BiLoG-Net：用于乳腺钼靶中乳腺肿块分割和恶性肿瘤分类的双上下文位置引导网络
BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography
AI总结：
针对乳腺钼靶中肿块检测难题，提出BiLoG-Net深度学习框架，通过双上下文位置感知特征建模等，联合进行肿块分割与恶性肿瘤分类，在相关基准测试中性能优异，为临床辅助检测提供助力。
AI中文摘要：
乳腺癌仍是全球女性中最常被诊断出的恶性肿瘤，然而由于细微的强度变化、不均匀的组织密度和不清晰的病变边界，使得乳腺钼靶中乳腺肿块的准确检测和特征描述仍然具有挑战性，这使得放射学解释变得复杂。为了解决这些限制，我们提出了BiLoG-Net，这是一个深度学习框架，通过双上下文位置感知特征建模和分割引导注意力机制，联合执行乳腺肿块分割和恶性肿瘤分类。我们的架构集成了一种新颖的编码器-解码器范式，具有基于Fire的特征提取、轻量级全局和局部特征增强模块，以及自适应位置感知门控，以同时捕获远程上下文依赖关系和细粒度边界敏感细节。与传统的多阶段管道不同，我们紧密耦合的多任务设计能够在像素级定位和图像级诊断之间实现相互强化，减少误差传播，同时产生空间上有依据的恶性肿瘤预测。在CBIS-DDSM和INBreast基准上进行评估，BiLoG-Net分别以94.20%和93.10%的Dice分数、95.20%和93.60%的分类准确率以及97.10%和96.00%的AUC值实现了领先的性能，大大优于现有的基于CNN和Transformer的基线。通过在单个端到端模型中结合精确的边界描绘和可靠的恶性肿瘤评估，这项工作在临床计算机辅助检测系统中具有强大的潜力，有助于放射科医生在繁忙的临床环境中对可疑病例进行优先级排序并提高筛查效率。
英文摘要：
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.
