发表机构
Monash University; Renmin University of China; Lancaster University（莫纳什大学; 中国人民大学; 兰卡斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对乳腺超声诊断中深度学习的可靠性与可解释性难题，提出BooF框架实现MLLM与专家模型协作，经多数据集验证其性能优于现有最优方法。
AI 中文摘要
乳腺超声（BUS）广泛用于乳腺癌诊断，但仍依赖操作者。尽管深度学习展现出潜力，确保诊断可靠性和可解释性颇具挑战。近期多模态大语言模型（MLLM）因领域知识有限常生成虚假描述，误导下游专家模型并损害临床有效性。为应对这些挑战，我们提出引导与反馈（BooF）模型协作框架，实现MLLM与专家模型的协同交互。具体而言，在引导阶段，MLLM受BI-RADS词典及初步良恶性视觉专家预测的引导，使其能将通用推理迁移至BUS分析，同时避免幻觉。随后，反馈阶段通过轻量型注意力门控跨模态融合模块将这些描述与视觉特征融合，使专家模型能利用文本反馈并自适应过滤噪声。在多个BUS数据集上的大量实验表明，BooF在诊断准确率和可解释性方面显著优于现有最优方法。
英文摘要
Breast ultrasound (BUS) is widely used for breast cancer diagnosis yet remains operator-dependent. While deep learning shows promise, ensuring diagnostic reliability and interpretability is challenging. Recent Multimodal Large Language Models (MLLMs) often generate spurious descriptions due to limited domain knowledge, which mislead downstream expert models and compromise clinical validity. To address these challenges, we propose the Boot-and-Feedback (BooF) model collaboration framework for synergistic MLLM-expert interaction. Specifically, in the Boot Stage, the MLLM is guided by the BI-RADS lexicon and preliminary benign-malignant vision-expert predictions, enabling it to transfer general reasoning to BUS analysis while avoiding hallucinations. Subsequently, the Feedback Stage integrates these descriptions with visual features via a lightweight Attention-Gated Cross-Modality Fusion Module. This allows the expert to leverage textual feedback while adaptively filtering noise. Extensive experiments on multiple BUS datasets demonstrate that BooF substantially outperforms state-of-the-art methods in terms of diagnostic accuracy and interpretability.
Comments5 pages, 2 figures. Published in ICASSP 2026
Journal refICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026
DOI：10.1109/ICASSP55912.2026.11460659
