A Novel Algorithm for Classification Of Mammographic Breast Density (MBD) Towards Breast Cancer Prediction From Digital Mammograms

DOI

10.2991/978-94-6463-852-3_32How to use a DOI?

Keywords

Breast Cancer Prediction; Early Diagnosis; Risk Prediction Models; ML; DL; Hybrid Learning; Boosting (XGBoost); CNNs; Breast Density Imaging; Heart Risk Factors; SHAP Insights; LASSO Regression; Decision Aid Systems; Model Testing

Abstract

It remains among the most common causes of cancer death. The disease therefore has to take its share in the midst. Thus, discovering an effective early detection method and the precise forecasting tools is the crucial need at present. The new developments in machine learning, deep learning, and medical imaging have significantly improved predictability in breast cancer. This review will be focused on a deeper analysis of the most recent works put out on different prediction methodologies, which involve traditional machine learning algorithms as well as fusion deep learning models and the influence of mammographic breast density on disease prognosis and cardiovascular risk. The findings are that the techniques, such as decision trees, ensemble learning models like XGBoost and even deep convolutional neural networks, show the highest prediction accuracy. Mammographic breast density and tumor characteristics have also been described to possess prognostic value, which might be used in addition to risk stratification for both breast cancer and cardiovascular disease. Advanced computational models have the potential to enable early detection and more informed clinical decisions, though problems like dataset sizes, model complexity, and generalizability have to be overcome. The future directions of the study are discussed, along with how more interpretive models can be best utilized to achieve external validation and potential inclusion of other clinical features to improve predictive performance.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ammara Bandarkar
AU  - Misba Khan
AU  - Tawadi Khan
AU  - Tanveer Khan
AU  - Tabassum Maktum
PY  - 2025
DA  - 2025/10/07
TI  - A Novel Algorithm for Classification Of Mammographic Breast Density (MBD) Towards Breast Cancer Prediction From Digital Mammograms
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 503
EP  - 516
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_32
DO  - 10.2991/978-94-6463-852-3_32
ID  - Bandarkar2025
ER  -