Memory-aligned Knowledge Graph for Clinically Accurate Radiology Image Report Generation

Sixing Yan
2022 Proceedings of the 21st Workshop on Biomedical Language Processing   unpublished
Automatic generating the clinically accurate radiology report from X-ray images is important but challenging. The identification of multigrained abnormal regions in image and corresponding abnormalities is difficult for datadriven neural models. In this work, we introduce a Memory-aligned Knowledge Graph (MaKG) of clinical abnormalities to better learn the visual patterns of abnormalities and their relationships by integrating it into a deep model architecture for the report generation. We
more » ... out extensive experiments and show that the proposed MaKG deep model can improve the clinical accuracy of the generated reports.
doi:10.18653/v1/2022.bionlp-1.11 fatcat:t4wfuqdhxrfxnhfn7knv6ximoe