Dissertation > Excellent graduate degree dissertation topics show

Clustered Calcification Computer-aided Detection and Analysis for Mammographic Images Based on Statistical Models

Author: ZhangXin
Tutor: FengZuo
School: Northwestern University
Course: Computer Software and Theory
Keywords: image breast computer-aided detection texture statistical models
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 46
Quote: 4
Read: Download Dissertation

Abstract


In this paper, an algorithm for shape description and detection of clustered calcification based on statistical texture models is proposed. We extract the region of interests for clustered calcification firstly. Then normal and lesion training samples are incorporated into statistical texture models separately by principal component analysis. Specifically, we obtains a series of statistical parameters to describe unknown samples after it. Both normal and lesion statistical models and corresponding parameters can also be used for unknown sample representation and classification. We also Fourier transform and high-dimensional feature extraction of each region of interest. Then, compare and analysis of the three different results, texture modeling results, frequency domain modeling results and feature modeling results, with support vector machine classification results. The main contents of this paper are listed as follows:1) Extract the region of interest for breast imagesSelect the lesion images and normal images of breast with obvious characteristics according to contribution matrix. At the same time, we extract the texture features、spatial features and frequency domain features of each breast images, and then take them as the training samples for statistical models.2) Establishment of the statistical model of breast imagesEstablish three different statistical models by the training samples which we obtained at the first step. The three different statistical models are texture statistical models、frequency domain statistical models and feature statistical models. After establish the statistical models, we get a series of parameters to describe the training samples.3) Detect the breast lesion images based on statistical modelsAfter detect the breast lesion images uses the three different statistical models, we compare the three different result with the SVM algorithms.4) Design and implementation of a computer-aided breast cancer detection system The experimental results show that the texture modeling result depend on sample selection to some extent, and the frequency domain modeling results has better performance than the traditional SVM based classifiers. The greatest advantage of statistical texture models is that it can formed a series of parameters to describe and streamline the breast images.

Related Dissertations

  1. Based on OGC WPS standard spatial statistics PSE and PSE-SDBI achieve research,TP393.09
  2. Research on Segmentation Methods Based on MRF Model from SAR Images,TN957.52
  3. Semantic Structure Identification Based on PCFG-HDSM Model,TP391.1
  4. Complex background of face detection and localization,TP391.4
  5. Research on Monitoring Model of Seepage Flow around Hydraulic Structure,TV698.1
  6. Face Detection and Tracking in Color Image Sequences,TP391.41
  7. A Study on Characteristics and Cancellation of Clutter in Passive Radar Based on Opportunity Transmitters,TN958
  8. Study on Seismic Subsidence of Loess and Negative Skin Friction Along Piles by Field Test,TU473.1
  9. Research on Techniques of Computer-aided Diagnosis of Breast Cancer for Mammography,TP29-AI
  10. Breast tumor ultrasound image segmentation algorithm dynamic contour Research and Application,TP391.41
  11. Computer-Aided Detection Based on Textural Features and High-performance Classifiers,TP391.41
  12. Research on Facial Feature Extraction and Matching Algorithms for Image Retrieval,TP391.41
  13. Tongue Feature Extraction and Research of Fusion Classification,TP391.41
  14. Research on Joint Target Detection for Dual-Sensor Image and System Implementation,TP391.41
  15. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  16. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  17. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  18. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  19. Study on Virtual Detector of Infrared Hyper-Spectral Image,TP391.41
  20. Research on Removal Algorithm of Shadows in Image Segmentation,TP391.41
  21. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  22. 3D Visualization Research of Medicial Ultrasound Image,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