Epithelial area detection in cytokeratin microscopic images using MSER segmentation in an anisotropic pyramid

Authors:
Cristian Smochina;Radu Rogojanu;Vasile Manta;Walter Kropatsch
Affiliations:
Faculty of Automatic Control and Computer Engineering, "Gheorghe Asachi" Technical University of Iasi, Romania;Institute of Pathophysiology and Allergy Research, Medical University, Vienna, Austria;Faculty of Automatic Control and Computer Engineering, "Gheorghe Asachi" Technical University of Iasi, Romania;Pattern Recognition and Image Processing Group, Institute of Computer Graphics and Algorithms, Vienna University of Technology, Austria
Venue:
PRIB'11 Proceedings of the 6th IAPR international conference on Pattern recognition in bioinformatics
Year:
2011

Citing 6
Cited 0

Digital Image Processing

Digital Image Processing
An Anisotrophic Diffusion Algorithm with Optimized Rotation Invariance

Mustererkennung 2000, 22. DAGM-Symposium
A Comparison of Affine Region Detectors

International Journal of Computer Vision
3D Segmentation by Maximally Stable Volumes (MSVs)

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Semantic segmentation of microscopic images using a morphological hierarchy

CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I
Are MSER Features Really Interesting?

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of semantic segmentation in microscopic images is to extract the cellular, nuclear or tissue components. This problem is challenging due to the large variations of features of these components (size, shape, orientation or texture). In this paper we present an automatic technique to robustly delimit the epithelial area (crypts) in microscopic images taken from colon tissues sections marked with cytokeratin-8. The epithelial area is highlighted using the anisotropic diffusion pyramid and segmented using MSER+. The crypts separation and lumen detection is performed by imposing topological constraints about the epithelial layer distribution within the tissue and the round-like shape of the crypt. The evaluation of the proposed method is made by comparing the results with ground-truth segmentations.