中国中西医结合影像学杂志2025，Vol.23Issue(5)：666-670,5.DOI:10.3969/j.issn.1672-0512.2025.05.026
基于知识图谱的腹部前后立位片的智能质量控制
Intelligent quality control for abdominal anteroposterior radiograph based on knowledge graph
摘要
Abstract
Objective:To design an intelligent image quality control algorithm model for abdominal anteroposterior radiograph based on knowledge graph for clinical practice.Methods:Utilizing the Anhui Provincial Imaging Cloud Platform,4 499 de-identified abdominal radiograph images were included.All images were divided into a training set(3 136 images),a validation set(457 images),and a test set(906 images)in a ratio of 7∶1∶2.A knowledge graph for single-person and multi-person quality control labeling was constructed,an artificial intelligence(AI)quality control model was trained.Taking the results of three quality control experts as the reference standard for quality control,the image technical quality accuracy and image clarity accuracy among the single-person,multi-person and AI quality control methods were compared.The correlations between single-person quality control,multi-person quality control and reference standards were evaluated.Results:In the test set,compared with the reference standard,the average accuracy of AI quality control was higher than that of single-person quality control(A,B)(P＜0.01).In terms of image clarity,the correlation of AI quality control was the highest(0.754),followed by multi-person quality control(0.671),single-person quality control A(0.625)and B(0.617)in sequence.Conclusions:In the quality assessment of image projection technique and image clarity,the effect of AI quality control is significantly better than that of single-person quality control,and even for some labels,it is slightly better than that of multi-person quality control,showing potential for clinical application.关键词
腹部平片/图像质量控制/知识图谱/人工智能Key words
Abdominal Radiograph/Image quality control/Knowledge graph/Artificial intelligence引用本文复制引用
鲁文豪,谷宗运,张禹萱,王倩,宋亮亮,李传富..基于知识图谱的腹部前后立位片的智能质量控制[J].中国中西医结合影像学杂志,2025,23(5):666-670,5.基金项目
安徽省高校协同创新项目(GXXT-2021-065,GXXT-2022-031) （GXXT-2021-065,GXXT-2022-031）
安徽省高等学校科学研究重大项目(2023AH040102). （2023AH040102）
