Skip to Content

Mammography-Based AI Model May Predict Breast Cancer Risk

FRIDAY, Feb. 5, 2021 -- The mammography-based deep learning (DL) risk model, Mirai, demonstrates improved discriminatory capacity for identifying high-risk breast cancer over prior models and DL approaches, according to a study published in the Jan. 27 issue of Science Translational Medicine.

Adam Yala, from the Massachusetts Institute of Technology (MIT) in Cambridge, and colleagues developed Mirai, a mammography-based DL model designed to predict risk at multiple time points and produced predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) and was tested on test sets from MGH, Karolinska University Hospital in Stockholm, and Chang Gung Memorial Hospital (CGMH) in Taoyuan City, Taiwan.

The researchers obtained C-indices of 0.76, 0.81, and 0.79 for test sets from MGH, the Karolinska University Hospital, and CGMH, respectively. Significantly higher five-year receiver operating characteristic areas under the curve were obtained with Mirai versus the Tyrer-Cuzick model and prior DL models: Hybrid DL and Image-Only DL, trained on the same dataset. Across all datasets, high-risk patients were identified more accurately with Mirai than with prior methods. On the MGH test set, of the patients who would develop cancer within five years, 41.5, 36.1, and 22.9 percent were identified as high-risk with the Mirai, Hybrid DL, and Tyrer-Cuzick models, respectively.

"Mirai demonstrated improved discriminatory capacity over the state-of-the-art clinically adopted Tyrer-Cuzick and prior deep learning approaches Hybrid DL and Image-Only DL," the authors write.

Several authors disclosed financial ties to the biopharmaceutical industry; MIT and MGH filed patents regarding Mirai.

Abstract/Full Text

© 2021 HealthDay. All rights reserved.

Read this next

Two Cases of SARS-CoV-2 Variant P.1 Identified in Minnesota

FRIDAY, March 5, 2021 -- Two cases of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variant P.1 identified in Minnesota are described in a report published in...

Three Modes of Transmission Explain Most Giardiasis Outbreaks

FRIDAY, March 5, 2021 -- Three main modes of transmission have been identified for giardiasis outbreaks in the United States in 2012 to 2017, although a single transmission mode...

Ambulatory Function Poorer for Older Cancer Survivors

FRIDAY, March 5, 2021 -- Cancer survivors have poorer ambulatory function, which is associated with increased mortality, according to a study published online March 4 in Cancer...

More News Resources

Subscribe to our Newsletter

Whatever your topic of interest, subscribe to our newsletters to get the best of in your inbox.