本文已被:浏览 192次 下载 115次 |
码上扫一扫! |
基于超声影像的下腔静脉自动识别与定位 |
杨敬涵1,陈子叶2,孙景源3,曹文4,吕朝阳4,李硕4,李明秋4,张普5,徐径舟2,周昌1,杨宇祥6,张甫6,李庆利1,郭瑞君4,陈建刚1* |
|
(1. 华东师范大学上海市多维度信息处理重点实验室, 上海 200241; 2. 西交利物浦大学智能工程学院, 苏州 215123; 3. 利物浦大学计算机科学系, 利物浦 L693BX; 4. 首都医科大学附属北京朝阳医院超声医学科, 北京 100020; 5. 保定骨科医院普外科, 保定 071000; 6. 湖南师范大学工程与设计学院电子工程系, 长沙 410081 *通信作者) |
|
摘要: |
目的 探究基于下腔静脉(IVC)超声影像的IVC自动识别与直径测量方法。方法 提出一种基于拓扑结构与自动跟踪算法的IVC自动识别与定位方法,采用跟踪方式对数据集进行IVC识别和连续定位,以提高测量的效率和准确性。以超声医师的人工测量结果作为金标准,在采集自ICU的18例患者的18组超声数据集上进行测试。结果 自动化算法识别准确率为94.44%(17/18),IVC直径自动测量误差在±1.96s(s为标准差)范围内,表明自动测量方法可替代人工测量方法。结论 本研究提出的基于拓扑结构与自动跟踪算法的IVC自动识别与定位算法具有较高的识别成功率及IVC直径测量准确性,可以辅助临床医师进行IVC的识别定位与直径测量。 |
关键词: 超声图像 下腔静脉 血管识别与定位 自动化测量 |
DOI:10.16781/j.CN31-2187/R.20230760 |
投稿时间:2023-12-23修订日期:2024-05-07 |
基金项目:国家自然科学基金(82151318,32201134,32171366,31671002),上海市“科技创新行动计划”医学创新研究专项(21Y11902500),2023年地方科学发展基金(XZ202301YD0032C),吉林省科技发展计划项目(20230204094YY). |
|
Automated identification and localization of inferior vena cava based on ultrasound images |
YANG Jinghan1,CHEN Ziye2,SUN Jingyuan3,CAO Wen4,Lü Chaoyang4,LI Shuo4,LI Mingqiu4,ZHANG Pu5,XU Jingzhou2,ZHOU Chang1,YANG Yuxiang6,ZHANG Fu6,LI Qingli1,GUO Ruijun4,CHEN Jiangang1* |
(1. Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, China; 2. School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou 215123, Jiangsu, China; 3. Department of Computer Science, University of Liverpool, Liverpool L693BX, England; 4. Department of Ultrasound, Beijing Chao-yang Hospital, Capital Medical University, Beijing 100020, China; 5. Department of General Surgery, Baoding Orthopaedics Hospital, Baoding 071000, Hebei, China; 6. Department of Electronic Engineering, School of Engineering and Design, Hunan Normal University, Changsha 410081, Hunan, China * Corresponding author) |
Abstract: |
Objective To explore the automated identification and diameter measurement methods for inferior vena cava (IVC) based on clinical ultrasound images of IVC. Methods An automated identification and localization method based on topology and automatic tracking algorithm was proposed. Tracking algorithm was used for identifying and continuously locating to improve the efficiency and accuracy of measurement. Tests were conducted on 18 sets of ultrasound data collected from 18 patients in intensive care unit (ICU), with clinicians’ measurements as the gold standard. Results The recognition accuracy of the automated method was 94.44% (17/18), and the measurement error of IVC diameter was within the range of ±1.96s(s was the standard deviation). The automated method could replace the manual method. Conclusion The proposed IVC automated identification and localization algorithm based on topology and automatic tracking algorithm has high recognition success rate and IVC diameter measurement accuracy. It can assist clinicians in identifying and locating IVC, so as to improve the accuracy of IVC measurement. |
Key words: ultrasound images inferior vena cava identification and localization of vessel automated measurement |