Neuron segmentation with high-level biological priors / N. E. Krasowski, T. Beier, G. W. Knott, U. Köthe, F. A. Hamprecht, and A. Kreshuk

We present a novel approach to the problem of neuron segmentation in image volumes acquired by an electron microscopy. Existing methods, such as agglomerative or correlation clustering, rely solely on boundary evidence and have problems where such an evidence is lacking (e.g., incomplete staining) or ambiguous (e.g., co-located cell and mitochondria membranes). We investigate if these difficulties can be overcome by means of sparse region appearance cues that differentiate between pre- and postsynaptic neuron segments in mammalian neural tissue. We combine these cues with the traditional boundary evidence in the asymmetric multiway cut (AMWC) model, which simultaneously solves the partitioning and the semantic region labeling problems. We show that AMWC problems over superpixel graphs can be solved to global optimality with a cutting plane approach, and that the introduction of semantic class priors leads to significantly better segmentations..

Medienart:

E-Artikel

Erscheinungsjahr:

2018

Erschienen:

2018

Enthalten in:

Zur Gesamtaufnahme - volume:37

Enthalten in:

IEEE transactions on medical imaging - 37(2018), 4, Seite 829-839

Sprache:

Englisch

Beteiligte Personen:

Krasowski, Nikola Enrico [VerfasserIn]
Beier, Thorsten, 1987- [VerfasserIn]
Köthe, Ullrich [VerfasserIn]
Hamprecht, Fred [VerfasserIn]
Kreshuk, Anna [VerfasserIn]

Links:

Volltext

Themen:

AMWC problems
Agglomerative correlation clustering
Algorithms
Animals
Asymmetric multiway cut model
Automated tracing
Biological tissues
Biomembranes
Co-located cell
Connectomics
Cutting plane approach
Electron microscopy
Graph theory
High-level biological priors
Image Processing, Computer-Assisted
Image edge detection
Image resolution
Image segmentation
Image volumes
Incomplete staining
Labeling
Mammalian neural tissue
Medical image processing
Mice
Microscopy, Electron
Mitochondria membranes
Neuron segmentation
Neurons
Pattern clustering
Postsynaptic neuron segments
Probabilistic graphical model
Segmentation
Semantic class priors
Semantic region labeling problems
Semantics
Sparse region appearance cues

Anmerkungen:

Publication: 06 June 2017

Gesehen am 28.10.2019

Umfang:

11

doi:

10.1109/TMI.2017.2712360

funding:

Förderinstitution / Projekttitel:

PPN (Katalog-ID):

1680043676

Zugang & Verfügbarkeit




Zugehörige Publikationen/Bände

    Haven't found what you're looking for?