The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article présente une méthode de segmentation pour détecter les cellules dans des images cytologiques colorées par immunohistochimie. Une approche de segmentation en deux phases est utilisée dans laquelle une approche de regroupement non supervisée couplée à une fusion de clusters basée sur une fonction de fitness est utilisée comme première phase pour obtenir une première approximation des emplacements des cellules. Une approche conjointe de segmentation-classification intégrant l’ellipse comme modèle de forme est utilisée comme deuxième phase pour détecter le contour cellulaire final. Le modèle de segmentation estime une fonction de densité multivariée de caractéristiques d'image de bas niveau à partir d'échantillons d'apprentissage et l'utilise comme mesure de la probabilité que chaque pixel de l'image soit une cellule. Cette estimation est contrainte par l'ensemble de niveaux zéro, qui est obtenu comme solution à une représentation implicite d'une ellipse. Les résultats de la segmentation sont présentés et comparés aux mesures de vérité terrain.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Shishir SHAH, "Automatic Cell Segmentation Using a Shape-Classification Model in Immunohistochemically Stained Cytological Images" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 1955-1962, July 2008, doi: 10.1093/ietisy/e91-d.7.1955.
Abstract: This paper presents a segmentation method for detecting cells in immunohistochemically stained cytological images. A two-phase approach to segmentation is used where an unsupervised clustering approach coupled with cluster merging based on a fitness function is used as the first phase to obtain a first approximation of the cell locations. A joint segmentation-classification approach incorporating ellipse as a shape model is used as the second phase to detect the final cell contour. The segmentation model estimates a multivariate density function of low-level image features from training samples and uses it as a measure of how likely each image pixel is to be a cell. This estimate is constrained by the zero level set, which is obtained as a solution to an implicit representation of an ellipse. Results of segmentation are presented and compared to ground truth measurements.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.1955/_p
Copier
@ARTICLE{e91-d_7_1955,
author={Shishir SHAH, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Cell Segmentation Using a Shape-Classification Model in Immunohistochemically Stained Cytological Images},
year={2008},
volume={E91-D},
number={7},
pages={1955-1962},
abstract={This paper presents a segmentation method for detecting cells in immunohistochemically stained cytological images. A two-phase approach to segmentation is used where an unsupervised clustering approach coupled with cluster merging based on a fitness function is used as the first phase to obtain a first approximation of the cell locations. A joint segmentation-classification approach incorporating ellipse as a shape model is used as the second phase to detect the final cell contour. The segmentation model estimates a multivariate density function of low-level image features from training samples and uses it as a measure of how likely each image pixel is to be a cell. This estimate is constrained by the zero level set, which is obtained as a solution to an implicit representation of an ellipse. Results of segmentation are presented and compared to ground truth measurements.},
keywords={},
doi={10.1093/ietisy/e91-d.7.1955},
ISSN={1745-1361},
month={July},}
Copier
TY - JOUR
TI - Automatic Cell Segmentation Using a Shape-Classification Model in Immunohistochemically Stained Cytological Images
T2 - IEICE TRANSACTIONS on Information
SP - 1955
EP - 1962
AU - Shishir SHAH
PY - 2008
DO - 10.1093/ietisy/e91-d.7.1955
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - This paper presents a segmentation method for detecting cells in immunohistochemically stained cytological images. A two-phase approach to segmentation is used where an unsupervised clustering approach coupled with cluster merging based on a fitness function is used as the first phase to obtain a first approximation of the cell locations. A joint segmentation-classification approach incorporating ellipse as a shape model is used as the second phase to detect the final cell contour. The segmentation model estimates a multivariate density function of low-level image features from training samples and uses it as a measure of how likely each image pixel is to be a cell. This estimate is constrained by the zero level set, which is obtained as a solution to an implicit representation of an ellipse. Results of segmentation are presented and compared to ground truth measurements.
ER -