Machine learning-based analysis of average glandular dose in mammography: The role of breast density

Average glandular dose (D_g) is the primary metric for assessing radiation risk in screening mammography. Although D_g analysis is commonly interpreted according to compressed breast thickness (CBT), breast density (BD) may significantly influence D_g. This study evaluated the influence of BD on D_g variability using the TG282-based dosimetry model and a machine learning approach.

The cross-sectional study included 1233 full-field digital mammography images from three mammography units. D_g was estimated using a TG282-based model. Images were stratified by CBT, view (CC and MLO), and BD (ACR BI-RADS). Non-parametric tests and Spearman's correlation assessed group differences and associations. A Random Forest (RF) regression model was implemented to explore non-linear relationships between D_g and age, CBT, compression force, and BD. Model performance was assessed using R², MAE, and MAPE. Feature importance analysis identified the contribution of each predictor. D_g,75 benchmarks were defined as the 75th percentile of D_g distributions stratified by BD and CBT.

D_g distributions were non-normal, and D_g was higher in MLO than CC views (p < 0.05). Significant differences were observed across CBT and BD categories. D_g correlated positively with mAs and exposure time, while BD and compression force showed moderate associations. Within the four-predictor RF model (R² = 0.56, MAPE = 14.38 %), compression force (45.72 %) and BD (23.93 %) had the highest relative feature importance. D_g,75benchmarks increased with BD within CBT groups.

Incorporating BD improves the characterisation of D_g variability in mammography. The RF model characterised multivariable relationships between BD and compression-related factors, supporting more anatomically informed dose optimisation strategies.

BD-stratified D_g,75benchmarks may improve identification of atypical dose values and support targeted dose monitoring in mammography.