THE CORRELATION ANALYSIS OF THE SHAPE PARAMETERS FOR ENDOTHELIAL IMAGE CHARACTERISATION

Authors

  • Karolina Nurzynska Institute of Informatics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology
  • Adam Piorkowski AGH University of Science and Technology, Departament of Geoinformatics and Applied Computer Science

DOI:

https://doi.org/10.5566/ias.1554

Keywords:

correlation analysis, endothelial images, shape parameters

Abstract

Microscopic images of corneal endothelium cells are investigated to deliver information about their medical state. Although this could be achieved automatically, this examination is manual and very time consuming. Two medical parameters for endothelial layer quality description have been introduced and more are planned. Yet, since they will exploit image processing, a thoughtful overview of applicable existing shape parameters is necessary. This work investigates the possibility of exploiting well-known image processing techniques for describing the endothelial layer by calculating information about shape features using spatial moments or topological attributes. The comparison concentrates on finding which shape measures could be combined to improve descriptions, and which cannot due to their high correlation and the fact that they do not contain any new information. The performed experiments revealed a set of 17 non-correlated features and four groups of shape parameters that show some correlation, but one representative can always be selected. Moreover, the investigation proved some correlation between the metrics used in medicine and considered shape features. 

References

Agarwal S, Agarwal A, Apple D, Buratto L (2002).

Textbook of ophthalmology, vol. 2.

New Dehli: Jaypee Brothers, Medical Publishers Ltd.

Ayala G, Diaz M, Martinez-Costa L (2001).

Granulometric moments and corneal endothelium status.

Pattern Recogn 34:1219-27.

Bernander KB, Gustavsson K, Selig B, Sintorn IM, Luengo Hendriks CL (2013).

Improving the stochastic watershed.

Pattern Recogn Lett 34:993-1000.

Caetano CAC, Entura L, Sousa SJ, Tufo REA (2000).

Identification and segmentation of cells in images of donated corneas

using mathematical morphology.

In: Computer graphics and image processing, 2000. Proceedings XIII

Brazilian Symposium on. IEEE. Oct. 17-20, 2000, Gramado, Brasil.

Charłampowicz K, Reska D, Boldak C (2014).

Automatic segmentation of corneal endothelial cells using active

contours.

Adv Comp Sc Res 11:47-60.

Dagher I, El Tom K (2008).

Waterballoons: A hybrid watershed balloon snake segmentation.

Image and Vi Comp 26:905-12.

Diaz ME, Ayala G, Sebastian R, Martinez-Costa L (2007).

Granulometric analysis of corneal endothelium specular images by

using a germ-grain model.

Comp Biol Medi 37:364-75.

Doughty M (1990).

The ambiguous coefficient of variation: Polymegethism of the corneal

endothelium and central corneal thickness.

International Contact Lens Clinic 17:240-8.

Doughty M (1992).

Concerning the symmetry of the hexagonal cells of the corneal

endothelium.

Exp Eye Res 55:145-54.

Foracchia M, Ruggeri A (2000).

Cell contour detection in corneal endothelium in-vivo microscopy.

In: Engineering in Medicine and Biology Society, 2000. Proceedings of

the 22nd Annual International Conference of the IEEE, vol. 2. IEEE. Jul. 23-28, 2000, Buenos Aires, Argentina.

Foracchia M, Ruggeri A (2003).

Corneal endothelium analysis by means of bayesian shape modeling.

In: Proc. 25th Annual International Conference of the IEEE-EMBS.

IEEE. Sep. 17-21, 2003, Cancun, Mexico.

Foracchia M, Ruggeri A (2007).

Corneal endothelium cell field analysis by means of interacting

bayesian shape models.

In: Engineering in medicine and biology society, 2007. EMBS 2007.

th Annual International Conference of the IEEE. IEEE. Aug. 23-26, 2007. Lyon, France.

Gavet Y, Pinoli JC (2008).

Visual perception based automatic recognition of cell mosaics in

human corneal endotheliummicroscopy images.

Image Anal Stereol 27:53-61.

Gavet Y, Pinoli JC (2013).

Human visual perception and dissimilarity.

SPIE Newsroom .

Gonzalez RC, Woods RE (2001).

Digital image processing.

Boston, MA, USA: Addison-Wesley Longman Publishing Co., Inc., 2nd ed.

Gronkowska-Serafin J, Piorkowski A (2014).

Corneal endothelial grid structure factor based on coefficient of

variation of the cell sides lengths.

In: Image processing and communications challenges 5,

Advances in intelligent systems and computing. 233: 13-9.

Habrat K, Habrat M, Gronkowska-Serafin J, Piorkowski A (2016).

Cell detection in corneal endothelial images using directional

filters.

In: Image processing and communications challenges 7, Advances in Intelligent Systems and Computing, 389: 113-23.

Hasegawa A, Itoh K, Ichioka Y (1996).

Generalization of shift invariant neural networks: image processing

of corneal endothelium.

Neural Networks 9:345-56.

Hu MK (1962).

Visual pattern recognition by moment invariants, computer methods in

image analysis.

IRE Transactions on information theory 8.

Jahne B (2002).

Digital image processing: concepts, algorithms, and scientific

applications.

Secaucus, NJ, USA: Springer-Verlag New York, Inc., 5th ed.

Khan MAU, Niazi MKK, Khan MA, Ibrahim MT (2007).

Endothelial cell image enhancement using non-subsampled image

pyramid.

Inform Technol 6:1057-62.

Ko M, Lee J, Chi J (2000).

Cell density of the corneal endothelium in human fetus by flat

preparation.

Cornea 19:80-3.

Ko M, Park W, Lee J, Chi J (2001).

A histomorphometric study of corneal endothelial cells in normal

human foetuses.

Exp Eye Res 72:403-9.

Latała Z, Wojnar L (2001).

Computer-aided versus manual grain size assessment in a single phase

material.

Mater Charact 46:227 - 233.

Mahzoun M, Okazaki K, Mitsumoto H, Kawai H, Sato Y, Tamura S, Kani K (1996).

Detection and complement of hexagonal borders in corneal endothelial

cell image.

Med Imaging Technol 14:56-69.

Malmberg F, Selig B, Luengo Hendriks C (2014).

Exact evaluation of stochastic watersheds: From trees to general

graphs.

In: Barcucci E, Frosini A, Rinaldi S, eds., Discrete geometry for

computer imagery, Lect Notes Comp Sci.

Springer International Publishing, 8668: 309-19.

Meijering E (2012).

Cell segmentation: 50 years down the road [life sciences].

Signal Processing Magazine IEEE 29:140-5.

Meyer L, Ubels J, Edelhauser H (1988).

Corneal endothelial morphology in the rat.

Invest Ophthalmol Vis Sci 29:940-9.

Nadachi R, Nunokawa K (1992).

Automated corneal endothelial cell analysis.

In: Computer-based medical systems, 1992. Proceedings., Fifth Annual

IEEE Symposium on. IEEE. Jun. 14-17, 1992, Durham, North Carolina, USA.

Ollivier F, Brooks D, Komaromy A, Kallberg M, Andrew S, Sapp H, Sherwood M,

Dawson W (2003).

Corneal thickness and endothelial cell density measured by

non-contact specular microscopy and pachymetry in rhesus macaques (macaca

mulatta) with laser-induced ocular hypertension.

Exp Eye Res 76:671-7.

Oszutowska-Mazurek D, Mazurek P, Derda K, Sycz K, Waker-Wójciuk G (2015).

Sensitivity of nuclear-cytoplasmic index and nuclear-cytoplasmic

relation in computer aided cytoscreening diagnosis.

Przeglad Elektrotechniczny 91:56-8.

Oszutowska-Mazurek D, Mazurek P, Sycz K, Waker-Wójciuk G (2012).

Estimation of fractal dimension according to optical density of cell

nuclei in papanicolaou smears.

In: Information Technologies in Biomedicine,

Lect Notes Comp Sc. Springer, 7339:456-63.

Oszutowska-Mazurek D, Mazurek P, Sycz K, Waker-Wójciuk G (2013).

Variogram based estimator of fractal dimension for the analysis of

cell nuclei from the papanicolaou smears.

In: Image Processing and Communications Challenges 4, Advances in Intelligent Systems and Computing. Springer, 184:47-54.

Piorkowski A, Gronkowska-Serafin J (2015).

Towards precise segmentation of corneal endothelial cells.

In: Bioinformatics and Biomedical Engineering,

Lect Notes Comp Sc. 9043:240-9.

Piorkowski A, Mazurek P, Gronkowska-Serafin J (2015).

Comparison of assessment regularity methods dedicated to isotropic

cells structures analysis.

In: Image Processing and Communications Challenges 6, Advances in Intelligent Systems and Computing, 313:169-78.

Piorkowski A, Nurzynska K, Gronkowska-Serafin J, Selig B, Boldak C, Reska D

(2016).

Influence of applied corneal endothelium image segmentation

techniques on the clinical parameters.

Comp Med Imaging Graphics. DOI:10.1016/j.compmedimag.2016.07.010

Poletti E, Ruggeri A (2014).

Segmentation of corneal endothelial cells contour through

classification of individual component signatures.

In: XIII Mediterranean Conference on Medical and Biological

Engineering and Computing 2013. Springer. Sep. 25-28, 2013, Seville, Spain.

Rao GN, Lohman L, Aquavella J (1982).

Cell size-shape relationships in corneal endothelium.

Invest Ophthal Vis Sc 22:271-4.

Ruggeri A, Scarpa F (2015).

Computerized analysis of human corneal endothelium morphology.

Acta Ophthalmol 93. doi:10.1111/j.1755-3768.2015.0551

Ruggeri A, Scarpa F, De Luca M, Meltendorf C, Schroeter J (2010).

A system for the automatic estimation of morphometric parameters of

corneal endothelium in alizarine red stained images.

Br J Ophthalmol 94:643-7.

Russ J (1998).

The Image Processing Handbook.

CRC Press, Springer, and IEEE Press, 3rd ed.

Saeed K, Tabędzki M, Rybnik M, Adamski M (2010).

K3M: A universal algorithm for image skeletonization and a review of thinning techniques.

Int Appl Math Comp

:317-35.

Sanchez-Marin F (1999).

Automatic segmentation of contours of corneal cells.

Comput Biol Med 29:243-58.

Scarpa F, Ruggeri A (2015).

Segmentation of corneal endothelial cells contour by means of a

genetic algorithm.

In: Ophthalmic medical image analysis. Second International Workshop.

Selig B, Malmberg F, Luengo Hendriks CL (2015a).

Fast evaluation of the robust stochastic watershed.

In: Mathematical morphology and its applications to signal and image processing: Proceedings of the 12th International Syposium on Mathematical

Morphology, Reykjavik, Iceland, May 27-29, Lect Notes Comp Sc, 9082:705-716 .

Selig B, Vermeer KA, Rieger B, Hillenaar T, Luengo Hendriks CL

(2015b).

Fully automatic evaluation of the corneal endothelium from in vivo

confocal microscopy.

BMC Med Imaging 15.

Serra J, Mlynarczuk M (2000).

Morphological merging of multidimensional data.

Proceedings of STERMAT 2000 :385-90.

Vincent LM, Masters BR (1992).

Morphological image processing and network analysis of cornea

endothelial cell images.

San Diego'92. International Society for Optics and

Photonics. 1769:212-226

Zapter V, Martinez-Costa L, Ayala G (2005).

A granulometric analysis of specular microscopy images of human

corneal endothelia.

Comp Vis Image Und 97:297-314.

Zhou Y (2007).

Cell segmentation using level set method.

Master's thesis, Johannes Kepler Universitat, Linz.

Downloads

Published

2016-12-08

Issue

Section

Original Research Paper

How to Cite

Nurzynska, K., & Piorkowski, A. (2016). THE CORRELATION ANALYSIS OF THE SHAPE PARAMETERS FOR ENDOTHELIAL IMAGE CHARACTERISATION. Image Analysis and Stereology, 35(3), 149-158. https://doi.org/10.5566/ias.1554