Discovery - University of Dundee - Online Publications

Library & Learning Centre

Multi-task Fully Convolutional Network for Brain Tumour Segmentation

Multi-task Fully Convolutional Network for Brain Tumour Segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations

Authors

Research units

Info

Original languageEnglish
Title of host publicationMedical Image Understanding and Analysis
Subtitle of host publication21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings
EditorsMaria Valdes Hernandez, Victor Gonzalez-Castro
Place of PublicationSwitzerland
PublisherSpringer
Pages239-248
Number of pages10
ISBN (Electronic)9783319609645
ISBN (Print)9783319609638
DOIs
StatePublished - 2017
EventMedical Image Understanding and Analysis (MIUA) 2017 - Edinburgh, United Kingdom

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer
Volume723
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceMedical Image Understanding and Analysis (MIUA) 2017
Abbreviated titleMIUA 2017
CountryUnited Kingdom
CityEdinburgh
Period11/07/1713/07/17
Internet address

Abstract

In this paper, a novel, multi-task fully convolutional network (FCN) architecture is proposed for automatic segmentation of brain tumour. The proposed network builds on the hierarchical relationship between tumour substructures with branch and leaf losses imposed and optimised simultaneously. The network takes multimodal MR images along with their symmetric-difference images as input and extracts multi-level contextual information, firstly by the branch losses which are then fed to the leaf loss in a combination stage. The model was evaluated on BRATS13 and BRATS15 datasets and results show that the proposed multi-task FCN outperforms single-task FCN on all sub-tasks. The method is among the most accurate available and its computational cost is relatively low at test time.

Documents

DOI

Library & Learning Centre

Contact | Accessibility | Policy