摘要
为方便骨科医生更为准确地对痛风性关节炎进行诊断,提出一种基于三维可视化的计算机辅助痛风诊断方法,实现区域分割、三维重建及指标评估分析三大功能。以双能量CT序列为输入,利用阈值分割、区域增长及逻辑回归等算法对骨质和尿酸盐结晶(monosodium urate,MSU)区域进行分割,以统计相应指标和对分割后区域进行三维重建的方式进行辅助诊断。实验结果表明,该方法能够精确地统计痛风诊断相应指标,并可在二维和三维空间显示定位相应的骨质及尿酸盐结晶区域,有效辅助医生进行诊断。
To facilitate orthopedic doctors to more accurately diagnose gouty arthritis,a computer-assisted gout diagnosis method based on 3D visualization was proposed,which realized region segmentation,3D reconstruction,and index evaluation.The dual energy CT sequence was imported,threshold segmentation,region growth,and logistic regression algorithms were used to segment bone and urate crystal(monosodium urate,MSU)regions,and auxiliary diagnosis was realized by counting the corresponding indicators and performing three-dimensional reconstruction of the segmented region.The experimental results show that the method can accurately count the corresponding indicators of gout diagnosis,and display the corresponding bone and urate crystallization areas in two-dimensional and three-dimensional space,which can effectively assist doctors in diagnosis.
作者
胡颜民
李彬
柏瑞
田联房
HU Yan-min;LI Bin;BAI Rui;TIAN Lian-fang(School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,China;Department of Radiology,Guangdong Gosun Medical Imaging Diagnostic Center,Guangzhou 510017,China)
出处
《计算机工程与设计》
北大核心
2021年第1期189-195,共7页
Computer Engineering and Design
基金
广东省基础与应用基础研究基金项目(2019A1515011148)
中央高校基本科研业务费专项基金项目(2019MS139)
广东省科技计划基金项目(2017A020215164)。
关键词
痛风诊断
计算机辅助
逻辑回归
三维重建
三维可视化
gout diagnosis
computer aided
logistic regression
3D reconstruction
3D visualization
