Dissertation > Excellent graduate degree dissertation topics show

Brain Connectivity Pattern Analysis Based on DTI

Author: FangPeng
Tutor: HuDeWen
School: National University of Defense Science and Technology
Course: Control Science and Engineering
Keywords: Diffusion tensor imaging (DTI) Split brain function Probability track White matter fiber connections Machine Learning
CLC: R445.2
Type: Master's thesis
Year: 2011
Downloads: 43
Quote: 0
Read: Download Dissertation

Abstract


Diffusion tensor imaging (DTI) is the use of tissue water molecule diffusion anisotropy imaging method to detect the microscopic structure of the organization . Diffusion tensor imaging is a sensitive non- invasive method to detect structural changes of the microstructure , it is estimated by measuring the diffusion of water molecules in the white matter fiber direction and speed , diffusion tensor voxel model of white matter fiber track reconstruction. Machine learning methods of diffusion tensor imaging data analysis , pattern classification of patients with depression and normal white matter fiber connections , the group has significant distinction of white matter fiber analysis . In this paper, the coverage split brain area and create a model of the diffusion tensor fiber tracking algorithm using probabilistic brain range white matter fiber tracts reconstructed . In this paper will be to test the brain 's white matter fiber connection strength as a classification feature , local linear embedding and support vector machine combined machine learning methods , patients with depression and normal mode analysis , cross-validation classification recognition rate was 91.7 % , a permutation test to further verify the reliability of the classification results . 33 extracted in a leave-one- out cross validation consistent high distinguish ability of white matter fiber connections , these connections are mainly distributed in the prefrontal - Edge system parietal lobe - the limbic system and visual - temporal lobe three networks , three network anomalies and mental depression in patients with depression , emotion, cognition , attention disorders closely linked to white matter fiber connections in the three network abnormalities may explain the abnormal behavior of patients with depression , and may become a clinical diagnosis of biological label .

Related Dissertations

  1. Based on Data Distribution Characteristics of Text Classification,TP391.1
  2. Research and Implement of Chinese Word Segment Techniques Based on the Conditional Random Field,TP391.1
  3. Semi-supervised Learning and Active Learning of Sentiment Classification Coupled with Domain Knowledge,TP181
  4. A Static Behavior-Based Method to Detect Malware on Android,TP309
  5. Supervision topic model research and application,TP391.1
  6. Distortion effects on image quality evaluation and classification,TP391.41
  7. Learning-based human motion synthesis inverse kinematics,TP391.41
  8. Content-based malicious code detection Research and Implementation,TP393.092
  9. Home Academic Information Extraction System,TP393.092
  10. Social network algorithm and its application in recommendation,TP391.3
  11. Application of Data Mining in Email Anti-Spam System,TP393.098
  12. Based on self-learning social relation extraction research,TP391.1
  13. Graph model based on statistical and machine learning algorithm and its application of certain,TP181
  14. P2P Traffic Identification Method,TP393.06
  15. Based on rough sets and SVM national defense Comprehensive Quality Assessment Methods,E075
  16. SVM Based on SIFT and scene classification,TP391.41
  17. Machine learning based on sparse coding and image content recognition algorithm,TP391.41
  18. Random Forests Feature Selection,TP311.13
  19. Research on Techniques of Collecting Internet Traffic Ground Truth,TP393.06
  20. Research of Protein-Protein Interaction Extraction Based on Rich Feature and Multiple Kernels Learning,Q51

CLC: > Medicine, health > Clinical > Diagnostics > Diagnostic Imaging > Magnetic resonance imaging
© 2012 www.DissertationTopic.Net  Mobile