Unsupervised decomposition of low-intensity low-dimensional multi-spectral fluorescent images for tumour demarcation

Kopriva, Ivica; Peršin, A.

doi:10.1016/j.media.2009.02.002

Cited by 13 publications

(21 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods are referred to as i) dependent component analysis (DCA), 10,11 ii) multilayer hierarchical alternating least-square non-negative matrix factorization (HALS NMF), 16,17 iii) non-negative matrix underapproximation (NMU), 15 and iv) non-negative tensor factorization (NTF). 18 DCA is an extension of independent component analysis for problems in which statistical independence assumption between sources is not fulfilled.…”

Section: Factorization Methods For Unsupervised Segmentation Of Multimentioning

confidence: 99%

“…The firstorder mapping represents the original image itself, and model (1) becomes a standard LMM in the original input space, X Ϸ AS, used commonly in multispectral image analysis, [7][8][9][10][11] where AʦR 0 ϩ I3ϫJ stands for a matrix of spectral profiles of J materials present in the image. In mapped space, ͑X͒ʦR 0 ϩ I 3ϫI1I2 and A ʦR 0 ϩ I 3ϫJ , where I 3 Ͼ I 3 and J Ͼ J.…”

Section: Multispectral Image and Linear Mixture Modelmentioning

confidence: 99%

“…The statistical independence assumption fails when materials are spectrally similar. This occurs, for example, in the case of low-dimensional multispectral imaging of a skin tumor with a low fluorescence intensity, 10,11 but occurs also with multispectral microscopy imaging of an unstained specimen with low contrast between the cell and the background.…”

Section: Multispectral Image and Linear Mixture Modelmentioning

confidence: 99%

“…Representing the image by LMM in mapped space has two advantages: it implicitly takes into account the possible presence of nonlinearities in the image (ie, they are not required to be known) and it enhances contrast between spectrally similar materials, which occurs because of increased dimensionality of the mapped space. In this regard, nonlinear band expansion as used by Kopriva and Peršin 10 and by Ouyang et al 14 is a special case (second-order) of the rth-order RVM used in our methodology.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Rational Variety Mapping for Contrast-Enhanced Nonlinear Unsupervised Segmentation of Multispectral Images of Unstained Specimen

Kopriva

Hadžija

Korolija

et al. 2011

The American Journal of Pathology

View full text Add to dashboard Cite

A methodology is proposed for nonlinear contrastenhanced unsupervised segmentation of multispectral (color) microscopy images of principally unstained specimens. The methodology exploits spectral diversity and spatial sparseness to find anatomical differences between materials (cells, nuclei, and background) present in the image. It consists of rth-order rational variety mapping (RVM) followed by matrix/tensor factorization. Sparseness constraint implies duality between nonlinear unsupervised segmentation and multiclass pattern assignment problems. Classes not linearly separable in the original input space become separable with high probability in the higher-dimensional mapped space. Hence, RVM mapping has two advantages: it takes implicitly into account nonlinearities present in the image (ie, they are not required to be known) and it increases spectral diversity (ie, contrast) between materials, due to increased dimensionality of the mapped space. This is expected to improve performance of systems for automated classification and analysis of microscopic histopathological images. The methodology was validated using RVM of the second and third orders of the experimental multispectral microscopy images of unstained sciatic nerve fibers (nervus ischiadicus) and of unstained white pulp in the spleen tissue, compared with a manually defined ground truth labeled by two trained pathophysiologists. The methodology can also be useful Staining of the specimen in the slide preparation process has been standard procedure for many years, because it increases contrast between the cell and the background. However, staining involves hours of preprocessing of the specimen, and can also add chemical effects to the nature of the cells, cause their shrinkage, and alter their morphology.1 For example, in studying effects of DNA damage on cell viability, fluorescent probes must not be used to stain the cell nuclei, to avoid compromising the viability of the cultures.2 Similarly, when studying the effects of inhibitor compounds designed to block the replication of cancerous cells, fluorescent dyes must not be used to mark nuclei, because the dyes themselves have toxicity.3 The subcellular localization of genetically encoded proteins imposes constraints on the cell recognition methods used to draw conclusion about function of a protein; again, staining of the cell is not allowed, to preserve the quality of the specimen and to avoid influencing the result of an investigation. 4 When staining is not allowed, contrast between the cell and the background will be poor, and it is challenging for either a trained pathologist or an automated image processing system to achieve good results. Furthermore, manual classification of cells by trained pathologists in images of stained specimens shows interobserver variability up to 20%.5 These findings prompted us to explore the possibility of developing a contrast enhancement methodology based on nonlinear unsupervised segmentation of multispectral images with poor contrast between the materials (ie...

show abstract

Section: Factorization Methods For Unsupervised Segmentation Of Multimentioning

confidence: 99%

Section: Multispectral Image and Linear Mixture Modelmentioning

confidence: 99%

Section: Multispectral Image and Linear Mixture Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Rational Variety Mapping for Contrast-Enhanced Nonlinear Unsupervised Segmentation of Multispectral Images of Unstained Specimen

Kopriva

Hadžija

Korolija

et al. 2011

The American Journal of Pathology

View full text Add to dashboard Cite

show abstract

“…We now execute comparative performance evaluation of the presented methods on the RGB fluorescent image of the skin tumor (basal cell carcinoma) [38]. For this purpose an image of a skin tumor is recorded after the tumor was treated for 4h with -5-aminolaevulinic acid (ALA).…”

Section: Experiments 2: Rgb Fluorescent Images Of the Skin Tumormentioning

confidence: 99%

Blind decomposition of low‐dimensional multi‐spectral image by sparse component analysis

Kopriva

Cichocki

2009

Journal of Chemometrics

View full text Add to dashboard Cite

Multilayer hierarchical alternating least square nonnegative matrix factorization approach has been applied to blind decomposition of low-dimensional multi-spectral image. Performance of the algorithm is invariant with respect to statistical (in)dependence between materials present in the image that is an assumption upon which many existing blind source separation methods depend. The proposed method performs blind decomposition exploiting spectral diversity and spatial sparsity between the materials present in the image. Unlike many existing blind source separation methods the method is capable to estimate the unknown number of materials present in the image. This number can be less than, equal to or greater than the number of spectral

show abstract

Complete determination of plant tissues based only on auto‐fluorescence and the advanced image analysis – study of needles and stamens

Savić

Živković

Jovanović

et al. 2015

Journal of Chemometrics

View full text Add to dashboard Cite

Unsupervised decomposition of low-intensity low-dimensional multi-spectral fluorescent images for tumour demarcation

Cited by 13 publications

References 41 publications

Rational Variety Mapping for Contrast-Enhanced Nonlinear Unsupervised Segmentation of Multispectral Images of Unstained Specimen

Rational Variety Mapping for Contrast-Enhanced Nonlinear Unsupervised Segmentation of Multispectral Images of Unstained Specimen

Blind decomposition of low‐dimensional multi‐spectral image by sparse component analysis

Complete determination of plant tissues based only on auto‐fluorescence and the advanced image analysis – study of needles and stamens

Contact Info

Product

Resources

About