Adaptive kernelized evidential clustering for automatic 3D tumor segmentation in FDG–PET images

Automatically and reliably delineating tumor contours in noisy and blurring PET images is a challenging work in clinical oncology. In this paper, we introduce a specific unsupervised learning method to this end. More specifically, a robust clustering algorithm with spatial knowledge enhancement is d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multimedia systems Jg. 25; H. 2; S. 127 - 133
Hauptverfasser: Wang, Fan, Lian, Chunfeng, Vera, Pierre, Ruan, Su
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2019
Springer Nature B.V
Springer Verlag
Schlagworte:
Algorithms
Blurring
Clustering
Computer Communication Networks
Computer Graphics
Computer Science
Cryptology
Data Storage Representation
Feature extraction
Health risk assessment
Image segmentation
Life Sciences
Machine learning
Operating Systems
Positron emission
Special Issue Paper
Tomography
Tumors
Automatic tumor segmentation
Adaptive kernel metric
Theory of belief functions
Unsupervised learning
PET images, 3D
PET images
3D
ISSN:0942-4962, 1432-1882
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Automatically and reliably delineating tumor contours in noisy and blurring PET images is a challenging work in clinical oncology. In this paper, we introduce a specific unsupervised learning method to this end. More specifically, a robust clustering algorithm with spatial knowledge enhancement is developed in the framework of belief functions, a formal and powerful tool for modeling and reasoning with uncertain and/or imprecise information. Diverse patch-based image features are extracted to comprehensively describe PET image voxels. Then, informative input features are iteratively selected to learn an adaptive kernel-induced metric in an unsupervised way, so as to precisely grouping voxels into different clusters. The effectiveness of the proposed method has been evaluated on FDG–PET images for lung tumor patients.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0942-4962
1432-1882
DOI:10.1007/s00530-017-0579-0