Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation

Philipp Kainz, Michael Pfeiffer, Martin Urschler

Research output: Contribution to journalArticleResearch

Abstract

Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods. As part of the GlaS@MICCAI2015 colon gland segmentation challenge, we present a learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer. Images are preprocessed according to the Hematoxylin-Eosin staining protocol and two deep convolutional neural networks (CNN) are trained as pixel classifiers. The CNN predictions are then regularized using a figure-ground segmentation based on weighted total variation to produce the final segmentation result. On two test sets, our approach achieves a tissue classification accuracy of 98% and 94%, making use of the inherent capability of our system to distinguish between benign and malignant tissue.
LanguageUndefined/Unknown
JournalarXiv.org e-Print archive
Issue number arXiv:1511.06919
StatusPublished - 21 Nov 2015

Fields of Expertise

  • Information, Communication & Computing

Cooperations

  • BioTechMed-Graz

Cite this

Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation. / Kainz, Philipp; Pfeiffer, Michael; Urschler, Martin.

In: arXiv.org e-Print archive, No. arXiv:1511.06919 , 21.11.2015.

Research output: Contribution to journalArticleResearch

@article{4ccf8b7cf6cc47c2aab77bb0b1bcbe3c,
title = "Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation",
abstract = "Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods. As part of the GlaS@MICCAI2015 colon gland segmentation challenge, we present a learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer. Images are preprocessed according to the Hematoxylin-Eosin staining protocol and two deep convolutional neural networks (CNN) are trained as pixel classifiers. The CNN predictions are then regularized using a figure-ground segmentation based on weighted total variation to produce the final segmentation result. On two test sets, our approach achieves a tissue classification accuracy of 98{\%} and 94{\%}, making use of the inherent capability of our system to distinguish between benign and malignant tissue.",
author = "Philipp Kainz and Michael Pfeiffer and Martin Urschler",
year = "2015",
month = "11",
day = "21",
language = "undefiniert/unbekannt",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",
number = "arXiv:1511.06919",

}

TY - JOUR

T1 - Semantic Segmentation of Colon Glands with Deep Convolutional Neural Networks and Total Variation Segmentation

AU - Kainz,Philipp

AU - Pfeiffer,Michael

AU - Urschler,Martin

PY - 2015/11/21

Y1 - 2015/11/21

N2 - Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods. As part of the GlaS@MICCAI2015 colon gland segmentation challenge, we present a learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer. Images are preprocessed according to the Hematoxylin-Eosin staining protocol and two deep convolutional neural networks (CNN) are trained as pixel classifiers. The CNN predictions are then regularized using a figure-ground segmentation based on weighted total variation to produce the final segmentation result. On two test sets, our approach achieves a tissue classification accuracy of 98% and 94%, making use of the inherent capability of our system to distinguish between benign and malignant tissue.

AB - Segmentation of histopathology sections is an ubiquitous requirement in digital pathology and due to the large variability of biological tissue, machine learning techniques have shown superior performance over standard image processing methods. As part of the GlaS@MICCAI2015 colon gland segmentation challenge, we present a learning-based algorithm to segment glands in tissue of benign and malignant colorectal cancer. Images are preprocessed according to the Hematoxylin-Eosin staining protocol and two deep convolutional neural networks (CNN) are trained as pixel classifiers. The CNN predictions are then regularized using a figure-ground segmentation based on weighted total variation to produce the final segmentation result. On two test sets, our approach achieves a tissue classification accuracy of 98% and 94%, making use of the inherent capability of our system to distinguish between benign and malignant tissue.

M3 - Artikel

JO - arXiv.org e-Print archive

T2 - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

IS - arXiv:1511.06919

ER -