Dissertation > Excellent graduate degree dissertation topics show

Computer-aided Detection for Virtual Colonoscopy Based on Texture Analysis

Author: WangTian
Tutor: ZhangJunYing
School: Xi'an University of Electronic Science and Technology
Course: Applied Computer Technology
Keywords: Virtual colonoscopy Computer-aided detection Colon polyps GLCM Grayscale - gradient co-occurrence matrix
CLC: TP391.41
Type: Master's thesis
Year: 2008
Downloads: 58
Quote: 2
Read: Download Dissertation

Abstract


Virtual colonoscopy (virtual colonoscopy, VC) computer-aided detection (computer-aided detection, CAD) differences polyps and normal tissue morphology and other features new technical means to achieve the automatic detection of colonic polyps by the computer , with the physician directly using the virtual colonoscopy colonic lesions checks compared to CAD - based VC system is expected to provide a more objective and consistent test results , to improve the detection rate , thus contributing to the clinical application of VC in the census and physical examination . VC development in the past few years , there have been many CAD polyp detection methods based on morphology , higher in polyp detection sensitivity , but due to small differences in the density of the surrounding tissue of the colon polyps in CT images , and colon exists within the various polyp morphology similar structure , there are a lot of false-positive test point ( the false positives FPS ) in geometry - based method of detection results . The texture distribution mode polyps except geometry differences are also different from normal colon wall tissue and colon feces and other impurities , virtual colonoscopy to reduce the false-positive rate of CAD detection , this paper presents an analysis based on the 3D morphology / texture aided detection method used polyp geometric features , and 3D texture features combined curvature (curvedness, CV) shape index (shape index, SI) the geometric characteristics positioning suspected area . 3DeROI model established by finding the inner and outer boundaries of suspected polyps region . Then using gray level co-occurrence matrix (GLCM) and gray - gradient co-occurrence matrix (GLGCM) two texture analysis 3DeROI the suspected polyp regional of the model structure extract texture features . Design a BP (back propagation) neural network and SVM (support vector machine) classifier suspected polyps region classification . Supine and lateral posture seven patients CT scan data classifier training and testing , the results show that the proposed CAD method can effectively detect colon polyps and remove 77.5% false positive detection point .

Related Dissertations

  1. The Application of Ant Colony Algorithm in Meteorological Satellite Cloud Pictures Segmentation,TP391.41
  2. Information Extraction of Marine Oil Spill with Collaborative Images of ASAR and MODIS,X87
  3. Automatic Recognition analyze of Fabric Structure Based on GLCM and BP Neural Network,TP391.41
  4. Mammary gland lumps Texture feature extraction and auxiliary diagnostic methods research,TP391.41
  5. Re-compression JPEG image tamper detection and localization,TP391.41
  6. Based on the average gray level co-occurrence matrix and characteristics analysis of LSB matching secret,TP391.41
  7. Texture Feature Research of Multi-Spectral Remote Sensing Image,TP751
  8. Research on Algorithm of Lung Nodule Detection Based on the Image Processing Technology,TP391.41
  9. Remote Sensing Image Segmentation Base on Dual-Tree Complex Wavelet Transform and Gray-level Co-occurrence Matrix,TP751
  10. Computer-Aided Detection Based on Textural Features and High-performance Classifiers,TP391.41
  11. Remote Sensing Image Data Object-oriented Classification and Fuzzy Logic Classification Research,TP751
  12. Application and Research of Automatic Detection System of Tire Cord Quality in Vision Technology,TP274
  13. Content-based image retrieval technology research,TP391.41
  14. Content-based Image Database Retrieval Technology Research,TP391.41
  15. Based on the direction of enhancing image compression method,TP391.41
  16. Population density estimates and shadow removal in video surveillance research,TP391.41
  17. MSCT colonography in colorectal tumors and polyps value,R656.9;R816.5
  18. Research on Techniques of Computer-aided Diagnosis of Breast Cancer for Mammography,TP29-AI
  19. The Study of the Method about Vegetation Information Extract Based on Independent Component Analysis,Q94-3
  20. Study on Gas/Liquid Two-phase Flow Patterns Based on Conductance Sensor and Image Processing Techniques,O359

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile