OPGAgent: An Agent for Auditable Dental Panoramic X-ray Interpretation

TL;DR

OPGAgent is a novel multi-tool agentic system designed for comprehensive, auditable interpretation of dental panoramic X-rays, outperforming existing vision language models and enabling detailed, structured clinical reporting.

Contribution

This work introduces OPGAgent, the first agentic system for dental X-ray analysis that combines specialized modules with a consensus mechanism, advancing accuracy and auditability in dental imaging interpretation.

Findings

Outperforms current dental VLMs on structured-report and VQA tasks.

Provides comprehensive, auditable analysis with conflict resolution.

Demonstrates effectiveness on OPG-Bench and MMOral-OPG benchmarks.

Abstract

Orthopantomograms (OPGs) are the standard panoramic radiograph in dentistry, used for full-arch screening across multiple diagnostic tasks. While Vision Language Models (VLMs) now allow multi-task OPG analysis through natural language, they underperform task-specific models on most individual tasks. Agentic systems that orchestrate specialized tools offer a path to both versatility and accuracy, this approach remains unexplored in the field of dental imaging. To address this gap, we propose OPGAgent, a multi-tool agentic system for auditable OPG interpretation. OPGAgent coordinates specialized perception modules with a consensus mechanism through three components: (1) a Hierarchical Evidence Gathering module that decomposes OPG analysis into global, quadrant, and tooth-level phases with dynamically invoking tools, (2) a Specialized Toolbox encapsulating spatial, detection, utility, and expert zoos, and (3) a Consensus Subagent that resolves conflicts through anatomical constraints. We further propose OPG-Bench, a structured-report protocol based on (Location, Field, Value) triples derived from real clinical reports, which enables a comprehensive review of findings and hallucinations, extending beyond the limitations of VQA indicators. On our OPG-Bench and the public MMOral-OPG benchmark, OPGAgent outperforms current dental VLMs and medical agent frameworks across both structured-report and VQA evaluation. Code will be released upon acceptance.