Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/111346
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Globally optimal breast mass segmentation from DCE-MRI using deep semantic segmentation as shape prior
Author: Maicas, G.
Carneiro, G.
Bradley, A.
Citation: Proceedings of the IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017 / pp.305-309
Publisher: IEEE
Publisher Place: Online
Issue Date: 2017
Series/Report no.: IEEE International Symposium on Biomedical Imaging
ISBN: 9781509011711
ISSN: 1945-7928
1945-8452
Conference Name: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) (18 Apr 2017 - 21 Apr 2017 : Melbourne, AUSTRALIA)
Statement of
Responsibility: 
Gabriel Maicas, Gustavo Carneiro, Andrew P. Bradley
Abstract: We introduce a new fully automated breast mass segmentation method from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). The method is based on globally optimal inference in a continuous space (GOCS) using a shape prior computed from a semantic segmentation produced by a deep learning (DL) model. We propose this approach because the limited amount of annotated training samples does not allow the implementation of a robust DL model that could produce accurate segmentation results on its own. Furthermore, GOCS does not need precise initialisation compared to locally optimal methods on a continuous space (e.g., Mumford-Shah based level set methods); also, GOCS has smaller memory complexity compared to globally optimal inference on a discrete space (e.g., graph cuts). Experimental results show that the proposed method produces the current state-of-the-art mass segmentation (from DCEMRI) results, achieving a mean Dice coefficient of 0.77 for the test set.
Keywords: Breast cancer; deep learning; energy-based segmentation; shape prior; breast mass segmentation; breast MRI; global optimization
Rights: ©2017 IEEE
RMID: 0030073409
DOI: 10.1109/ISBI.2017.7950525
Grant ID: http://purl.org/au-research/grants/arc/DP140102794
http://purl.org/au-research/grants/arc/FT110100623
Published version: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7944115
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.