Development and validation of an improved volumetric breast density estimation model using the ResNet technique.
Authors
Affiliations (6)
Affiliations (6)
- Radiology Center, Kindai University Hospital, 377-2, Ono-higashi, Osaka-sayama, Osaka, 589-8511, JAPAN.
- Kindai University, 377-2, Ono-higashi, Osaka-sayama, Osaka, 589-8511, JAPAN.
- Faculty of Informatics, and Cyber Informatics Research Institute, Kindai University , 3-4-1, Kowakae, Higashi-osaka, Osaka, 577-8502, JAPAN.
- Faculty of Medicine, Kindai University, 377-2, Ono-higashi, Osaka-sayama, Osaka Prefecture, 589-8511, JAPAN.
- Plusman LLC, 1-3-6 Hirakawacho, Chiyoda-ku, Tokyo, 102-0093, JAPAN.
- Niigata University, 2-746, Asahimachi-dori, Chuo-ku, Niigata , 951-8518, JAPAN.
Abstract

Temporal changes in volumetric breast density (VBD) may serve as prognostic biomarkers for predicting the risk of future breast cancer development. However, accurately measuring VBD from archived X-ray mammograms remains challenging. In a previous study, we proposed a method to estimate volumetric breast density using imaging parameters (tube voltage, tube current, and exposure time) and patient age. This approach, based on a multiple regression model, achieved a determination coefficient (R²) of 0.868. 
Approach:
In this study, we developed and applied machine learning models-Random Forest, XG-Boost-and the deep learning model Residual Network (ResNet) to the same dataset. Model performance was assessed using several metrics: determination coefficient, correlation coefficient, root mean square error, mean absolute error, root mean square percentage error, and mean absolute percentage error. A five-fold cross-validation was conducted to ensure robust validation. 
Main results:
The best-performing fold resulted in R² values of 0.895, 0.907, and 0.918 for Random Forest, XG-Boost, and ResNet, respectively, all surpassing the previous study's results. ResNet consistently achieved the lowest error values across all metrics. 
Significance:
These findings suggest that ResNet successfully achieved the task of accurately determining VBD from past mammography-a task that has not been realised to date. We are confident that this achievement contributes to advancing research aimed at predicting future risks of breast cancer development by enabling high-accuracy time-series analyses of retrospective VBD.
.