templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora

2026-10-04

AI Summary

The construction of radiology templates traditionally relies on expert consensus, which suffers from delayed updates and limited adaptability to clinical evolution. This work proposes TEMPLAR, a novel template-centric multi-agent collaborative framework that integrates large language models, Span-Triple atomic clustering, and consistency-constrained reasoning. By incorporating anatomy-diagnosis dual knowledge graphs, the framework enables dynamic evolution and external evidence integration to achieve automatic template induction and refinement. Evaluated across four datasets, TEMPLAR outperforms baseline methods in coverage, informational fidelity, and diagnostic fidelity, while attaining the highest quality scores under LLM-based evaluation.

Abstract

Structured radiology reporting mitigates the heterogeneity of free-text reports, yet its benefits depend on high-quality reporting templates. In practice, such templates are conventionally built through labor-intensive expert consensus and therefore vary across institutions and lag behind evolving clinical practice. Large language models (LLMs) enable automated template induction, but existing approaches remain limited: single-LLM induction is constrained by context length, and the corpus-scale method ASTAR produces a static, closed-corpus template without external grounding or downstream adaptation. To address these limitations, we propose TEMPLAR, a TEMPLate-centric Agentic framework for inducing and evolving standardized Radiology reporting templates from large-scale clinical corpora. TEMPLAR treats the template as a persistent central state maintained alongside two provenance-aware knowledge graphs, namely an anatomical graph that constrains template construction and a diagnostic graph that supports finding-to-diagnosis reasoning. Three agents operate on this state. The Induction Agent derives canonical clinical slots from anatomy-constrained Span-Triple atoms via dual-view similarity clustering; the Evolution Agent then assembles these slots into a hierarchical template and revises it under consistency constraints, external clinical evidence, and downstream structuring feedback; and the Clinical Agent applies the evolved template to report structuring, reconstruction, and diagnostic reasoning. Across four datasets, TEMPLAR outperforms ASTAR, three medical LLMs, and six general-purpose LLMs in coverage, information fidelity, and diagnostic fidelity, while achieving the highest or tied-highest LLM-rated template quality. Its fidelity advantages over ASTAR persist under cross-dataset transfer, and cumulative ablations support complementary contributions of its key components.

Problem

• radiology reporting templates
• template induction
• large language models
• clinical corpora
• structured reporting

Innovation

• Agentic framework
• Radiology reporting templates
• Knowledge graphs
• Large language models
• Template induction and evolution