<div class="csl-bib-body">
<div class="csl-entry">Taha, A. A., & Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. <i>BMC Medical Imaging</i>. https://doi.org/10.1186/s12880-015-0068-x</div>
</div>
Background<br />Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics.<br />Result<br />First we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project.<br />Conclusion<br />We propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.
en
dc.description.sponsorship
European Union Seventh Framework Programme (FP7/2007-2013)
-
dc.language
English
-
dc.language.iso
en
-
dc.publisher
BioMed Central
-
dc.relation.ispartof
BMC Medical Imaging
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Evaluation metrics
en
dc.subject
Evaluation tool
en
dc.subject
Medical volume segmentation
en
dc.subject
Metric selection
en
dc.title
Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool
en
dc.type
Article
en
dc.type
Artikel
de
dc.rights.license
Creative Commons Attribution 4.0 International
en
dc.rights.license
Creative Commons Namensnennung 4.0 International
de
dc.relation.grantno
318068
-
dc.rights.holder
2015 The Authors
-
dc.type.category
Original Research Article
-
tuw.journal.peerreviewed
true
-
tuw.peerreviewed
true
-
tuw.version
vor
-
dcterms.isPartOf.title
BMC Medical Imaging
-
tuw.publication.orgunit
E194 - Institut für Softwaretechnik und Interaktive Systeme
-
tuw.publisher.doi
10.1186/s12880-015-0068-x
-
dc.date.onlinefirst
2015-08-12
-
dc.identifier.eissn
1471-2342
-
dc.identifier.libraryid
AC11360014
-
dc.description.numberOfPages
1
-
dc.identifier.urn
urn:nbn:at:at-ubtuw:3-1470
-
tuw.author.orcid
0000-0002-7604-9041
-
tuw.author.orcid
0000-0002-7149-5843
-
dc.rights.identifier
CC BY 4.0
en
dc.rights.identifier
CC BY 4.0
de
wb.sci
true
-
item.openaccessfulltext
Open Access
-
item.cerifentitytype
Publications
-
item.cerifentitytype
Publications
-
item.openairecristype
http://purl.org/coar/resource_type/c_18cf
-
item.openairecristype
http://purl.org/coar/resource_type/c_18cf
-
item.fulltext
with Fulltext
-
item.grantfulltext
open
-
item.languageiso639-1
en
-
item.openairetype
Article
-
item.openairetype
Artikel
-
crisitem.author.dept
E194 - Institut für Information Systems Engineering
-
crisitem.author.dept
E194-04 - Forschungsbereich E-Commerce
-
crisitem.author.orcid
0000-0002-7149-5843
-
crisitem.author.parentorg
E180 - Fakultät für Informatik
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering