Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
Published 16 Sept 2026arXiv:2609.15334
Updated 7 h ago · first seen 15 Sept 2026
paper_01M2JK0CVYEVY99VDYWGCNPCFX
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.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 4
- Property changedPaperConcept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv - Property changedPaperConcept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation: published at changed from 2026-09-15T04:00:00+00:00 to 2026-09-16T04:00:00+00:00
Published15 Sept 2026→16 Sept 2026arxiv - Property changedPaperConcept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - New paperPaperConcept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
New paper: Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
arxiv
Sources
Sources 3
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.