PACER：不完整临床情境下放射学报告生成的渐进式可用性条件证据路由
PACER: Progressive Availability-Conditioned Evidence Routing for Radiology Report Generation under Incomplete Clinical Context
- Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
- Yancheng Institute of Technology（盐城工学院）
- Shanghai University（上海大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对不完整临床情境下放射学报告生成中证据利用不足的问题，提出PACER框架，通过细化-校准-承诺流程路由可用证据，在MIMIC-RG4和MIMIC-CXR上取得领先临床效能。
AI中文摘要：
放射学报告生成（RRG）日益整合异质性临床证据，如多视图放射影像和既往报告，这些证据的可用性在不同检查间有所变化。然而，适应不同的输入组合并不能确保有效的证据利用：生成的报告仍可能遗漏或不准确地描述临床相关发现。为解决这一问题，我们提出PACER，一种面向结构化不完整情境RRG的渐进式可用性条件证据路由框架，遵循细化-校准-承诺（Refine-Calibrate-Commit）流程。该框架首先通过跨冻结编码器深度的端点保持分块路由细化观测到的视觉表征，在保留预训练终端表征的同时融入互补线索。随后，根据观测到的证据和可用性状态校准语言模型前缀，使共享生成器的条件随可用源集变化而适应。最后，在同一自回归轨迹中，在报告生成前产生极性结构的临床承诺，为后续生成提供结构化的临床上下文。实验表明，在所有四种MIMIC-RG4设置中，该方法达到了最先进的临床效能，并在MIMIC-CXR上表现强劲，同时保持了有竞争力的语言生成质量。
英文摘要：
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.
