Header

UZH-Logo

Maintenance Infos

Semantic segmentation of colon glands with deep convolutional neural networks and total variation segmentation


Kainz, P; Pfeiffer, M; Urschler, M (2015). Semantic segmentation of colon glands with deep convolutional neural networks and total variation segmentation. Computer Vision and Pattern Recognition cs.CV, Institute of Neuroinformatics.

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.

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.

Statistics

Downloads

32 downloads since deposited on 22 Feb 2016
24 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Working Paper
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2015
Deposited On:22 Feb 2016 10:08
Last Modified:21 Nov 2017 18:23
Publisher:Cornell University
Series Name:Computer Vision and Pattern Recognition
Free access at:Official URL. An embargo period may apply.
Official URL:http://arxiv.org/abs/1511.06919
Other Identification Number:1511.069

Download

Download PDF  'Semantic segmentation of colon glands with deep convolutional neural networks and total variation segmentation'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 5MB