基于动态DR的肺区域智能分割方法  

Intelligent Segmentation Method of Lung Region Based on Dynamic DR

在线阅读下载全文

作  者:陈卓 邓兴广 缪晓强 郑晗 CHEN Zhuo;DENG Xing-guang;MIAO Xiao-qiang;ZHENG Han(Center for Certification and Evaluation,Guangdong Food and Drug Administration,Guangdong Guangzhou 510080;D Medical Dynamic and Functional Imaging Joint Laboratory,Shenzhen Technology University,Guangdong Shenzhen 518055;Shenzhen Angell Technology Co,Ltd.,Guangdong Shenzhen 518055)

机构地区:[1]广东省药品监督管理局审评认证中心,广东广州510080 [2]深圳技术大学4D医学动态与功能成像联合实验室,广东深圳518055 [3]深圳市安健科技股份有限公司,广东深圳518055

出  处:《中国医疗器械信息》2022年第13期32-37,136,共7页China Medical Device Information

基  金:国家重点研发计划资助课题(项目编号:2019YFC0118801)。

摘  要:多功能数字化动态数字X射线摄影(Digital Radiography,DR)具有高清影像、适时点片、实时回放、连续点片等多种功能,在临床诊断中得到广泛应用。动态DR可获得肺部呼吸运动变化的图像,对呼吸康复的效果测定、肺癌、慢性阻塞性肺疾病、支气管哮喘、间质性肺炎等肺部疾病的诊断起到有用的价值,还可以观察到肺部的血流分布和通气分布情况。文章基于动态DR全呼吸周期的图像,通过传统方法和深度学习的结合进行量化分析,包括肺野识别、左右肺划分、肺部面积计算、膈肌定位、实时输出肺面积变化曲线和膈肌运动曲线。为临床医生提供多项量化指标,并且为临床动态DR诊断提供辅助支持。At present,the high-definition image,timely ordering,real-time playback,continuous ordering and other functions of multi-functional digital dynamic DR have been widely used in clinical diagnosis.Dynamic DR can obtain images of changes in pulmonary breathing movement,which is useful for the determination of the effect of respiratory rehabilitation and the diagnosis of lung diseases such as lung cancer,chronic obstructive pulmonary disease(COPD),bronchial asthma,and interstitial pneumonia.The distribution of blood flow and ventilation in the lungs was observed.In this paper,based on the images of the dynamic DR full respiratory cycle,quantitative analysis is carried out through the combination of traditional methods and deep learning,including lung field identification,left and right lung division,lung area calculation,diaphragm muscle positioning,real-time output of lung area change curve and diaphragm muscle movement curve.Provide clinicians with a number of quantitative indicators,and provide auxiliary support for clinical dynamic DR diagnosis.

关 键 词:动态DR 深度学习 肺分割 骨抑制 横膈膜 

分 类 号:TH774[机械工程—仪器科学与技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象