Epithelium and Stroma Identification in Histopathological Images using Unsupervised and Semi-supervised Superpixel-based Segmentation

Research output: Contribution to journalArticle

Standard

Epithelium and Stroma Identification in Histopathological Images using Unsupervised and Semi-supervised Superpixel-based Segmentation. / Fouad, Shereen; Randell, David; Galton, Antony; Mehanna, Hesham; Landini, Gabriel.

In: Journal of Imaging, Vol. 3, No. 4 (Special Issue "Selected Papers from “MIUA 2017”"), 61, 11.12.2017.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex

@article{1ef90c4e9668408cac738c921b5595e4,
title = "Epithelium and Stroma Identification in Histopathological Images using Unsupervised and Semi-supervised Superpixel-based Segmentation",
abstract = "We present superpixel-based segmentation frameworks for unsupervised and semi-supervised epithelium-stroma identification in histopathological images or oropharyngeal tissue micro arrays. A superpixel segmentation algorithm is initially used to split-up the image into binary regions (superpixels) and their colour features are extracted and fed into several base clustering algorithms with various parameter initializations. Two Consensus Clustering (CC) formulations are then used: the Evidence Accumulation Clustering (EAC) and the voting-based consensus function. These combine the base clustering outcomes to obtain a more robust detection of tissue compartments than the base clustering methods on their own. For the voting-based function, a technique is introduced to generate consistent labellings across the base clustering results. The obtained CC result is then utilized to build a self-training Semi-Supervised Classification (SSC) model. Unlike supervised segmentations, which rely on large number of labelled training images, our SSC approach performs a quality segmentation while relying on few labelled samples. Experiments conducted on forty-five hand-annotated images of oropharyngeal cancer tissue microarrays show that (a) the CC algorithm generates more accurate and stable results than individual clustering algorithms; (b) the clustering performance of the voting-based function outperforms the existing EAC; and (c) the proposed SSC algorithm outperforms the supervised methods, which is trained with only a few labelled instances.",
author = "Shereen Fouad and David Randell and Antony Galton and Hesham Mehanna and Gabriel Landini",
year = "2017",
month = dec,
day = "11",
doi = "10.3390/jimaging3040061",
language = "English",
volume = "3",
journal = "Journal of Imaging",
issn = "2313-433X",
publisher = "MDPI AG",
number = "4 (Special Issue {"}Selected Papers from “MIUA 2017”{"})",

}

RIS

TY - JOUR

T1 - Epithelium and Stroma Identification in Histopathological Images using Unsupervised and Semi-supervised Superpixel-based Segmentation

AU - Fouad, Shereen

AU - Randell, David

AU - Galton, Antony

AU - Mehanna, Hesham

AU - Landini, Gabriel

PY - 2017/12/11

Y1 - 2017/12/11

N2 - We present superpixel-based segmentation frameworks for unsupervised and semi-supervised epithelium-stroma identification in histopathological images or oropharyngeal tissue micro arrays. A superpixel segmentation algorithm is initially used to split-up the image into binary regions (superpixels) and their colour features are extracted and fed into several base clustering algorithms with various parameter initializations. Two Consensus Clustering (CC) formulations are then used: the Evidence Accumulation Clustering (EAC) and the voting-based consensus function. These combine the base clustering outcomes to obtain a more robust detection of tissue compartments than the base clustering methods on their own. For the voting-based function, a technique is introduced to generate consistent labellings across the base clustering results. The obtained CC result is then utilized to build a self-training Semi-Supervised Classification (SSC) model. Unlike supervised segmentations, which rely on large number of labelled training images, our SSC approach performs a quality segmentation while relying on few labelled samples. Experiments conducted on forty-five hand-annotated images of oropharyngeal cancer tissue microarrays show that (a) the CC algorithm generates more accurate and stable results than individual clustering algorithms; (b) the clustering performance of the voting-based function outperforms the existing EAC; and (c) the proposed SSC algorithm outperforms the supervised methods, which is trained with only a few labelled instances.

AB - We present superpixel-based segmentation frameworks for unsupervised and semi-supervised epithelium-stroma identification in histopathological images or oropharyngeal tissue micro arrays. A superpixel segmentation algorithm is initially used to split-up the image into binary regions (superpixels) and their colour features are extracted and fed into several base clustering algorithms with various parameter initializations. Two Consensus Clustering (CC) formulations are then used: the Evidence Accumulation Clustering (EAC) and the voting-based consensus function. These combine the base clustering outcomes to obtain a more robust detection of tissue compartments than the base clustering methods on their own. For the voting-based function, a technique is introduced to generate consistent labellings across the base clustering results. The obtained CC result is then utilized to build a self-training Semi-Supervised Classification (SSC) model. Unlike supervised segmentations, which rely on large number of labelled training images, our SSC approach performs a quality segmentation while relying on few labelled samples. Experiments conducted on forty-five hand-annotated images of oropharyngeal cancer tissue microarrays show that (a) the CC algorithm generates more accurate and stable results than individual clustering algorithms; (b) the clustering performance of the voting-based function outperforms the existing EAC; and (c) the proposed SSC algorithm outperforms the supervised methods, which is trained with only a few labelled instances.

U2 - 10.3390/jimaging3040061

DO - 10.3390/jimaging3040061

M3 - Article

VL - 3

JO - Journal of Imaging

JF - Journal of Imaging

SN - 2313-433X

IS - 4 (Special Issue "Selected Papers from “MIUA 2017”")

M1 - 61

ER -