MAGIS:基于证据的多智能体推理用于可解释的斜视临床决策
DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
AI总结:
提出MAGIS框架,通过多智能体协作、双重证据约束上下文和基于证据的纠正验证机制,将斜视诊断从黑箱生成转变为结构化推理,在细粒度斜视基准上将加权F1分数从72.0%提升至91.3%,并显著提高诊断报告的临床可靠性。
摘要:
斜视是一种常见的眼部疾病,需要细粒度亚型诊断以制定个性化治疗方案。然而,现有的深度学习方法主要提供诊断预测,缺乏透明推理;而近期的大视觉语言模型(LVLMs)虽然在联合图像理解和报告生成方面有前景,但在这种对证据敏感且规则驱动的医学任务中极易产生幻觉。为解决这些问题,我们提出了MAGIS,一个基于证据的多智能体可解释斜视诊断推理框架。MAGIS将黑箱端到端生成转变为结构化的诊断过程,包括候选假设生成、双重证据约束上下文、基于证据的纠正验证和报告生成。具体而言,我们引入了双重证据约束上下文(DECC)机制,将来自九个注视方位照片的视觉证据和基于证据的临床诊断规则联合组织成约束上下文,以实现可靠的诊断推理。我们进一步开发了基于证据的纠正验证(EBCV)机制,验证当前诊断假设是否得到视觉证据、基于热图的视觉线索和基于证据的临床诊断规则的支持。当检测到不一致时,触发假设修正。在细粒度斜视基准上的实验表明,MAGIS不仅显著优于其他最先进的诊断系统,将加权F1分数从72.0%提高到91.3%,而且大幅提升了生成诊断报告的临床可靠性(一致性、对齐性和完整性)。这些结果表明,MAGIS为构建准确、基于证据且临床可解释的斜视诊断系统提供了有效解决方案。
英文摘要:
Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learning methods mainly provide diagnostic predictions without transparent reasoning, while recent large vision-language models (LVLMs), although promising for joint image understanding and report generation, remain highly prone to hallucination in this evidence-sensitive and rule-driven medical task. To address these challenges, we propose DECIS, a Dual-Evidence Corrective verification for Interpretable Strabismus diagnostic decision-making framework. DECIS transforms black-box end-to-end generation into a structured diagnostic process consisting of candidate hypothesis generation, dual-evidence constrained context, evidence-based corrective verification, and report generation. Specifically, we introduce a Dual-Evidence Constrained Context (DECC) mechanism that jointly organizes visual evidence from the photograph of the nine cardinal positions of gaze and evidence-based clinical diagnostic rules into a constrained context for reliable diagnostic reasoning. We further develop an Evidence-Based Corrective Verification (EBCV) mechanism that verifies whether the current diagnostic hypothesis is supported by visual evidence, heatmap-based visual cues, and evidence-based clinical diagnostic rules. Hypothesis refinement is triggered when inconsistency is detected. Experiments on a fine-grained strabismus benchmark demonstrate that DECIS not only outperforms other state-of-the-art diagnostic systems, improving the weighted F1 score from 72.0% to 91.3%, but also improves the clinical reliability (consistency, alignment, and completeness) of generated diagnostic reports. These results demonstrate that DECIS provides an effective solution for building accurate, evidence-based, and clinically interpretable strabismus diagnosis systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。