Buchumschlag

A recurrent neural network for particle tracking in microscopy images using future information, track hypotheses, and multiple detections

Automatic tracking of particles in time-lapse fluorescence microscopy images is essential for quantifying the dynamic behavior of subcellular structures and virus structures. We introduce a novel particle tracking approach based on a deep recurrent neural network architecture that exploits past and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Spilger, Roman (VerfasserIn) , Imle, Andrea (VerfasserIn) , Lee, Ji Young (VerfasserIn) , Müller, Barbara (VerfasserIn) , Fackler, Oliver Till (VerfasserIn) , Bartenschlager, Ralf (VerfasserIn) , Rohr, Karl (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 13 January 2020
In: IEEE transactions on image processing
Year: 2020, Jahrgang: 29, Pages: 3681-3694
ISSN:1941-0042
DOI:10.1109/TIP.2020.2964515
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1109/TIP.2020.2964515
Volltext
Verfasserangaben:Roman Spilger, Andrea Imle, Ji-Young Lee, Barbara Müller, Oliver T. Fackler, Ralf Bartenschlager, Karl Rohr
Beschreibung
Zusammenfassung:Automatic tracking of particles in time-lapse fluorescence microscopy images is essential for quantifying the dynamic behavior of subcellular structures and virus structures. We introduce a novel particle tracking approach based on a deep recurrent neural network architecture that exploits past and future information in both forward and backward direction. Assignment probabilities are determined jointly across multiple detections, and the probability of missing detections is computed. In addition, existence probabilities are determined by the network to handle track initiation and termination. For correspondence finding, track hypotheses are propagated to future time points so that information at later time points can be used to resolve ambiguities. A handcrafted similarity measure and handcrafted motion features are not necessary. Manually labeled data is not required for network training. We evaluated the performance of our approach using image data of the Particle Tracking Challenge as well as real fluorescence microscopy image sequences of virus structures. It turned out that the proposed approach outperforms previous methods.
Beschreibung:Gesehen am 30.03.2020
Beschreibung:Online Resource
ISSN:1941-0042
DOI:10.1109/TIP.2020.2964515

Ähnliche Einträge