PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation
Quick Answer
The PDD-RRG framework enhances automatic radiology report generation by introducing a decision-making stage that integrates conflicting diagnoses.
Quick Take
By utilizing subsets of input data and Bayesian methods, it improves clinical efficacy without retraining existing models, as demonstrated on the MIMIC-CXR dataset.
Key Points
- Introduces a decision-making stage post-report generation for radiology.
- Utilizes Bayesian posterior probability to refine diagnostic conclusions.
- Demonstrated effectiveness on the MIMIC-CXR dataset.
- Enhances existing RRG models without requiring retraining.
- Addresses challenges of conflicting diagnoses in clinical practice.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | Accepted by IJCAI 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.03055 [cs.CV] |
| (or arXiv:2608.03055v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.03055 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Yu [view email]
[v1]
Tue, 4 Aug 2026 03:12:34 UTC (4,658 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.