BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography

2026-07-11

AI Summary

This study addresses the significant challenges in mammographic mass segmentation and benign-malignant classification, which arise from ambiguous boundaries, tissue heterogeneity, and low contrast. To tackle these issues, the authors propose BiLoG-Net, an end-to-end multitask network featuring a novel tightly coupled architecture that integrates dual-context position-aware modeling, a lightweight global-local feature enhancement module, and a segmentation-guided attention mechanism. This design simultaneously captures fine boundary details and long-range dependencies while producing spatially interpretable malignancy predictions. Evaluated on the CBIS-DDSM and INBreast datasets, BiLoG-Net achieves Dice scores of 94.20% and 93.10%, classification accuracies of 95.20% and 93.60%, and AUC values of 97.10% and 96.00%, respectively, substantially outperforming existing CNN- and Transformer-based baselines.

Abstract

Breast cancer remains the most commonly diagnosed malignancy among women worldwide, yet accurate detection and characterization of breast masses in mammography remain challenging due to subtle intensity variations, heterogeneous tissue densities, and indistinct lesion boundaries that complicate radiological interpretation. To address these limitations, we propose BiLoG-Net, a deep learning framework that jointly performs breast mass segmentation and malignancy classification through bi-context location-aware feature modeling and segmentation-guided attention mechanisms. Our architecture integrates a novel encoder-decoder paradigm with Fire-based feature extraction, lightweight global and local feature enhancement modules, and adaptive location-aware gating to simultaneously capture long-range contextual dependencies and fine-grained boundary-sensitive details. Unlike conventional multi-stage pipelines, our tightly coupled multi-task design enables mutual reinforcement between pixel-level localization and image-level diagnosis, reducing error propagation while producing spatially grounded malignancy predictions. Evaluated on CBIS-DDSM and INBreast benchmarks, BiLoG-Net achieves state-of-the-art performance with Dice scores of 94.20% and 93.10%, classification accuracies of 95.20% and 93.60%, and AUC values of 97.10% and 96.00%, respectively, substantially outperforming existing CNN and transformer-based baselines. By combining precise boundary delineation with reliable malignancy assessment in a single end-to-end model, this work holds strong potential for clinical computer-aided detection systems, helping radiologists prioritize suspicious cases and improve screening efficiency in busy clinical settings.

Problem

• breast mass segmentation
• malignancy classification
• mammography
• lesion boundary
• tissue heterogeneity

Innovation

• bi-context location-aware modeling
• segmentation-guided attention
• multi-task learning
• boundary-sensitive feature enhancement
• end-to-end joint segmentation and classification