4.6 Article

Improving Medical X-ray Report Generation by Using Knowledge Graph

期刊

APPLIED SCIENCES-BASEL
卷 12, 期 21, 页码 -

出版社

MDPI
DOI: 10.3390/app122111111

关键词

radiology report; computer-aided diagnosis; prior knowledge; knowledge graph; deep learning

资金

  1. Natural Science Foundation China (NSFC) [61402397, 61263043, 61562093, 61663046]
  2. Open Foundation of Key Laboratory in Media Convergence of Yunnan Province [220225201]
  3. Open Foundation of Key Laboratory in Software Engineering of Yunnan Province [2020SE304]
  4. Practical innovation project of Yunnan University [2021z34, 2021y128, 2021y129]

向作者/读者索取更多资源

This paper focuses on the automatic generation of medical reports from chest X-ray images. By constructing associations based on a knowledge graph and using a graph neural network, disease situational representations with prior knowledge are generated, and radiology reports are generated using self-supervised learning. Experimental results demonstrate that this method outperforms existing methods in performance.
In clinical diagnosis, radiological reports are essential to guide the patient's treatment. However, writing radiology reports is a critical and time-consuming task for radiologists. Existing deep learning methods often ignore the interplay between medical findings, which may be a bottleneck limiting the quality of generated radiology reports. Our paper focuses on the automatic generation of medical reports from input chest X-ray images. In this work, we mine the associations between medical discoveries in the given texts and construct a knowledge graph based on the associations between medical discoveries. The patient's chest X-ray image and clinical history file were used as input to extract the image-text hybrid features. Then, this feature is used as the input of the adjacency matrix of the knowledge graph, and the graph neural network is used to aggregate and transfer the information between each node to generate the situational representation of the disease with prior knowledge. These disease situational representations with prior knowledge are fed into the generator for self-supervised learning to generate radiology reports. We evaluate the performance of the proposed method using metrics from natural language generation and clinical efficacy on two public datasets. Our experiments show that our method outperforms state-of-the-art methods with the help of a knowledge graph constituted by prior knowledge of the patient.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据