Machine learning-based analysis of average glandular dose in mammography: The role of breast density
Radiography · 2026
DOI: 10.1016/j.radi.2026.103545 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiography, 2026. Verfasst von A González-Ruíz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro #1, Sta María Tonanzintla, 72840 San Andrés Cholula, Puebla, Mexico; Insti…. Hauptthemen laut MEDLINE: Mammography, Radiation Dosage, Machine Learning, Breast Density. Die Arbeit nennt 36 Literaturangaben.
Abstract (Originalsprache)
INTRODUCTION: Average glandular dose (Dg) is the primary metric for assessing radiation risk in screening mammography. Although Dg analysis is commonly interpreted according to compressed breast thickness (CBT), breast density (BD) may significantly influence Dg. This study evaluated the influence of BD on Dg variability using the TG282-based dosimetry model and a machine learning approach. METHODS: The cross-sectional study included 1233 full-field digital mammography images from three mammography units. Dg 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 Dg 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. Dg,75 benchmarks were defined as the 75th percentile of Dg distributions stratified by BD and CBT. RESULTS: Dg distributions were non-normal, and Dg was higher in MLO than CC views (p < 0.05). Significant differences were observed across CBT and BD categories. Dg 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. Dg,75benchmarks increased with BD within CBT groups. CONCLUSION: Incorporating BD improves the characterisation of Dg variability in mammography. The RF model characterised multivariable relationships between BD and compression-related factors, supporting more anatomically informed dose optimisation strategies. IMPLICATIONS FOR PRACTICE: BD-stratified Dg,75benchmarks may improve identification of atypical dose values and support targeted dose monitoring in mammography.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro #1, Sta María Tonanzintla, 72840 San Andrés Cholula, Puebla, Mexico; Instituto Nacional de Investigaciones Nucleares, Carretera La Marquesa S/N,…
- Facultad de Medicina, Universidad Autónoma del Estado de México, Paseo Tollocan S/N, Toluca, Estado de México 50130, Mexico.
- Hospital de Ginecología y Obstetricia, Instituto Materno Infantil del Estado de México, Puerto de Palos S/N, Isidro Fabela Primera Secc, 50170 Toluca de Lerdo, Mexico.
- Instituto Nacional de Investigaciones Nucleares, Carretera La Marquesa S/N, Ocoyoacac, 52750, Estado de México, Mexico.
- Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro #1, Sta María Tonanzintla, 72840 San Andrés Cholula, Puebla, Mexico.
- Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro #1, Sta María Tonanzintla, 72840 San Andrés Cholula, Puebla, Mexico. Electronic address: hperegrina@inaoep.mx.
Zitieren
APA
González-Ruíz, A., Sánchez Mendoza, H. I., Ferreira Martinez, C., Santos-Cuevas, C. L., Ortiz-Oliveros, H. B., Hernández Farías, D. I., & Peregrina-Barreto, H. (2026). Machine learning-based analysis of average glandular dose in mammography: The role of breast density. Radiography. https://doi.org/10.1016/j.radi.2026.103545
Vancouver
González-Ruíz A, Sánchez Mendoza HI, Ferreira Martinez C, Santos-Cuevas CL, Ortiz-Oliveros HB, Hernández Farías DI, et al. Machine learning-based analysis of average glandular dose in mammography: The role of breast density. Radiography. 2026. doi:10.1016/j.radi.2026.103545
BibTeX
@article{GonzlezRuz2026,
author = {González-Ruíz, A and Sánchez Mendoza, H I and Ferreira Martinez, C and Santos-Cuevas, C L and Ortiz-Oliveros, H B and Hernández Farías, D I and Peregrina-Barreto, H},
title = {Machine learning-based analysis of average glandular dose in mammography: The role of breast density},
journal = {Radiography},
year = {2026},
doi = {10.1016/j.radi.2026.103545}
}
EUVIMED