A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology

We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the differentiable properties of persistent homology, a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence Jg. 44; H. 12; S. 8766 - 8778
Hauptverfasser:	Clough, James R., Byrne, Nicholas, Oksuz, Ilkay, Zimmer, Veronika A., Schnabel, Julia A., King, Andrew P.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms convolutional neural networks Data analysis Deep Learning Homology Image Processing, Computer-Assisted - methods Image segmentation Labels Loss measurement Magnetic resonance imaging Magnetic Resonance Imaging - methods medical imaging Myocardium Network topologies Network topology Neural networks Neural Networks, Computer Object recognition persistent homology Segmentation Shape Topology Training
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!