AI 中文总结
针对现有RRG模型未充分利用检查信息、易因额外输入引发诊断错误的问题，提出PDD-RRG框架，通过多视角生成报告并聚合诊断结论，无需重训练即可提升RRG模型临床效能。
AI 中文摘要
自动放射学报告生成（RRG）旨在模拟放射科医生的工作流程，辅助其开展临床诊断。然而，现有方法往往未能充分利用检查相关的所有信息，而这正是临床实践中的常规操作。尽管部分研究尝试融入多视图图像与历史数据，但这些额外输入有时反而会引发可避免的诊断错误。为应对这些挑战，我们首次在报告生成后引入决策阶段，提出后验诊断决策框架（PDD-RRG）以整合潜在冲突的诊断结果。具体而言，我们构建多种输入数据子集，利用现有RRG模型从不同视角生成报告；随后计算贝叶斯后验概率与各临床观测的学习阈值，得到聚合诊断结论，并据此优化生成的报告。在MIMIC-CXR数据集上开展的实验表明，所提PDD-RRG无需任何重训练即可有效提升现有RRG模型的临床效能。
英文摘要
Automatic radiology report generation (RRG) aims to simulate the workflow of radiologists, assisting them in clinical diagnosis. However, existing methods often fall short in utilizing all information relevant to the examination, as is typically done in clinical practice. Although some works attempt to incorporate multi-view images and historical data, these additional inputs may sometimes lead to avoidable diagnostic errors on the contrary. To address these challenges, we introduce a decision-making stage after report generation for the first time and propose a Posterior Diagnostic Decision framework (PDD-RRG) to integrate potentially conflicting diagnoses. Specifically, we create various subsets of input data and utilize an existing RRG model to generate reports from different perspectives. Then the Bayesian posterior probability and the learned thresholds for each clinical observation are calculated to obtain an aggregated diagnostic conclusion, which is subsequently used to refine the generated report. Experiments on MIMIC-CXR demonstrate that our proposed PDD-RRG can effectively enhance the clinical efficacy of existing RRG models without any retraining.
CommentsAccepted by IJCAI 2026
