IVCVJul 8, 2025

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

arXiv:2507.06410v2h-index: 22025 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD)
Originality Incremental advance
AI Analysis

This work addresses the problem of standardizing breast density assessments for clinical practice, which is incremental as it builds on existing deep learning methods with enhancements.

The study tackled automated binary classification of breast density in mammography using an ensemble of deep learning models with attention mechanisms, achieving an AUC of 0.963 and F1-score of 0.952.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes