tsta

فارسی

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Late Fusion-Based Deep Learning for Breast Cancer Classification in Mammography

Authors :

Mehdi Baharloo¹ Ata Jodeiri²

1- دانشگاه علوم پزشکی تبریز 2- دانشگاه علوم پزشکی تبریز

Keywords :

Breast cancer،Mammograghy،Deep lreaning،Late fusion،BI_RADS

Abstract :

This study investigates a late fusion framework for breast cancer classification in mammography using deep learning. Two EfficientNet-B0 models were trained independently on craniocaudal (CC) and mediolateral oblique (MLO) mammographic views. Their outputs were integrated via a fully connected late fusion layer. Experimental evaluation on a dataset collected from two hospitals showed that single-view models achieved 82.14% accuracy with perfect sensitivity but limited specificity, while the late fusion model improved performance to 92.86% accuracy, 1.000 sensitivity, and 0.8667 specificity. The proposed lightweight fusion framework is computationally efficient and particularly suitable for small, clinically curated datasets. These results confirm that multi-view late fusion reduces false positives and enhances diagnostic reliability in computer-aided mammography. Moreover, our deterministic and lightweight fusion enables faster inference compared with probabilistic or transformer-based fusion methods.