Tampere University of Technology

TUTCRIS Research Portal

Texture descriptors ensembles enable image-based classification of maturation of human stem cell-derived retinal pigmented epithelium

Research output: Contribution to journalArticleScientificpeer-review

Standard

Texture descriptors ensembles enable image-based classification of maturation of human stem cell-derived retinal pigmented epithelium. / Nanni, Loris; Paci, Michelangelo; Dos Santos, Florentino Luciano Caetano; Skottman, Heli; Juuti-Uusitalo, Kati; Hyttinen, Jari.

In: PLoS ONE, Vol. 11, No. 2, e0149399, 01.02.2016.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Nanni, Loris ; Paci, Michelangelo ; Dos Santos, Florentino Luciano Caetano ; Skottman, Heli ; Juuti-Uusitalo, Kati ; Hyttinen, Jari. / Texture descriptors ensembles enable image-based classification of maturation of human stem cell-derived retinal pigmented epithelium. In: PLoS ONE. 2016 ; Vol. 11, No. 2.

Bibtex - Download

@article{00fd18a8a597461fa7c9547583e0e275,
title = "Texture descriptors ensembles enable image-based classification of maturation of human stem cell-derived retinal pigmented epithelium",
abstract = "Aims A fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-ofthe- art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification. Methods For image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level. Dataset and Results The RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49{\%} with the 10-fold cross validation and 91.98{\%} with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97{\%}. Conclusions Here we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors' accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies.",
author = "Loris Nanni and Michelangelo Paci and {Dos Santos}, {Florentino Luciano Caetano} and Heli Skottman and Kati Juuti-Uusitalo and Jari Hyttinen",
year = "2016",
month = "2",
day = "1",
doi = "10.1371/journal.pone.0149399",
language = "English",
volume = "11",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Texture descriptors ensembles enable image-based classification of maturation of human stem cell-derived retinal pigmented epithelium

AU - Nanni, Loris

AU - Paci, Michelangelo

AU - Dos Santos, Florentino Luciano Caetano

AU - Skottman, Heli

AU - Juuti-Uusitalo, Kati

AU - Hyttinen, Jari

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Aims A fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-ofthe- art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification. Methods For image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level. Dataset and Results The RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49% with the 10-fold cross validation and 91.98% with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97%. Conclusions Here we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors' accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies.

AB - Aims A fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-ofthe- art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification. Methods For image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level. Dataset and Results The RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49% with the 10-fold cross validation and 91.98% with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97%. Conclusions Here we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors' accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies.

U2 - 10.1371/journal.pone.0149399

DO - 10.1371/journal.pone.0149399

M3 - Article

VL - 11

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 2

M1 - e0149399

ER -