Titelaufnahme

Titel
Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool
VerfasserTaha, Abdel Aziz ; Hanbury, Allan In der Gemeinsamen Normdatei der DNB nachschlagen
Erschienen in
BMC medical imaging, 2015, Jg. 15, H. 29, S. 1-28
Erschienen2015
Ausgabe
Published version
SpracheEnglisch
DokumenttypAufsatz in einer Zeitschrift
Schlagwörter (EN)Evaluation metrics / Evaluation tool / Medical volume segmentation / Metric selection
ISSN1471-2342
URNurn:nbn:at:at-ubtuw:3-1470 Persistent Identifier (URN)
DOI10.1186/s12880-015-0068-x 
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool [2.16 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

Background

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.

Result

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.

Conclusion

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.

Lizenz
CC-BY-Lizenz (4.0)Creative Commons Namensnennung 4.0 International Lizenz