Dissertation > Excellent graduate degree dissertation topics show

Study on Muscle Morphology and Activity Under Functional Electrical Stimulation Based on Ultrasound Image Analysis

Author: XuLiFeng
Tutor: WanBaiKun
School: Tianjin University
Course: Biomedical Engineering
Keywords: Spinal cord injury and paraplegia functional electrical stimulation ultrasound image muscle thickness muscle texture support vector machine artificial neural network
CLC: R31
Type: Master's thesis
Year: 2012
Downloads: 52
Quote: 0
Read: Download Dissertation

Abstract


Nowadays, the incidence of paraplegia induced by spinal cord injury (SCI) has been increased significantly. The rebuilding of limb function is a key and difficult point in rehabilitation of paraplegic patients. Functional electrical stimulation (FES) is widely considered as an effective tool in this field.But lots of new technologies of FES have been employed only in laboratory, the stimulation patterns and the effects of FES in clinical application are very limited, one of the reasons is that the mechanism research of FES is still lacking, and there is few research on the macro-level description of how it affects muscle functional activities and status. The state of skeletal muscle contraction and relaxation is the basis of the human body movement, the structure of skeletal muscle is the primary determinant of its function and activity. Therefore, in order to achieve the purpose of the rebuilding of limb function and its rapid development and application, the structure and function of target skeletal muscle must be explored more deeply under FES.Same-angle contraction and same-torque contraction conditions were designed in this research. FES-induced movement and voluntary movement patterns were included in each contraction. B-mode ultrasound imaging system is used to image the target muscle under FES-induced pattern, the information of muscle activity including muscle thickness and texture features was obtained and at the same time joint angles were collected, then angle is as a feedback to collect muscle image under voluntary movement pattern.First, the correlation between muscles’characteristics parameters including thickness and texture characteristics and joint angle were calculated and the significant result indicates that the periodic FES is the direct reason for periodic muscle activity. Second, the muscle characteristic parameters differences between FES-induced contraction and voluntary contraction with the same movement effect were compared based on proportion, then the factors causing this difference were obtained through analyzing the subject individual differences. The multiple linear regression method was used to find the main factor. The main factor was adjusted through adjusting the stimulation pattern and intensity to achieve the regression of muscle characteristic parameters from FES-induced contraction towards voluntary contraction, which led to the regression of muscle activity and status.In this study, the machine learning methods including support vector machine and artificial neural network were used to predict the joint angle based on the default stimulation intensity, muscle thickness and texture information. The result shows that the method of combining stimulation intensity and muscle information is superior to stimulation intensity only as input. This indicates muscle thickness and texture information play an important role in reflecting muscle activity and status, and it provides a potential stimulation method in the precise control of FES system.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  3. Research on Autamatic Music Structrue Analysis,TN912.3
  4. Research on Methods of Medical Ultrasound Image Denoising,TP391.41
  5. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  6. Fault Diagnosis Method Based on Support Vector Machine,TP18
  7. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  8. BP network optimization based on genetic algorithm optimization of the biodiesel process,TE667
  9. Ketones 3D-QSPR study,O641
  10. The Optimization Research of Feedforward Neural Network Based on Genetic Algorithms,TP183
  11. The Research of Medical Ultrasound Image Denosing Algorithms Based on Multiscale Geometric Analysis,TP391.41
  12. The New Privacy Preserving Algorithms for Linear Programming and SVMS,O221.1
  13. Research of Fault Diagnosis Method of Analog Circuit Based on Improved Support Vector Machines,TN710
  14. The Forecast Methods of Mining Risk of the Coal Resources Affected by Dynamic Disaster,TD713
  15. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  16. Research on Classification and Matching for Hand Vein Image,TP391.41
  17. Optimizzation on Tread Rubber Loss Factor Based on Support Vector Machine,U463.341
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. Research of Facial Expression Recognition Algorithm,TP391.41
  20. Cloud Classification Based on Geostationary Meteorological Satellite Imagery,TP391.41
  21. Research of Blind Equalization Algorithm Based on Neural Networks,TN911.7

CLC: > Medicine, health > Basic Medical > Medical science in general
© 2012 www.DissertationTopic.Net  Mobile