"...a new, interpretable #AI-model to predict five-year breast cancer risk from mammograms"

"...a new, interpretable #AI-model to predict five-year breast cancer risk from mammograms"

“We can, with surprisingly high accuracy, predict whether a woman will develop cancer in the next 1 to 5 years based solely on localized differences between her left and right breast tissue,” he said. “This could have public impact because it could, in the not-too-distant future, affect how often women receive mammograms.”

https://www.rsna.org/news/2024/march/deep-learning-for-predicting-breast-cancer

https://pubs.rsna.org/doi/10.1148/radiol.232780?_gl=1*1jiogwy*corpRollup_ga*MTk3NjA2MjMxNC4xNzIyNDM3MTA3*corpRollup_ga_EQ32SZ84M3*MTcyMjQzNzEwNi4xLjEuMTcyMjQzNzQwMC42MC4wLjA.

Thank you Eugenia Praloran for tagging me. The proposal to reduce the frequency of mammograms based on a predictive model such as AsymMirai raises important questions and requires careful evaluation. 1. Potential advantages: 1.1. Reduced burden on patients: Reducing the frequency of mammograms could reduce the anxiety and inconvenience associated with this exam for many women. 1.2. Optimization of resources: If the model proves to be highly accurate, it could allow for more efficient allocation of healthcare resources. 2. Disadvantages and considerations: 2.1. Limitations of the model: Although AsymMirai shows good performance, it is important to remember that no model is perfect. There are multiple factors that influence the development of breast cancer that may not be captured by an image-based model, such as genetic, hormonal, and environmental factors. ...

Eugenia Praloran

Dentist. Journalist. Theatre researcher and author

7 个月

要查看或添加评论,请登录

Ken Wasserman的更多文章

社区洞察

其他会员也浏览了