A hybrid classification model for digital pathology using structural and statistical pattern recognition

Date
2013
Authors
Ozdemir, E.
Gunduz-Demir, C.
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
IEEE Transactions on Medical Imaging
Print ISSN
0278-0062
Electronic ISSN
Publisher
Institute of Electrical and Electronics Engineers
Volume
32
Issue
2
Pages
474 - 483
Language
English
Type
Article
Journal Title
Journal ISSN
Volume Title
Series
Abstract

Cancer causes deviations in the distribution of cells, leading to changes in biological structures that they form. Correct localization and characterization of these structures are crucial for accurate cancer diagnosis and grading. In this paper, we introduce an effective hybrid model that employs both structural and statistical pattern recognition techniques to locate and characterize the biological structures in a tissue image for tissue quantification. To this end, this hybrid model defines an attributed graph for a tissue image and a set of query graphs as a reference to the normal biological structure. It then locates key regions that are most similar to a normal biological structure by searching the query graphs over the entire tissue graph. Unlike conventional approaches, this hybrid model quantifies the located key regions with two different types of features extracted using structural and statistical techniques. The first type includes embedding of graph edit distances to the query graphs whereas the second one comprises textural features of the key regions. Working with colon tissue images, our experiments demonstrate that the proposed hybrid model leads to higher classification accuracies, compared against the conventional approaches that use only statistical techniques for tissue quantification. © 2012 IEEE.

Course
Other identifiers
Book Title
Keywords
Automated cancer diagnosis, Cancer, Graph embedding, Histopathological image analysis, Inexact graph matching, Structural pattern recognition, Tissue characterization, Methodology, Reproducibility, Sensitivity and specificity, Statistical analysis, Statistical model, Three dimensional imaging, Biopsy, Computer simulation, Data interpretation, Image enhancement
Citation
Published Version (Please cite this version)