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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sharifian, Peyman, Hong, Xiaotong, Karimian, Alireza, Amini, Mehdi, Arabi, Hossein
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911049105539072
author Sharifian, Peyman
Hong, Xiaotong
Karimian, Alireza
Amini, Mehdi
Arabi, Hossein
author_facet Sharifian, Peyman
Hong, Xiaotong
Karimian, Alireza
Amini, Mehdi
Arabi, Hossein
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography
Sharifian, Peyman
Hong, Xiaotong
Karimian, Alireza
Amini, Mehdi
Arabi, Hossein
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.06410