Abstract 4632: Automated quantitative measures of terminal duct lobular unit involution and breast cancer risk

Background Terminal duct lobular units (TDLUs) involute with age. Prior studies using qualitative or semi-quantitative measures of TDLU involution found inverse associations with breast cancer (BC) risk. We applied our validated deep learning computational method to yield quantitative measures of TDLU involution in normal breast tissue and then assessed their association with established BC risk factors and BC risk. Materials and Methods This study used a nested case-control design within the Nurses' Health Study cohorts. Cases and controls were diagnosed with benign breast disease (BBD) and cases subsequently developed BC (median 7.75 years later). Cases and controls were matched on year of BBD diagnosis, age at BC diagnosis (or index date for controls), and years between BBD and BC diagnosis (or index date). We applied our computational method to 3951 whole slide images of normal breast tissue from BBD biopsies (287 cases and 1083 controls; median 3 images per woman). Quantitative estimates of TDLU involution were derived for 3 standardized measures (median TDLU span, TDLU count per non-adipose tissue area, median acini count) and 5 novel measures (median TDLU area, TDLU area as a percentage of total tissue area, TDLU area as a percentage of total non-adipose tissue area, acini count per non-adipose tissue area, median acini density). TDLU involution was also manually categorized in 177 cases and 857 controls. Associations between TDLU involution measures and risk factors were evaluated among controls using Spearman's rho or Chi-squared tests. The relationship between each measure and BC risk was evaluated using logistic regression models controlling for the matching factors and BBD histological subtypes. Results All 8 TDLU measures were significantly inversely correlated with age at BBD biopsy (range: rho -0.07 to -0.42; p