YorkSpace has migrated to a new version of its software. Access our Help Resources to learn how to use the refreshed site. Contact diginit@yorku.ca if you have any questions about the migration.
 

Machine Learning and its Application in Automatic Change Detection in Medical Images

Simple item page
dc.contributor.advisorHongmei Zhu, Hongmei
dc.contributor.advisorBabyn, Paul
dc.creatorNika, Varvara
dc.date.accessioned2015-08-28T15:07:28Z
dc.date.available2015-08-28T15:07:28Z
dc.date.copyright2014-11-21
dc.date.issued2015-08-28
dc.date.updated2015-08-28T15:07:28Z
dc.degree.disciplineMathematics & Statistics
dc.degree.levelDoctoral
dc.degree.namePhD - Doctor of Philosophy
dc.description.abstractChange detection is a fundamental problem in various fields, such as image surveillance, remote sensing, medical imaging, etc. The challenge of change detection in medical images is to detect disease-related changes while rejecting changes caused by noise, patient position change, and imaging acquisition artifacts such as field inhomogeneity. In this thesis, first, we overview the existing change detection methods, their underlying mathematical frameworks and limitations. Second, we present our contributions in solving the problem. We design optimal subspaces to approximate the background image in more efficient fashion. This is based on our structure principal component analysis, aiming to capture the structural similarity between scans in the context of change detection. We theoretically and numerically discuss the proper choices of norms used in the subspace approximation. The mathematical frameworks developed in this thesis consist of: (i) a new mathematical model to change detection by defining it as an optimization problem involving a cost function, input and output image sets, projection onto a subspace, and a similarity measure; (ii) development and implementation of numerical pipelines to compute the clinical changes by designing four mathematical algorithms; (iii) refining our algorithms by introducing the co-registration step utilizing the local dictionaries; and (iv) two new structure subspace learning models that are robust to outliers and noise, reduce the dimensionality of the dataset, and computationally efficient. We defined the co-registration step as a minimization problem involving a cost function, input and output image sets, a set of transform functions, projection onto a subspace, and a similarity measure. Based on the mathematical frameworks discussed above, numerical schemes are developed to automatically filter out clinically unrelated changes and identify true structure changes that may be of clinical importance. Our approaches are data-driven and utilize the knowledge of machine learning. We quantitatively analyze the performance of these algorithms using both synthetic and real human data. Our work has the potential to be used in computer aided diagnosis.
dc.identifier.urihttp://hdl.handle.net/10315/29947
dc.language.isoen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectMathematics
dc.subjectComputer science
dc.subjectMedical imaging and radiology
dc.subject.keywordsMachine learning
dc.subject.keywordsDictionary learning
dc.subject.keywordsChange detection
dc.subject.keywordsComputer-aided diagnosis
dc.subject.keywordsSubspace learning
dc.subject.keywordsMedical imaging
dc.subject.keywordsSparsity
dc.subject.keywordsCompressive sensing
dc.subject.keywordsCo-registration
dc.subject.keywordsEigenblock
dc.subject.keywordsStructure similarity
dc.subject.keywordsL1-norm
dc.subject.keywordsL2-norm
dc.subject.keywordsConvex optimization
dc.subject.keywordsDimensionality reduction
dc.subject.keywordsAdaptive dictionary
dc.subject.keywordsComponent analysis
dc.subject.keywordsPrincipal
dc.subject.keywordsSimilarity measure
dc.subject.keywordsEigensubspace
dc.titleMachine Learning and its Application in Automatic Change Detection in Medical Images
dc.typeElectronic Thesis or Dissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Nika_Varvara_2014_PhD.pdf
Size:
16.79 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.83 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.38 KB
Format:
Plain Text
Description:
Download

Collections

Mathematics & Statistics

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.