solutions. To date the work has been shown to improve radiologists' performance by a mean value of 34%, an improvement unparalleled by any other innovation in recent years. Its unprecedented success has led to engagement by 80% of breast-reading clinicians across all states in Australia and research agreements with world-leading imaging scientists across Australia, North and South America, Asia and Europe. It has contributed to 20 PhD projects and 70 publications.
We have a clear plan for consolidating our achievements with BREAST so that early breast cancer diagnosis within screening and symptomatic facilities continues to be transformed. It also provides a comprehensive work schedule enabling the introduction of 5 highly exciting innovations reflecting recent technological advancements, social responsibilities and educational needs. With regard to these innovations, BREAST II will specifically incorporate:
• Digital breast tomosynthesis (DBT) image sets: DBT is rapidly transforming breast cancer imaging in Australia and elsewhere, however currently there is no on-line training and performance monitoring system anywhere;
• Data files focusing on underserved populations: women of different cultures have different breast densities thus effectiveness of detecting cancer may vary. We will focus on indigenous populations in Australia and women in China and Southeast Asia;
• Educational image sets of high difficulty: particularly those with architectural distortion and lesion speculation so that readers can focus learning in these areas;
• Data sets designed for registrar radiologists.
• Pathology image files for pathologists: pathology is considered to be the diagnostic truth, however agreement between pathologists can be as low as 48%.
Each of the above items can be a PhD project.
The opportunity ID for this research opportunity is 2195