Dissertation > Excellent graduate degree dissertation topics show

The Research of Medical Image Analysis Based on Cost Sensitive Boosting

Author: YaoZuo
Tutor: ZhangSu
School: Shanghai Jiaotong University
Course: Biomedical Engineering
Keywords: Cost-Sensitive Boosting False Negative False Positive Medical Image Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 32
Quote: 0
Read: Download Dissertation

Abstract


Medical imaging technology plays an important role in medicaldetection. The computer aided medical image analysis, includingclassification, detection and recognition, is expected to raise the detectionrate and serve quantified reference basis to doctors. Furthermore, it iswidely used in review analysis and medical training. The traditionalclassification algorithms, with target to minimize the error rate, treat twotypes of errors (false negative and false positive) equally. However,medical diagnosis is a typical cost-sensitive problem, in which the cost offalse negative decision is rather critical than false positive. Thecost-insensitive models usually perform weak in controlling specific errorrate, and a cost-sensitive extension is needed to solve this kind ofproblem. Our work is focused on the research of medical image analysisbased on cost sensitive boosting.First, we analyze the cost-sensitive model and Boosting algorithm.As simple threshold manipulation is not able to provide prefectcost-sensitive performance in boosing， cost loss function and costweight-update strategy are introduced to change Boosting trainingemphasis to cost-sensitive neighborhood. It is used to derivecost-sensitive extension on AdaBoost, RealBoost and LogitBoost. Theexperiment on UCI dataset is conducted to verify the programmed costalgorithm，and comparing with cost-insensitive Boosting.Second, we discuss the application based on cost-sensitiveBoosting in the recognition between benign and malignant in breastcancer ultrasound image. The image feature is extracted according toBI-RADS (Breast imaging report and data system), and a more simplifiedsub-feature set is obtained through mRMR (minimal redundancy maximalrelevance) algorithm. Three cost-sensitive Boosting models are trainedand optimal classification parameters are set by tests. The experiment shows cost-sensitive AdaBoost performs the best, with AUC (area underROC curve) at0.859in the condition of controlled false negative rate at5%, and three of cost-sensitive model performs better thancost-insensitive ones.And then, we discuss the application based on cost-sensitiveBoosting in the abnormality detection on gastroscopic image. In theimage preprocess, specular reflection detection through IS (Intensity andSaturation) distribution is presented. Considering illuminationinsensitivity and rotation insensitivity, normalized color spaces, rg and hsspace, as well as normalized LBP (Local Binary Pattern) are introducedfor feature extraction. Then, patch method is used for classifier trainingand detection. Three cost-sensitive models are constructed and comparedwith cost-insensitive ones. The experiment shows that cost-sensitivealgorithm performs better in false negative controlling, and detection rateis raised through patch assemble.The cost-sensitive extension of Boosting, with application inmedical image analysis, could control false negative better and performwell generally.

Related Dissertations

  1. Mammographic X-ray analysis of false-negative breast cancer,R737.9
  2. Capture - recapture method in the investigation of the cause of death recalled Research and Application,R195
  3. A Study of Pathology Image Analysis of Tissue Remodeling Caused by Hypertension,R318
  4. The Research of Anomaly Based Intrusion Detection,TP393.08
  5. Application of Polymerase Chain Reaction for Detection of IgH and TCR Gene Rearrangements in Non-Hodgkin Lymphoma,R733.1
  6. Distributed Intrusion Detection System Research and Implementation of detection agents,TP393.08
  7. Information Hiding and Detection Technology Research and Application,TP309
  8. Research on the Detection and Defense of DdoS Based on Routing Collaboration,TP393.08
  9. The design of antivirus software error testing system based on Cloud-AV,TP311.53
  10. The Clinical Analysis of Continuous Electronic Intrapartum Fetal Heart Rate Monitoring in1011Pregnant Women,R714.5
  11. Diagnostic Role of18F-FDG PET/CT in Monitoring the Response of Locally Advanced Breast Cancer to Neo-Adjuvant Chemotherapy: A Meta-Analysis,R737.9
  12. 65Cases Clinical Analysis of Sentinel Lymph Node Biopsy Combined with Suspicious Lymph Node Sampling in Breast Cancer,R737.9
  13. Effect of Thin-section Diffution-weighted Imaging on Acute Cerebral Infarction Diagnosis,R743.3
  14. Analysis of Experimental Measurement and Calculation Methods of Detection Limit,O651
  15. Research on the Cardiac Sequential Image Analysis,R318
  16. Machine Learning Approaches to Medical Image Analysis,TP391.41
  17. Identification by mRNA Differential Display of Genes Possibly Associated with Metastasis of a Mouse Mammary Cancer MA891,R737.9
  18. Qualitatively Different Portal Hypertension: MSCT Angiography and Interventionals,R575.2
  19. Clinical and Pathological Study on the Sentinel Lymph Node in Gastric Cancer,R735.2
  20. The Research on the Quality Control Methods of Database Search Results of Tandem Mass Spectrometry Data in Proteomics,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