Breast area affects the performance of a commercial artificial intelligence algorithm assessment of negative digital breast tomosynthesis exams.
Authors
Affiliations (5)
Affiliations (5)
- Duke University School of Medicine, 40 Duke Medicine Circle, 124 Davison Building, Durham, NC 27710, United States. Electronic address: [email protected].
- iCAD, 2 Townsend West, Suite 6, Nashua, NH 03063, United States. Electronic address: [email protected].
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC 27710, United States. Electronic address: [email protected].
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC 27710, United States. Electronic address: [email protected].
- Department of Radiology, Duke University School of Medicine, 2301 Erwin Road, Durham, NC 27710, United States. Electronic address: [email protected].
Abstract
To understand whether cancer-neutral image attributes (breast area and number of slices) impact an AI algorithm assessment of negative digital breast tomosynthesis (DBT) screening exams. This retrospective cohort study included women from a single institution whose screening mammogram was interpreted as negative between 2016 and 2019. All patients had at least 2 years follow-up without evidence of malignancy. Primary outcome measures were AI-calculated assessment of present and future likelihood of malignancy, quantified as a case and risk score. A multivariable linear regression model evaluated the relationship between patient demographics (age, race/ethnicity), image size (breast area, number of slices), and AI algorithm outputs (breast density, case score, risk score). There were 4842 female patients included in the study (mean age 55.0 ± 10.6 years). For case score, there was a positive association with breast area (p < 0.0001), as well as older age, breast density (scattered vs fatty), and race (White vs Asian and Black vs White, all p < 0.05). For risk score, there was also a positive association with breast area (p < 0.001), as well as older age, breast density (scattered vs fatty, heterogeneously dense vs scattered, extremely dense vs heterogeneously dense), and race (White vs Asian, all p < 0.05). Number of DBT slices was not significantly associated with either case or risk scores. Known breast cancer risk factors and one neutral characteristic (breast area), significantly impacted an AI algorithm's assessment of present and future likelihood of malignancy.