AI-assisted imaging tool for breast cancer could tailor screening for women according to individual risk
An artificial intelligence model that analyzes women's past and recent annual 3D mammograms is more effective at predicting the five-year risk of developing breast cancer than a tool that uses only the most recent 3D mammogram, as well as an AI model that analyzes 2D mammograms, a new study shows.
Researchers at NYU Langone Health developed an AI-assisted imaging tool called NYU-DRP, which analyzes multiple years of a woman's 3D mammograms to predict the risk of developing breast cancer within five years. The tool outperformed others in predicting higher-risk cases, correctly identifying those at higher risk 72% of the time, compared to 70% and 68% for single DBT and AI-assisted 2D testing, respectively.
NYU-DRP was created using 313,531 yearly 3D mammograms from 161,165 women without breast cancer who had tests at NYU Langone hospitals between 2016 and 2020. When compared to the Tyrer-Cuzick risk assessment, NYU-DRP was more effective, correctly predicting higher-risk cases 67% of the time, while Tyrer-Cuzick accurately predicted 56% of the time.
The study found that breast density alone did not accurately predict a woman's risk, as dense tissue was misclassified in some cases. The NYU-DRP model identified a lower percentage of women with less-dense, fatty breasts as high-risk compared to actual cases. Researchers plan to further test the tool and share data with other academic centers and 3D mammogram manufacturers.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
