Wanders JOP, et al. - Given that texture patterns improve breast cancer risk segregation along with area-based mammographic density, experts aimed to study the additional value of texture pattern scores on top of volumetric mammographic density measures in a large screening cohort. An association of deep-learning-based texture pattern scores, measured automatically on digital mammograms, with breast cancer risk was seen, independent of volumetric mammographic density. This enhances the ability to differentiate between future breast cancer and non-breast cancer cases.

Methods

• The volumetric mammographic density and texture pattern scores were automatically evaluated for the first available digital mammography (DM) screening examination of 51,400 women (50–75 years of age) participating in the Dutch biennial breast cancer screening program between 2003 and 2011.
• They developed the texture assessment method in a previous study and validated it in the current study.
• From the screening registration system and through linkage with the Netherlands Cancer Registry, breast cancer information was gotten.
• They excluded all screen-detected breast cancers diagnosed at the first available digital screening examination.
• A total of 301 women were diagnosed with breast cancer, during a median follow-up period of 4.2 (interquartile range [IQR] 2.0–6.2) years.
• Using Cox proportional hazard analyses, researchers determined the relationships between texture pattern scores, volumetric breast density measures and breast cancer risk.
• Using c-indices, discriminatory performance was assessed.

Results

• The median age of the women at the time of the first available digital mammography examination was 56 years (IQR 51–63).
• Findings suggested a positive association of texture pattern score with breast cancer risk (hazard ratio [HR] 3.16 [95% CI 2.16–4.62] [p value for trend < 0.001], for quartile [Q] 4 compared to Q1).
• Results demonstrated that the c-index of texture was 0.61 (95% CI 0.57–0.64).
• Dense volume and percentage dense volume had positive associations with breast cancer risk (HR 1.85 [95% CI 1.32–2.59] [p value for trend < 0.001] and HR 2.17 [95% CI 1.51–3.12] [p value for trend <0.001], respectively, for Q4 compared to Q1)
• Experts noted that when adding texture measures to models with dense volume or percentage dense volume, c-indices increased from 0.56 (95% CI 0.53–0.59) to 0.62 (95% CI 0.58–0.65) (p < 0.001) and from 0.58 (95% CI 0.54–0.61) to 0.60 (95% CI 0.57–0.63) (p=0.054), respectively.