PACER: Progressive Availability-Conditioned Evidence Routing for Radiology Report Generation under Incomplete Clinical Context

2026-09-28

AI Summary

This study addresses the challenges of inefficient evidence utilization and omission of critical findings in radiology report generation under incomplete clinical contexts. To this end, we propose PACER, a novel framework that introduces a progressive availability-conditioned evidence routing mechanism. By integrating endpoint-preserving patch-level routing, language model prefix calibration, and structured commitment within autoregressive trajectories, PACER enables dynamic contextual adaptation of multi-source heterogeneous evidence and generates polarity-structured clinical commitments. Experimental results demonstrate that PACER achieves state-of-the-art clinical efficacy across all four settings on MIMIC-RG4 and exhibits strong performance on MIMIC-CXR, while consistently maintaining high-quality language generation.

Abstract

Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose availability varies across examinations. However, accommodating different input combinations does not ensure effective evidence use: generated reports may still omit or inaccurately describe clinically relevant findings. To address this problem, we propose PACER, a Progressive Availability-Conditioned Evidence Routing framework for structured incomplete-context RRG that follows a Refine-Calibrate-Commit pipeline. It first refines observed visual representations through endpoint-preserving patchwise routing across frozen encoder depths, incorporating complementary cues while retaining the pretrained terminal representation. It then calibrates the language-model prefix according to the observed evidence and availability state, adapting the shared generator's conditioning as the available source set changes. Finally, it generates polarity-structured clinical commitments before the report in the same autoregressive trajectory, providing structured clinical context for subsequent generation. Experiments demonstrate state-of-the-art clinical efficacy across all four MIMIC-RG4 settings and strong MIMIC-CXR performance, while maintaining competitive language-generation quality.

Problem

• Radiology Report Generation
• Incomplete Clinical Context
• Heterogeneous Evidence
• Evidence Utilization

Innovation

• Radiology Report Generation
• Incomplete Clinical Context
• Evidence Routing
• Availability-Conditioned Calibration
• Polarity-Structured Commitments