Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation

2026-09-14

AI Summary

为提高医学报告生成的可解释性，提出CORAL框架，通过定位病变和预测临床属性来整合空间基础和概念级监督，增强与临床决策过程的一致性。

Abstract

Medical imaging modalities such as ultrasound and X-ray are widely used in clinical practice, where diagnosis follows a structured, evidence-driven workflow aligned with standardized criteria. While multimodal large language models (MLLMs) show promise for automated medical report generation, most existing systems rely on end-to-end multimodal fusion without modeling clinically defined intermediate attributes, leading to limited grounding and interpretability. To address this issue, we propose CORAL (COncept-grounded ReAsoning with Localization), a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process. CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module. The resulting textual concept tokens are combined with mask-modulated visual features within an MLLM to enable structured report generation and diagnostic prediction. Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs, indicating that concept-grounded reasoning better aligns generation with clinical decision processes.

Problem

• medical report generation
• multimodal fusion
• concept grounding
• interpretability
• clinical attributes

Innovation

• concept-grounded reasoning
• prompt-driven localization
• multimodal framework
• concept bottleneck