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

ResearchSpace/Manakin Repository

Show simple item record Kainz, Philipp en Pfeiffer, Michael en Urschler, Martin en 2019-10-08T08:26:42Z en 2017-01 en
dc.identifier.citation PeerJ 5:e3874 Jan 2017 en
dc.identifier.issn 2167-8359 en
dc.identifier.uri en
dc.description.abstract 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. en
dc.format.medium Electronic-eCollection en
dc.language eng en
dc.relation.ispartofseries PeerJ en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri en
dc.rights.uri en
dc.title Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization. en
dc.type Journal Article en
dc.identifier.doi 10.7717/peerj.3874 en
pubs.begin-page e3874 en
pubs.volume 5 en
dc.rights.holder Copyright: The authors en
pubs.publication-status Published en
dc.rights.accessrights en
pubs.subtype research-article en
pubs.subtype Journal Article en
pubs.elements-id 776168 en Science en School of Computer Science en
dc.identifier.eissn 2167-8359 en
pubs.record-created-at-source-date 2017-10-12 en
pubs.dimensions-id 29018612 en

Full text options

Find Full text

This item appears in the following Collection(s)

Show simple item record Except where otherwise noted, this item's license is described as


Search ResearchSpace

Advanced Search