PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Upschulte, E.* ; Harmeling, S.* ; Amunts, K.* ; Dickscheid, T.*

Contour proposal networks for biomedical instance segmentation.

Med. Image Anal. 77:102371 (2022)
Verlagsversion DOI
Open Access Hybrid
We present a conceptually simple framework for object instance segmentation, called Contour Proposal Network (CPN), which detects possibly overlapping objects in an image while simultaneously fitting closed object contours using a fixed-size representation based on Fourier Descriptors. The CPN can incorporate state-of-the-art object detection architectures as backbone networks into a single-stage instance segmentation model that can be trained end-to-end. We construct CPN models with different backbone networks and apply them to instance segmentation of cells in datasets from different modalities. In our experiments, CPNs outperform U-NET, MASK R-CNN and STARDIST in instance segmentation accuracy. We present variants with execution times suitable for real-time applications. The trained models generalize well across different domains of cell types. Since the main assumption of the framework is closed object contours, it is applicable to a wide range of detection problems also beyond the biomedical domain. An implementation of the model architecture in PyTorch is freely available.
Impact Factor
Scopus SNIP
Web of Science
Times Cited
Altmetric
13.828
5.246
12
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 Cell Detection ; Cell Segmentation ; Cpn ; Object Detection
Sprache englisch
Veröffentlichungsjahr 2022
HGF-Berichtsjahr 2022
ISSN (print) / ISBN 1361-8415
e-ISSN 1361-8415
Zeitschrift Medical Image Analysis
Quellenangaben Band: 77, Heft: , Seiten: , Artikelnummer: 102371 Supplement: ,
Verlag Elsevier
Verlagsort Radarweg 29, 1043 Nx Amsterdam, Netherlands
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz AI - FZJ (HAI - FZJ)
Förderungen JARA-HPC on the supercomputer JURECA at Juelich Supercomputing Centre (JSC)
Helmholtz Association's Initiative and Networking Fund through the Helmholtz International BigBrain Analytics and Learning Laboratory (HIBALL)
"Computational Connectomics" of the German Research Foundation (DFG)
European Union
DOI 10.1016/j.media.2022.102371
WOS ID 000912927000003
Scopus ID 85124513907
Erfassungsdatum 2022-10-31
[➜Korrektur melden]