Boot-and-Feedback Framework for Generalist-Expert Model Collaboration in Breast Ultrasound Diagnosis

2026-08-24

AI Summary

为解决乳腺超声诊断中的操作依赖性和可靠性问题，提出了一种基于引导和反馈框架的通用-专家模型协作方法，提高了诊断准确性和可解释性。

Abstract

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.

Problem

• Breast Ultrasound
• Diagnostic Reliability
• Interpretability
• Multimodal Large Language Models
• Clinical Validity

Innovation

• Boot-and-Feedback Framework
• Multimodal Large Language Models
• Attention-Gated Cross-Modality Fusion Module
• BI-RADS lexicon