TU Darmstadt / ULB / TUbiblio

Comparative Local Quality Assessment of 3D Medical Image Segmentations with Focus on Statistical Shape Model-based Algorithms

Landesberger von Antburg, Tatiana ; Basgier, Dennis ; Becker, Meike (2016)
Comparative Local Quality Assessment of 3D Medical Image Segmentations with Focus on Statistical Shape Model-based Algorithms.
In: IEEE Transactions on Visualization and Computer Graphics, 22 (12)
doi: 10.1109/TVCG.2015.2501813
Artikel, Bibliographie

Kurzbeschreibung (Abstract)

The quality of automatic 3D medical segmentation algorithms needs to be assessed on test datasets comprising several 3D images (i.e., instances of an organ). The experts need to compare the segmentation quality across the dataset in order to detect systematic segmentation problems. However, such comparative evaluation is not supported well by current methods. We present a novel system for assessing and comparing segmentation quality in a dataset with multiple 3D images. The data is analyzed and visualized in several views. We detect and show regions with systematic segmentation quality characteristics. For this purpose, we extended a hierarchical clustering algorithm with a connectivity criterion. We combine quality values across the dataset for determining regions with characteristic segmentation quality across instances. Using our system, the experts can also identify 3D segmentations with extraordinary quality characteristics. While we focus on algorithms based on statistical shape models, our approach can also be applied to cases, where landmark correspondences among instances can be established. We applied our approach to three real datasets: liver, cochlea and facial nerve. The segmentation experts were able to identify organ regions with systematic segmentation characteristics as well as to detect outlier instances.

Typ des Eintrags: Artikel
Erschienen: 2016
Autor(en): Landesberger von Antburg, Tatiana ; Basgier, Dennis ; Becker, Meike
Art des Eintrags: Bibliographie
Titel: Comparative Local Quality Assessment of 3D Medical Image Segmentations with Focus on Statistical Shape Model-based Algorithms
Sprache: Englisch
Publikationsjahr: 2016
Titel der Zeitschrift, Zeitung oder Schriftenreihe: IEEE Transactions on Visualization and Computer Graphics
Jahrgang/Volume einer Zeitschrift: 22
(Heft-)Nummer: 12
DOI: 10.1109/TVCG.2015.2501813
Kurzbeschreibung (Abstract):

The quality of automatic 3D medical segmentation algorithms needs to be assessed on test datasets comprising several 3D images (i.e., instances of an organ). The experts need to compare the segmentation quality across the dataset in order to detect systematic segmentation problems. However, such comparative evaluation is not supported well by current methods. We present a novel system for assessing and comparing segmentation quality in a dataset with multiple 3D images. The data is analyzed and visualized in several views. We detect and show regions with systematic segmentation quality characteristics. For this purpose, we extended a hierarchical clustering algorithm with a connectivity criterion. We combine quality values across the dataset for determining regions with characteristic segmentation quality across instances. Using our system, the experts can also identify 3D segmentations with extraordinary quality characteristics. While we focus on algorithms based on statistical shape models, our approach can also be applied to cases, where landmark correspondences among instances can be established. We applied our approach to three real datasets: liver, cochlea and facial nerve. The segmentation experts were able to identify organ regions with systematic segmentation characteristics as well as to detect outlier instances.

Freie Schlagworte: Forschungsgruppe Visual Search and Analysis (VISA), Forschungsgruppe Medical Computing (MECO), Visual analytics, Comparison, Clustering, Statistical shape models (SSM), Medical image processing, Image segmentation
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing
Hinterlegungsdatum: 03 Mai 2019 07:11
Letzte Änderung: 22 Jul 2021 18:31
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen