胶囊内窥镜无线遥测定位的校正

郭旭东; 严荣国; 颜国正

doi:10.3788/OPE.20101812.2650

您当前的位置：

首页 >

文章列表页 >

胶囊内窥镜无线遥测定位的校正

信息科学 | 更新时间：2020-08-12

- 胶囊内窥镜无线遥测定位的校正
- Calibration method for wirelessly localizing capsule endoscopy
- 光学精密工程 2010年18卷第12期页码：2650-2655
- 作者机构：
  
  1. 上海理工大学医疗器械与食品学院,上海200093
  2. 上海交通大学电子信息与电气工程学院,上海200240
- 作者简介：
- 基金信息：
  
  上海市教育委员会科研创新资助项目(No.10YZ93)();国家自然科学基金资助项目(No.30900320,No.6100164)()
- DOI：10.3788/OPE.20101812.2650
  中图分类号： TH776;TP391.4
- 收稿日期：2010-03-30，
  
  修回日期：2010-06-03，
  
  网络出版日期：2010-12-25，
  
  纸质出版日期：2010-12-25
- 稿件说明：
移动端阅览
郭旭东, 严荣国, 颜国正. 胶囊内窥镜无线遥测定位的校正[J]. 光学精密工程, 2010,18(12): 2650-2655

GUO Xu-dong, YAN Rong-guo, YAN Guo-zheng. Calibration method for wirelessly localizing capsule endoscopy[J]. Editorial Office of Optics and Precision Engineering, 2010,18(12): 2650-2655
郭旭东, 严荣国, 颜国正. 胶囊内窥镜无线遥测定位的校正[J]. 光学精密工程, 2010,18(12): 2650-2655 DOI： 10.3788/OPE.20101812.2650.

GUO Xu-dong, YAN Rong-guo, YAN Guo-zheng. Calibration method for wirelessly localizing capsule endoscopy[J]. Editorial Office of Optics and Precision Engineering, 2010,18(12): 2650-2655 DOI： 10.3788/OPE.20101812.2650.

摘要

为了进一步提高采用交流励磁定位无线跟踪胶囊内窥镜的定位精度

减小系统误差

提出了改进的神经网络定位校正方法。首先

设计了适应于胶囊内窥镜定位校正的神经网络结构;然后

采用Levenberg-Marquart算法结合贝叶斯正则化方法改进校正网络

抑制校正网络的过拟合。通过定位实验平台

建立了定位目标的跟踪位置与实际位置的样本对照数据表

并应用校正网络对定位数据进行校正。定位校正实验表明

改进的神经网络校正法可进一步减小定位误差

校正后的

分量的平均误差分别减小至8.7 mm

10.1 mm

7.3 mm

0.086 rad和0.081 rad。与基本BP算法相比

采用Levenberg-Marquart贝叶斯正则化的改进算法有效提高了定位校正网络的泛化能力和收敛精度。

Abstract

In order to non-invasively track a capsule endoscopy in the gastrointestinal tract

a telemetric localization method using alternating magnetic fields was presented. Focusing on the method

a Bayesian-regularization neural network based on the Levenberg-Marquart algorithm was investigated to reduce system errors. Firstly

the neural network structure for localization calibration was designed. Then

both Bayesian-regularization and Levenberg-Marquart algorithms were used to train the neural network to limit an over-fitting. Using an experimental platform for localization

both the calibration table for training the network and the validation table for verifying the calibration quality were established

and the location data were calibrated by the trained neural network. The calibration experiment shows that the proposed neural network can be trained well enough to efficiently compensate the errors in electromagnetic localizing system. The mean errors of

respectively have been reduced to 8.7 mm

10.1 mm

7.3 mm

0.086 rad and 0.081 rad after calibration. Comparing with the standard Back-Propagation(BP) algorithm

the Bayesian-regularization neural network based on Levenberg-Marquart algorithm has better performance in the generalization capability and convergence precision.

关键词

Keywords

references

IDDAN G, MERON G, GLUKHOVSKY A, et al.. Wireless capsule endoscopy[J]. Nature, 2000,405(6785):417-420.[2] SWAIN P. The future of wireless capsule endoscopy[J]. World J. Gastroenterol., 2008,14(26):4142-4145.[3] 杨伟昂, 王炳周, 吴灵飞. 胶囊内镜临床应用新进展[J]. 世界华人消化杂志, 2008,16(36):4081-4087. YANG W A, WANG B ZH, WU L F. Recent progress in clinical applications of capsule endoscopy[J]. World Chinese Journal of Digestology, 2008,16(36):4081-4087. (in Chinese)[4] 俞凯君, 李鹏. 磁共振成像的三维图形定位的实现[J]. 上海生物医学工程, 2006,27(2):87-89. YU K J, LI P. 3D graphics localization in MRI[J]. Shanghai Journal of Biomedical Engineering, 2006,27(2):87-89. (in Chinese)[5] 李君兰, 张大卫, 王以忠, 等. 面向IC封装的显微视觉定位系统[J]. 光学精密工程, 2010,18(4):965-972. LI J L, ZHANG D W, WANG Y ZH. Micro-vision positioning systems for IC packaging[J]. Opt. Precision Eng., 2010,18(4):965-972. (in Chinese)[6] JACOB H, LEVY D, SHREIBER R, et al.. Localization of the given M2A ingestible capsule in the given diagnostic imaging system[J]. Gastrointestinal Endoscopy, 2002,55(5):AB135.[7] STATHOPOULOS E, SCHLAGETER V, MEY-RA B, et al.. Magnetic pill tracking: a novel non-invasive tool for investigation of human digestive motility[J]. Neurogastroenterol Motility, 2005,17:148-154.[8] WEITSCHIES W, BLUME H, MNNIKES H. Magnetic marker monitoring: high resolution real-time tracking of oral solid dosage forms in the gastrointestinal tract[J]. European Journal of Pharmaceutics and Biopharmaceutics, 2010,74(1):93-101.[9] WU X D, HOU W S, PENG C L, et al.. Wearable magnetic locating and tracking system for MEMS medical capsule[J]. Sensors and Actuators A, 2008,141:432-439.[10] 郑小林, 李金, 侯文生, 等. 应用磁传感器阵列定位跟踪消化道诊疗胶囊[J]. 光学精密工程, 2009,17(3):576-582. ZHENG X L, LI J, HOU W SH, et al.. Localizing and tracking of medical capsule in human by magnetic sensor array[J]. Opt. Precision Eng., 2009,17(3):576-582. (in Chinese)[11] GUO X D, YAN G ZH, HE W H. A position telemetric method for implantable microcapsules in the gastrointestinal tract[J]. Measurement Science and Technology, 2008,19(4):045201-045208.[12] 姜萍萍, 颜国正, 郭旭东, 等. 用于体内胶囊式遥测系统的电磁跟踪定位方法[J]. 光学精密工程, 2007,15(8):1247-1252. JIANG P P, YAN G ZH, GUO X D, et al.. Electro-magnetic tracking system for capsule-typed telemetric device[J]. Opt. Precision Eng., 2007,15(8):1247-1252. (in Chinese)[13] FORESEE F D, HAGAN M T. Gauss-Newton approximation to bayesian regularization . Proceedings of the IEEE International Joint Conference on Neural Networks, Piscataway, NJ: IEEE Press, 1997(3):1930-1935.[14] SURATGAR A A, TAVAKOLI M B, HOSEINABADI A. Modified Levenberg-Marquardt method for neural networks training[J]. Trans. Eng. Comput. Technol., 2005(6):46-48.

浏览量

363

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于神经网络的全斯托克斯光电探测器

基于圆卷积神经网络的粘连导电粒子检测

面向领域自适应的部分最优传输高光谱图像分类

基于热传导和卷积神经网络的磨床主轴热误差预测

基于刚度预测-神经网络的调姿平台误差补偿