Crypts detection in microscopic images using hierarchical structures

This paper presents an extended and improved version of an automatic technique which robustly identifies the epithelial nuclei (crypt) against interstitial nuclei in microscopic images taken from colon tissues. The detection of the crypt inner boundary is performed using the closing morphological hierarchy. The disadvantages of this approach related to the execution time and the used memory are highlighted and the morphological pyramid is used instead due to its computational efficiency, the reduced amount of used memory and the increased robustness. An analysis of the two approaches is performed considering the number of processed pixels, the used memory and the complexity. The outer border is determined by the epithelial nuclei overlapped by the maximal isoline of the inner boundary. The percentage of the mis-segmented nuclei against epithelial nuclei per crypt is used to evaluate the proposed methods. The limitations are described in order to highlight the situations in which the current approaches do not provide suitable results.

[1]  W. Kropatsch,et al.  Sampling step importance in hierarchical semantic segmentation of microscopic images , 2011, 15th International Conference on System Theory, Control and Computing.

[2]  H. Wu,et al.  Segmentation of intestinal gland images with iterative region growing , 2005, Journal of microscopy.

[3]  Cenk Sokmensuer,et al.  Automatic segmentation of colon glands using object-graphs , 2010, Medical Image Anal..

[4]  Xinhua Zhuang,et al.  The digital morphological sampling theorem , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[5]  A. Madabhushi,et al.  Gland Segmentation and Computerized Gleason Grading of Prostate Histology by Integrating Low-, High-level and Domain Specific Information , 2007 .

[6]  Mohamed F. Tolba,et al.  MR-Brain Image Segmentation Using Gaussian Multiresolution Analysis and the EM Algorithm , 2003, ICEIS.

[7]  Tim W. Nattkemper,et al.  Automatic segmentation of digital micrographs: A survey , 2004, MedInfo.

[8]  G. Raju,et al.  The Dual Tree Complex Wavelet Packet Transform : A Review , 2011 .

[9]  Barry R. Masters,et al.  Digital Image Processing, Third Edition , 2009 .

[10]  Yll Haxhimusa,et al.  Multiresolution Image Segmentations in Graph Pyramids , 2007, Applied Graph Theory in Computer Vision and Pattern Recognition.

[11]  Abderrahim Elmoataz,et al.  Graph-based tools for microscopic cellular image segmentation , 2009, Pattern Recognit..

[12]  Yll Haxhimusa,et al.  Vision pyramids that do not grow too high , 2005, Pattern Recognit. Lett..

[13]  N. Wright,et al.  Colonic crypt organization and tumorigenesis , 2008, Nature Reviews Cancer.

[14]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[15]  Walter G. Kropatsch,et al.  Semantic Segmentation of Microscopic Images Using a Morphological Hierarchy , 2011, CAIP.

[16]  Gwo Giun Lee,et al.  Image segmentation using multiresolution wavelet analysis and expectation‐maximization (EM) algorithm for digital mammography , 1997 .

[17]  K Morikawa,et al.  Visualization of individual DNA molecules in solution by light microscopy: DAPI staining method. , 1981, Journal of biochemistry.

[18]  R. A. Zoroofi,et al.  An image analysis approach for automatic malignancy determination of prostate pathological images , 2007, Cytometry. Part B, Clinical cytometry.

[19]  Peer Stelldinger,et al.  A topological sampling theorem for Robust boundary reconstruction and image segmentation , 2009, Discret. Appl. Math..

[20]  David G. Kirkpatrick,et al.  Linear Time Euclidean Distance Algorithms , 1995, IEEE Trans. Pattern Anal. Mach. Intell..