Breast density prediction model in digital versus synthetic mammograms from a radiomic point of view: A retrospective study

Abstract

Purpose: In this retrospective study, we develop radiomics prediction models from synthetic mammograms(SM) and digital mammograms(DM) images to identify which imaging modality has the most predictive power when employed for prediction of breast density. Methods: Patients aged between 45 and 74 years, were included in the study. For each, a SM in standard resolution (ST) and High Resolution (HR) were obtained, and a 150 x 150 pixels square area was defined on the images to be used for texture analysis of the breast parenchyma. A semi-automated placing strategy was used to reduce user reliance on the segmentation location. S-IBEX software was employed to extract radiomics features. Feature robustness analysis was also done to ensure model reproducibility. The Least Absolute Shrinkage and Selection Operator(LASSO) logistic regression model was trained to predict dichotomized breast density according to BIRADS classification model performance was assessed through receiver operating curves (ROC) for DM, HR, and ST. Results: We extracted 123 features from the 10 ROIs of 96 patient. After robustness analysis, the most predictive features were employed to build logistic regression-based models. The average performance of the models were 0.74, 0.67, and 0.64 on DM, HR, and ST, respectively, suggesting that DM maintains the highest informative content on breast density. Conclusions: This study investigated how well radiomics models trained on various imaging modalities predicted breast density. Our results may be pertinent to the debate over screening mammography technique optimization using quantitative measures based on radiomics features.