Lectures and seminars Faculty event: Mikael Eriksson
Speaker: Mikael Eriksson
From short-term to long-term risk assessment of breast cancer.
Traditional risk assessment models for breast cancer have primarily relied on lifestyle factor, family history, and genetic determinants. However, these models are limited in their ability to predict the individual risk of breast cancer.
The introduction of AI techniques in breast cancer risk assessment has taken the field to a new level. By analysing vast amounts of image data, deep learning algorithms can identify mammographic patterns and find associations with the outcome that traditional models do not capture. By also using the available mammographic screening infrastructure to capture the additional mammographic patterns beyond breast cancer detection, risk assessment has the potential to scale to the general female population.
In this talk I will describe the development and evaluation of image-derived risk assessment models for improving screening outcomes and for use in risk reduction strategies. I will also talk about our work on clinical trials for risk reduction and personalized screening and, examples of using image-based risk assessment in the clinic.
About the speaker
Mikael Eriksson is a post-doctoral researcher at the department of Medical Epidemiology and Biostatistics at Karolinska Institutet. He also has an affiliation with Cambridge University. His research focuses risk assessment of breast cancer.
Join the faculty event in Wargentin! After the seminar, the faculty lunch will be served in Ljusgården.