Cargando…

Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization

Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based ap...

Descripción completa

Detalles Bibliográficos
Autores principales: Kainz, Philipp, Pfeiffer, Michael, Urschler, Martin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5629961/
https://www.ncbi.nlm.nih.gov/pubmed/29018612
http://dx.doi.org/10.7717/peerj.3874
_version_ 1783269155889217536
author Kainz, Philipp
Pfeiffer, Michael
Urschler, Martin
author_facet Kainz, Philipp
Pfeiffer, Michael
Urschler, Martin
author_sort Kainz, Philipp
collection PubMed
description Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.
format Online
Article
Text
id pubmed-5629961
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-56299612017-10-10 Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization Kainz, Philipp Pfeiffer, Michael Urschler, Martin PeerJ Bioengineering Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses. PeerJ Inc. 2017-10-03 /pmc/articles/PMC5629961/ /pubmed/29018612 http://dx.doi.org/10.7717/peerj.3874 Text en ©2017 Kainz et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Bioengineering
Kainz, Philipp
Pfeiffer, Michael
Urschler, Martin
Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title_full Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title_fullStr Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title_full_unstemmed Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title_short Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
title_sort segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization
topic Bioengineering
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5629961/
https://www.ncbi.nlm.nih.gov/pubmed/29018612
http://dx.doi.org/10.7717/peerj.3874
work_keys_str_mv AT kainzphilipp segmentationandclassificationofcolonglandswithdeepconvolutionalneuralnetworksandtotalvariationregularization
AT pfeiffermichael segmentationandclassificationofcolonglandswithdeepconvolutionalneuralnetworksandtotalvariationregularization
AT urschlermartin segmentationandclassificationofcolonglandswithdeepconvolutionalneuralnetworksandtotalvariationregularization