uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Selig, Bettina
Publications (9 of 9) Show all publications
Piorkowski, A., Nurzynska, K., Gronkowska-Serafin, J., Selig, B., Boldak, C. & Reska, D. (2017). Influence of applied corneal endothelium image segmentation techniques on the clinical parameters. Computerized Medical Imaging and Graphics, 55, 13-27
Open this publication in new window or tab >>Influence of applied corneal endothelium image segmentation techniques on the clinical parameters
Show others...
2017 (English)In: Computerized Medical Imaging and Graphics, ISSN 0895-6111, E-ISSN 1879-0771, Vol. 55, p. 13-27Article in journal (Refereed) Published
Abstract [en]

The corneal endothelium state is verified on the basis of an in vivo specular microscope image from which the shape and density of cells are exploited for data description. Due to the relatively low image quality resulting from a high magnification of the living, non-stained tissue, both manual and automatic analysis of the data is a challenging task. Although, many automatic or semi-automatic solutions have already been introduced, all of them are prone to inaccuracy. This work presents a comparison of four methods (fully-automated or semi-automated) for endothelial cell segmentation, all of which represent a different approach to cell segmentation; fast robust stochastic watershed (FRSW), KH method, active contours solution (SNAKE), and TOPCON ImageNET. Moreover, an improvement framework is introduced which aims to unify precise cell border location in images preprocessed with differing techniques. Finally, the influence of the selected methods on clinical parameters is examined, both with and without the improvement framework application. The experiments revealed that although the image segmentation approaches differ, the measures calculated for clinical parameters are in high accordance when CV (coefficient of variation), and CVSL (coefficient of variation of cell sides length) are considered. Higher variation was noticed for the H (hexagonality) metric. Utilisation of the improvement framework assured better repeatability of precise endothelial cell border location between the methods while diminishing the dispersion of clinical parameter values calculated for such images. Finally, it was proven statistically that the image processing method applied for endothelial cell analysis does not influence the ability to differentiate between the images using medical parameters.

Keywords
The corneal endothelium cells, Non-contact specular microscope, Image processing, Segmentation
National Category
Radiology, Nuclear Medicine and Medical Imaging Computer and Information Sciences
Identifiers
urn:nbn:se:uu:diva-316420 (URN)10.1016/j.compmedimag.2016.07.010 (DOI)000392685900003 ()27553657 (PubMedID)
Available from: 2017-03-02 Created: 2017-03-02 Last updated: 2018-01-13Bibliographically approved
Selig, B., Malmberg, F. & Luengo Hendriks, C. L. (2015). Fast evaluation of the robust stochastic watershed. In: Mathematical Morphology and Its Applications to Signal and Image Processing: . Paper presented at ISMM 2015, May 27–29, Reykjavik, Iceland (pp. 705-716). Springer
Open this publication in new window or tab >>Fast evaluation of the robust stochastic watershed
2015 (English)In: Mathematical Morphology and Its Applications to Signal and Image Processing, Springer, 2015, p. 705-716Conference paper, Published paper (Refereed)
Abstract [en]

The stochastic watershed is a segmentation algorithm that estimates the importance of each boundary by repeatedly segmenting the image using a watershed with randomly placed seeds. Recently, this algorithm was further developed in two directions: (1) The exact evaluation algorithm efficiently produces the result of the stochastic watershed with an infinite number of repetitions. This algorithm computes the probability for each boundary to be found by a watershed with random seeds, making the result deterministic and much faster. (2) The robust stochastic watershed improves the usefulness of the segmentation result by avoiding false edges in large regions of uniform intensity. This algorithm simply adds noise to the input image for each repetition of the watershed with random seeds. In this paper, we combine these two algorithms into a method that produces a segmentation result comparable to the robust stochastic watershed, with a considerably reduced computation time. We propose to run the exact evaluation algorithm three times, with uniform noise added to the input image, to produce three different estimates of probabilities for the edges. We combine these three estimates with the geometric mean. In a relatively simple segmentation problem, F-measures averaged over the results on 46 images were identical to those of the robust stochastic watershed, but the computation times were an order of magnitude shorter.

Place, publisher, year, edition, pages
Springer, 2015
Series
Lecture Notes in Computer Science ; 9082
Keywords
Stochastic watershed, Watershed cuts, Monte Carlo simulations
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-254743 (URN)10.1007/978-3-319-18720-4_59 (DOI)000362366800059 ()978-3-319-18719-8 (ISBN)
Conference
ISMM 2015, May 27–29, Reykjavik, Iceland
Available from: 2015-06-10 Created: 2015-06-10 Last updated: 2018-01-11Bibliographically approved
Selig, B., Vermeer, K. A., Rieger, B., Hillenaar, T. & Luengo Hendriks, C. L. (2015). Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy. BMC Medical Imaging, 15, Article ID 13.
Open this publication in new window or tab >>Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy
Show others...
2015 (English)In: BMC Medical Imaging, ISSN 1471-2342, E-ISSN 1471-2342, Vol. 15, article id 13Article in journal (Refereed) Published
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-254738 (URN)10.1186/s12880-015-0054-3 (DOI)000355507100001 ()
Available from: 2015-04-26 Created: 2015-06-10 Last updated: 2017-12-04Bibliographically approved
Malmberg, F., Selig, B. & Luengo Hendriks, C. L. (2014). Exact evaluation of stochastic watersheds: From trees to general graphs. In: Discrete Geometry for Computer Imagery: . Paper presented at 18th IAPR International Conference on Discrete Geometry for Computer Imagery (DGCI), 2014, September 10-12, Siena, Italy (pp. 309-319). Springer Berlin/Heidelberg
Open this publication in new window or tab >>Exact evaluation of stochastic watersheds: From trees to general graphs
2014 (English)In: Discrete Geometry for Computer Imagery, Springer Berlin/Heidelberg, 2014, p. 309-319Conference paper, Published paper (Refereed)
Abstract [en]

The stochastic watershed is a method for identifying salient contours in an image, with applications to image segmentation. The method computes a probability density function (PDF), assigning to each piece of contour in the image the probability to appear as a segmentation boundary in seeded watershed segmentation with randomly selected seedpoints. Contours that appear with high probability are assumed to be more important. This paper concerns an efficient method for computing the stochastic watershed PDF exactly, without performing any actual seeded watershed computations. A method for exact evaluation of stochastic watersheds was proposed by Meyer and Stawiaski (2010). Their method does not operate directly on the image, but on a compact tree representation where each edge in the tree corresponds to a watershed partition of the image elements. The output of the exact evaluation algorithm is thus a PDF defined over the edges of the tree. While the compact tree representation is useful in its own right, it is in many cases desirable to convert the results from this abstract representation back to the image, e. g, for further processing. Here, we present an efficient linear time algorithm for performing this conversion.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2014
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 8668
Keywords
stochastic watershed, watershed cut, minimum spanning tree
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:uu:diva-232251 (URN)10.1007/978-3-319-09955-2_26 (DOI)000358195100026 ()978-3-319-09954-5 (ISBN)
Conference
18th IAPR International Conference on Discrete Geometry for Computer Imagery (DGCI), 2014, September 10-12, Siena, Italy
Available from: 2014-09-16 Created: 2014-09-16 Last updated: 2018-01-11Bibliographically approved
Bernander, K. B., Gustavsson, K., Selig, B., Sintorn, I.-M. & Luengo Hendriks, C. L. (2013). Improving the stochastic watershed. Pattern Recognition Letters, 34(9), 993-1000
Open this publication in new window or tab >>Improving the stochastic watershed
Show others...
2013 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 34, no 9, p. 993-1000Article in journal (Refereed) Published
Abstract [en]

The stochastic watershed is an unsupervised segmentation tool recently proposed by Angulo and Jeulin. By repeated application of the seeded watershed with randomly placed markers, a probability density function for object boundaries is created. In a second step, the algorithm then generates a meaningful segmentation of the image using this probability density function. The method performs best when the image contains regions of similar size, since it tends to break up larger regions and merge smaller ones. We propose two simple modifications that greatly improve the properties of the stochastic watershed: (1) add noise to the input image at every iteration, and (2) distribute the markers using a randomly placed grid. The noise strength is a new parameter to be set, but the output of the algorithm is not very sensitive to this value. In return, the output becomes less sensitive to the two parameters of the standard algorithm. The improved algorithm does not break up larger regions, effectively making the algorithm useful for a larger class of segmentation problems.

Keywords
Mathematical morphology, Image segmentation, Random process, Stochastic watershed, Seeded watershed, Uniform grid
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:uu:diva-202340 (URN)10.1016/j.patrec.2013.02.012 (DOI)000318889800006 ()
Available from: 2013-06-24 Created: 2013-06-24 Last updated: 2018-01-11Bibliographically approved
Selig, B., Luengo Hendriks, C. L., Bardage, S., Daniel, G. & Borgefors, G. (2012). Automatic measurement of compression wood cell attributes in fluorescence microscopy images. Journal of Microscopy, 246(3), 298-308
Open this publication in new window or tab >>Automatic measurement of compression wood cell attributes in fluorescence microscopy images
Show others...
2012 (English)In: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 246, no 3, p. 298-308Article in journal (Refereed) Published
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:uu:diva-175180 (URN)10.1111/j.1365-2818.2012.03621.x (DOI)000303993700010 ()
Available from: 2012-05-14 Created: 2012-06-04 Last updated: 2018-01-12Bibliographically approved
Selig, B. & Luengo Hendriks, C. L. (2012). Stochastic watershed – an analysis. In: Proceedings of Swedish Society for Image Analysis, SSBA 2012. Paper presented at SSBA 2012. Stockholm: KTH Royal Institute of Technology
Open this publication in new window or tab >>Stochastic watershed – an analysis
2012 (English)In: Proceedings of Swedish Society for Image Analysis, SSBA 2012, Stockholm: KTH Royal Institute of Technology, 2012Conference paper, Oral presentation only (Other academic)
Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2012
National Category
Mathematics
Identifiers
urn:nbn:se:uu:diva-176741 (URN)
Conference
SSBA 2012
Available from: 2012-06-25 Created: 2012-06-25 Last updated: 2012-06-25
Selig, B., Luengo Hendriks, C. L. & Borgefors, G. (2009). Measuring Distribution of Lignin in Wood Fibre Cross-Sections. In: Josef Bigun, Antanas Verikas (Ed.), Proceedings SSBA 2009: Symposium on Image Analysis. Paper presented at Symposium on Image Analysis (pp. 5-8). Halmstad: EIS, Halmstad University
Open this publication in new window or tab >>Measuring Distribution of Lignin in Wood Fibre Cross-Sections
2009 (English)In: Proceedings SSBA 2009: Symposium on Image Analysis / [ed] Josef Bigun, Antanas Verikas, Halmstad: EIS, Halmstad University , 2009, p. 5-8Conference paper, Published paper (Other academic)
Abstract [en]

Lignification of wood fibres has important consequences to the paper production, but its exact effects are not well understood. To correlate exact levels of lignin in wood fibres to their mechanical properties, lignin autofluorescence is imaged in wood fibre cross-sections. Highly lignified areas can be detected and related to the area of the whole cell wall. Presently these measurements are performed manually, which is tedious and expensive. In this paper a method is proposed to estimate the degree of lignification automatically. The method is evaluated manually by an expert. Beside some difficulties segmenting cells that do not conform to our model, there was a highly significant correlation between the two methods.

Place, publisher, year, edition, pages
Halmstad: EIS, Halmstad University, 2009
Keywords
Lignin, Wood fibres, Snakes
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:uu:diva-111422 (URN)978-91-633-3924-0 (ISBN)
Conference
Symposium on Image Analysis
Available from: 2009-12-14 Created: 2009-12-14 Last updated: 2018-01-12Bibliographically approved
Selig, B., Luengo Hendriks, C. L., Bardage, S. & Borgefors, G. (2009). Segmentation of Highly Lignified Zones in Wood Fiber Cross-Sections. In: Proceedings of the 16th Scandinavian Conference on Image Analysis (SCIA) (pp. 369-378). Heidelberg: Springer Berlin
Open this publication in new window or tab >>Segmentation of Highly Lignified Zones in Wood Fiber Cross-Sections
2009 (English)In: Proceedings of the 16th Scandinavian Conference on Image Analysis (SCIA), Heidelberg: Springer Berlin , 2009, p. 369-378Conference paper, Published paper (Refereed)
Abstract [en]

Lignification of wood fibers has important consequences tothe paper production, but its exact effects are not well understood. Tocorrelate exact levels of lignin in wood fibers to their mechanical proper-ties, lignin autofluorescence is imaged in wood fiber cross-sections. Highlylignified areas can be detected and related to the area of the whole cellwall. Presently these measurements are performed manually, which is te-dious and expensive. In this paper a method is proposed to estimate thedegree of lignification automatically. A multi-stage snake-based segmen-tation is applied on each cell separately. To make a preliminary evaluationwe used an image which contained 17 complete cell cross-sections. Thisimage was segmented both automatically and manually by an expert.There was a highly significant correlation between the two methods, al-though a systematic difference indicates a disagreement in the definitionof the edges between the expert and the algorithm.

Place, publisher, year, edition, pages
Heidelberg: Springer Berlin, 2009
Series
Lecture Notes in Computer Science, ISSN 1611-3349 ; 5575
Keywords
Lignin, Wood fibres, Snakes
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:uu:diva-109894 (URN)10.1007/978-3-642-02230-2_38 (DOI)978-3-642-02229-6 (ISBN)
Available from: 2009-10-29 Created: 2009-10-29 Last updated: 2018-01-12Bibliographically approved
Organisations

Search in DiVA

Show all publications