Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/112018
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Mass segmentation in mammograms: a cross-sensor comparison of deep and tailored features
Author: Cardoso, J.
Marques, N.
Dhungel, N.
Carneiro, G.
Bradley, A.
Citation: Proceedings of the 24th IEEE International Conference on Image Processing (ICIP 2017), 2018 / vol.2017, pp.1737-1741
Publisher: IEEE
Publisher Place: Piscataway, N.J.
Issue Date: 2018
Series/Report no.: IEEE International Conference on Image Processing ICIP
ISBN: 9781509021758
ISSN: 1522-4880
Conference Name: 24th IEEE International Conference on Image Processing (ICIP 2017) (17 Sep 2017 - 20 Sep 2017 : Beijing, CHINA)
Statement of
Responsibility: 
Jaime S. Cardoso, Nuno Marques, Neeraj Dhungel, G. Carneiro, A. P. Bradley
Abstract: Through the years, several CAD systems have been developed to help radiologists in the hard task of detecting signs of cancer in mammograms. In these CAD systems, mass segmentation plays a central role in the decision process. In the literature, mass segmentation has been typically evaluated in a intra-sensor scenario, where the methodology is designed and evaluated in similar data. However, in practice, acquisition systems and PACS from multiple vendors abound and current works fails to take into account the differences in mammogram data in the performance evaluation. In this work it is argued that a comprehensive assessment of the mass segmentation methods requires the design and evaluation in datasets with different properties. To provide a more realistic evaluation, this work proposes: a) improvements to a state of the art method based on tailored features and a graph model; b) a head-to-head comparison of the improved model with recently proposed methodologies based in deep learning and structured prediction on four reference databases, performing a cross-sensor evaluation. The results obtained support the assertion that the evaluation methods from the literature are optimistically biased when evaluated on data gathered from exactly the same sensor and/or acquisition protocol.
Keywords: Mammogram; mass segmentation; transfer learning; cross-sensor
Rights: ©2017 IEEE
RMID: 0030085935
DOI: 10.1109/ICIP.2017.8296579
Grant ID: http://purl.org/au-research/grants/arc/DP140102794
Published version: https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8267582
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.