Deep-Learning Can Provide Fully-Automated Analysis Of Breast Density.

Aunt Minnie (2/9, Ridley) reports that a new study published online on January 24, 2018, in Medical Physics presents a deep-learning algorithm that can provide a fully-automated analysis of breast density on screening mammography exams, including density estimates that correlate well with assessments provided by radiologists. Researchers from the University of Pittsburgh Medical Center trained a deep-learning algorithm “to segment dense fibroglandular tissue on mammograms.” In testing, “the algorithm’s calculation of breast percent density (PD) correlated well with radiologists’ classifications of breast density using BI-RADS, and it also outperformed an existing breast density estimation algorithm, according to the authors.”

Author: Nicole Hardy

Categories: NewsNumber of views: 206