Back to Search
Start Over
Multilevel Segmentation of Histopathological Images Using Cooccurrence of Tissue Objects
- Source :
- IEEE Transactions on Biomedical Engineering
- Publication Year :
- 2012
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2012.
-
Abstract
- This paper presents a new approach for unsupervised segmentation of histopathological tissue images. This approach has two main contributions. First, it introduces a new set of high-level texture features to represent the prior knowledge of spatial organization of the tissue components. These texture features are defined on the tissue components, which are approximately represented by tissue objects, and quantify the frequency of two component types being cooccurred in a particular spatial relationship. As they are defined on components, rather than on image pixels, these object cooccurrence features are expected to be less vulnerable to noise and variations that are typically observed at the pixel level of tissue images. Second, it proposes to obtain multiple segmentations by multilevel partitioning of a graph constructed on the tissue objects and combine them by an ensemble function. This multilevel graph partitioning algorithm introduces randomization in graph construction and refinements in its multilevel scheme to increase diversity of individual segmentations, and thus, improve the final result. The experiments on 200 colon tissue images reveal that the proposed approachthe object cooccurrence features together with the multilevel segmentation algorithmis effective to obtain high-quality results. The experiments also show that it improves the segmentation results compared to the previous approaches. © 1964-2012 IEEE.
- Subjects :
- Computer science
Biopsy
Image pixels
High quality
Pixels
Pattern Recognition, Automated
Image texture
Multi-level partitioning
Co-occurrence
Graph construction
Tissue images
image quality
Multilevel segmentation
Segmentation
Computer vision
Colon tissue images
Texture features
Image segmentation
article
Graph partition
Textures
Multiple segmentation
colon biopsy
Prior knowledge
Spatial organization
immunohistochemistry
Colonic Neoplasms
cytoplasm
histopathology
Graph (abstract data type)
Algorithms
Two-component
Multilevel graph partitioning
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Biomedical Engineering
Segmentation results
Adenocarcinoma
Spatial relationships
Sensitivity and Specificity
Segmentation ensemble
Co-occurrence features
Histopathological image analysis
mucin
image analysis
Image Interpretation, Computer-Assisted
Humans
controlled study
Texture
Unsupervised segmentation
Tissue
algorithm
colon
Pixel
business.industry
scoring system
Reproducibility of Results
Pattern recognition
Graph theory
Image Enhancement
Histopathological images
Pixel level
Artificial intelligence
Experiments
epithelium cell
business
Tissue components
mathematical model
Subjects
Details
- ISSN :
- 15582531 and 00189294
- Volume :
- 59
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Biomedical Engineering
- Accession number :
- edsair.doi.dedup.....b86ad030cf9e239fb8cbc0b4b00e9505