Dual-View Colorized Mammogram ROIs With EfficientNet-B7 and Attention Network for Breast Lesion Classification
Open Access
- 2 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 35511-35526
Abstract
Breast cancer diagnosis using mammography can be significantly enhanced by integrating information from multi-source fusion and complementary imaging perspectives. In this paper, we propose a novel deep learning framework with dataset fusion for breast lesion classification. In particular, our approach fuses mammogram datasets of both Medio-Lateral-Oblique (MLO) and Cranio-Caudal (CC) views in four breast lesion categories from two data sources to ensure comprehensive lesion representation with total 5,906 images, and a combined EfficientNet-B7 and Multi-Head Attention (MHA) network is applied to classify these breast lesion categories. Therefore, the largest Region of Interest (ROI) in each image is extracted and then colorized before inserted into the network for lesion classification. Two colorized MLO and CC ROIs are separately processed by two parallel EfficientNet-B7 networks to produce the combined high-level features. The combined feature vectors from the dual EfficientNet-B7 network are then concatenated to yield a unified feature representation, which is subsequently refined using the MHA network to prioritize the most salient patterns and suppress background noise before classified using a fully connected head. To select an optimal classification model for these breast lesion categories, we performed four different models for two cases with and without an MHA network. Therefore, extensive experiments on integrated multi-source mammogram datasets demonstrate that the proposed framework outperforms conventional single-view and non-attentive models, achieving around 93.9% accuracy for breast lesion classification. It is obvious that the use of MHA improves accuracy by about 2% compared to not using it. The results highlight the value of dataset fusion and MHA-based feature selection in advancing computer-aided mammography.Keywords
Funding Information
- Ho Chi Minh City University of Technology and Engineering, Vietnam (T2026-10NTD)
This publication has 41 references indexed in Scilit:
- Global patterns and trends in breast cancer incidence and mortality across 185 countriesNature Medicine, 2025
- Utilizing Pseudo Color Image to Improve the Performance of Deep Transfer Learning–Based Computer-Aided Diagnosis Schemes in Breast Mass ClassificationJournal of Imaging Informatics in Medicine, 2024
- Mammography classification with multi-view deep learning techniques: Investigating graph and transformer-based architecturesMedical Image Analysis, 2024
- Dual view deep learning for enhanced breast cancer screening using mammographyScientific Reports, 2024
- Breast lesion classification from mammograms using deep neural network and test-time augmentationNeural Computing and Applications, 2023
- VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammographyScientific Data, 2023
- Memory-aware curriculum federated learning for breast cancer classificationComputer Methods and Programs in Biomedicine, 2022
- Attention-based deep learning for breast lesions classification on contrast enhanced spectral mammography: a multicentre studyBritish Journal of Cancer, 2022
- Current and future burden of breast cancer: Global statistics for 2020 and 2040The Breast, 2022
- Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound examsNature Communications, 2021