Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography

TL;DR

This paper introduces an automated deep learning ensemble system with attention mechanisms and a novel loss function for accurate breast density classification in mammography, aiming to improve screening consistency and early detection.

Contribution

It presents a new ensemble approach combining multiple CNNs with attention modules and a novel loss function to enhance classification accuracy in breast density assessment.

Findings

Achieved high AUC of 0.963 and F1-score of 0.952.

Outperformed individual models in density classification.

Demonstrated potential for clinical standardization and improved screening.

Abstract

Breast density assessment is a crucial component of mammographic interpretation, with high breast density (BI-RADS categories C and D) representing both a significant risk factor for developing breast cancer and a technical challenge for tumor detection. This study proposes an automated deep learning system for robust binary classification of breast density (low: A/B vs. high: C/D) using the VinDr-Mammo dataset. We implemented and compared four advanced convolutional neural networks: ResNet18, ResNet50, EfficientNet-B0, and DenseNet121, each enhanced with channel attention mechanisms. To address the inherent class imbalance, we developed a novel Combined Focal Label Smoothing Loss function that integrates focal loss, label smoothing, and class-balanced weighting. Our preprocessing pipeline incorporated advanced techniques, including contrast-limited adaptive histogram equalization (CLAHE) and comprehensive data augmentation. The individual models were combined through an optimized ensemble voting approach, achieving superior performance (AUC: 0.963, F1-score: 0.952) compared to any single model. This system demonstrates significant potential to standardize density assessments in clinical practice, potentially improving screening efficiency and early cancer detection rates while reducing inter-observer variability among radiologists.