Dissertation > Excellent graduate degree dissertation topics show

Study on Computer-aided Detection Method of Masses Based on Multiple Mammograms

Author: QinShaoDong
Tutor: ChenHouJin
School: Beijing Jiaotong University
Course: Circuits and Systems
Keywords: X-ray image of the breast Tumor detection Multiple matching fusion Mass identification
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 41
Quote: 0
Read: Download Dissertation

Abstract


Abstract: Breast cancer is one of the troubled contemporary female physical and mental health of the most common malignancies, has become the number one killer of the 35 to 60-year-old urban women. Early detection, early diagnosis, early treatment has a pivotal role in reducing breast cancer mortality. Diagnostician by the subjective factors of work experience, continuous work time, the diagnostic accuracy of breast X-ray has been difficult to ensure the emergence of computer-aided detection technology to solve this problem to some extent. Method lumps of widespread use of computer-aided detection of breast masses detected false positive rate, correct identification is low, and the fundamental reason is that the the single breast X-ray image information in the validity and limited. The X-ray image information fusion of multiple breast lumps detection methods have a good solution to this problem, and aided detection of breast cancer research focus on international. In order to improve the level of detection of breast lumps, this paper uses the method of information fusion of multiple images, tumor detection based on the the breast ipsilateral CC view and MLO view X-ray image. This article is mainly for breast mass segmentation and breast lumps identify two aspects of the study, the following results were obtained: 1. Proposed segmentation method based on improved layered detection of breast lumps. Image clarity requirements for the hierarchical detection method proposed by Wang Ying et al. Higher false positive region more improvement programs and a more accurate model of hierarchical. By the the clinical breast X-ray image test, removal of the breast image preprocessing the high gray interference area, removed lumps false positive test results area on each application improved hierarchical model in this article, the method to get the lumps of demarcation accurate, mass The detection rate of 98.1%. 2 to achieve a mass recognition method based on multiple breast X-ray image. First, according to the design based on the nipple of the breast contour and pectoral line positioning method to select the reference position, to match the breast ipsilateral CC view and MLO view and segmented regions based on the reference position, the two-view match; according to their own breast lumps characteristics matching area features information extraction; Finally breast mass recognition using BP neural network model. Practice shows that the application of the same BP network design method and image library algorithm verify the correct rate of 84.2%, based on the a single breast X-ray image detection method lumps identify this research is based on the detection of X-ray images of multiple breast lumps identify the correct rate of 88.7%. Compared with the mass detection method based on the a single breast X-ray image, the fusion image of multiple breast lumps detection methods known the amount of information to increase the reliability and validity of the information, mass recognition accuracy have been increased. The research is a good solution to the problem of insufficient amount of information based on the single X-ray image of the breast lump detection system commonly used to provide new solutions for improved detection system for breast cancer adjuvant.

Related Dissertations

  1. Preparation of Recombinant Human bFGF, Anti-bFGF Polyclonal Antibody and Their Primary Application in Tumor Detection,Q789
  2. Diagnosis Technology Research of Mammographic Masses Based on Content-based Image Retrieval,TP391.41
  3. Research on Techniques of Computer-aided Diagnosis of Breast Cancer for Mammography,TP29-AI
  4. Research on Computer-Aided Breast Masses Detection Algorithms,TP391.41
  5. A Study on Quality Identification of Surrounding Rock Based on Dynamical Response of Integrated Anchor System,TU457
  6. Preparation of Recombinant Human Angiogenin Protein and Polycional Antibody and Primary Study in Tumor Detection,Q789
  7. Automatically detect cancerous breast X - ray information theory,R737.9
  8. Research of Volcanic Rock Reservoir Evaluation and Accumulation Rule in K301 Region of Zhungarica Basin,P618.13
  9. A Study on Magnetoacoustic Tomography with Magnetic Induction (MAT-MI) for Imaging Electrical Impedance of Biological Tissue,O441.3
  10. Design and Approach of UWB Near-field Medical Detection System,TH776
  11. Research on Basic Algorithms of Digital Image Processing and Implementation with FPGA,TP391.41
  12. Research on Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  13. Research of High Speed Image Pre-processing System Based on FPGA,TP391.41
  14. Research on Algorithms of 2D Face Template Protection,TP391.41
  15. The Research and Implemention of Image Retrieval Based on User Interested Feature,TP391.41
  16. Research of Image Mosaic Technology,TP391.41
  17. Research and Implementation of Exact String Matchiing Algorithms,TP391.41
  18. Research on the Classification Based on the Reconstruction of Solder Joint,TP391.41
  19. Tongue Feature Extraction and Research of Fusion Classification,TP391.41
  20. The Fatigue State Recognition of the Driver Based on Eye Detection,TP391.41
  21. Research on Infrared Image Simulation for Aerial Objects and Background,TP391.41

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