发表机构
School of Biomedical Engineering, University of Technology Sydney; School of Computer Science, University of Technology Sydney; School of Electrical and Data Engineering, University of Technology Sydney（悉尼科技大学生物医学工程学院; 悉尼科技大学计算机科学学院; 悉尼科技大学电气与数据工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对乳腺钼靶病灶检测跨异构数据源性能下降的问题，提出基于MoE的MammoMix框架，结合门控机制与MoCAE校准模块，在3个公开数据集上优于基线检测器，提升了泛化性与鲁棒性。
AI 中文摘要
乳腺钼靶图像中的病灶检测仍是一项具有挑战性的任务，原因在于不同数据集间存在图像质量、病灶外观及人群统计学特征的差异。尽管当前目标检测器如YOLO和DETR在单个数据集上表现出色，但当在异构数据源上训练或跨数据源应用时，其性能往往会下降。为解决这一问题，我们提出MammoMix，一种基于专家混合（Mixture-of-Experts, MoE）范式的新型框架，用于实现鲁棒且可泛化的病灶检测。在MammoMix中，每个专家模型在特定域上进行训练，使其能专门化学习源数据的不同特征；门控机制则根据输入图像自适应权衡各专家的贡献，结合其输出实现域自适应推理。为提升可靠性，我们进一步引入校准模块MoCAE，用于调整置信度分数以反映真实的预测不确定性。我们在3个公开乳腺钼靶数据集（CSAW、DDSM和DMID，涵盖不同临床场景）上评估MammoMix。结果显示，MammoMix在平均精度和可靠性上均优于基线检测器，尤其在变异性更大的数据集上表现突出。我们的研究表明，专家专门化与校准集成融合可显著提升模型的泛化能力和鲁棒性，MammoMix为跨真实临床域实现可靠的AI辅助乳腺癌筛查迈出了有前景的一步。
英文摘要
Breast lesion detection in mammography remains a challenging task due to variations in image quality, lesion appearance, and population demographics across datasets. While current object detectors such as YOLO and DETR achieve strong results on individual datasets, their performance often degrades when trained on or applied across heterogeneous sources. To address this, we propose MammoMix, a novel framework based on Mixture-of-Experts (MoE) paradigm for robust and generalizable lesion detection. In MammoMix, each expert model is trained on a specific domain, allowing it to specialize in distinct characteristics of its source data. A gating mechanism adaptively weighs contributions from each expert based on input image, combining their outputs to enable domain-adaptive inference. To improve reliability, we further incorporate a calibration module, MoCAE, which adjusts confidence scores to reflect true predictive uncertainty. We evaluate MammoMix on 3 public mammography datasets: CSAW, DDSM, and DMID, covering diverse clinical settings. Results show that MammoMix outperforms baseline detectors in both average precision and reliability, particularly on datasets with greater variability. Our findings demonstrate that expert specialization and calibrated ensemble fusion significantly enhance model generalization and robustness. MammoMix offers a promising step toward dependable AI-assisted breast cancer screening across real-world clinical domains.
CommentsAustralasian Joint Conference on Artificial Intelligence 2025
DOI：10.1007/978-981-95-4972-6_22
