Prior Knowledge Enhances Radiology Report Generation.

TitlePrior Knowledge Enhances Radiology Report Generation.
Publication TypeJournal Article
Year of Publication2022
AuthorsWang S, Tang L, Lin M, Shih G, Ding Y, Peng Y
JournalAMIA Annu Symp Proc
Date Published2022
KeywordsDiagnosis, Computer-Assisted, Humans, Radiography, Radiology, Radiology Information Systems, Research Report

Radiology report generation aims to produce computer-aided diagnoses to alleviate the workload of radiologists and has drawn increasing attention recently. However, previous deep learning methods tend to neglect the mutual influences between medical findings, which can be the bottleneck that limits the quality of generated reports. In this work, we propose to mine and represent the associations among medical findings in an informative knowledge graph and incorporate this prior knowledge with radiology report generation to help improve the quality of generated reports. Experiment results demonstrate the superior performance of our proposed method on the IU X-ray dataset with a ROUGE-L of 0.384±0.007 and CIDEr of 0.340±0.011. Compared with previous works, our model achieves an average of 1.6% improvement (2.0% and 1.5% improvements in CIDEr and ROUGE-L, respectively). The experiments suggest that prior knowledge can bring performance gains to accurate radiology report generation. We will make the code publicly available at

Alternate JournalAMIA Annu Symp Proc
PubMed ID35854760
PubMed Central IDPMC9285179
Grant ListR00 LM013001 / LM / NLM NIH HHS / United States