PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Clough, J.* ; Byrne, N.* ; Öksüz, I.* ; Zimmer, V.A.* ; Schnabel, J.A.* ; King, A.*

A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology.

IEEE Trans. Pattern Anal. Mach. Intell., DOI: 10.1109/TPAMI.2020.3013679 (2020)
Postprint DOI
Open Access Hybrid
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 concept used in topological data analysis, we can specify the desired topology of segmented objects in terms of their Betti numbers and then drive the proposed segmentations to contain the specified topological features. Importantly this process does not require any ground-truth labels, just prior knowledge of the topology of the structure being segmented. We demonstrate our approach in four experiments: one on MNIST image denoising and digit recognition, one on left ventricular myocardium segmentation from magnetic resonance imaging data from the UK Biobank, one on the ACDC public challenge dataset and one on placenta segmentation from 3-D ultrasound. We find that embedding explicit prior knowledge in neural network segmentation tasks is most beneficial when the segmentation task is especially challenging and that it can be used in either a semi-supervised or post-processing context to extract a useful training gradient from images without pixelwise labels.
Impact Factor
Scopus SNIP
Scopus
Cited By
Altmetric
17.861
11.215
28
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Convolutional Neural Networks ; Image Segmentation ; Loss Measurement ; Medical Imaging ; Network Topology ; Neural Networks ; Persistent Homology ; Segmentation ; Shape ; Topology ; Topology ; Training
Sprache englisch
Veröffentlichungsjahr 2020
HGF-Berichtsjahr 2020
ISSN (print) / ISBN 0162-8828
e-ISSN 1939-3539
Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Begutachtungsstatus Peer reviewed
Institut(e) Institute for Machine Learning in Biomed Imaging (IML)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-507100-001
DOI 10.1109/TPAMI.2020.3013679
Scopus ID 85101301735
Erfassungsdatum 2022-06-10
[➜Korrektur melden]