English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  3D segmentation of SBFSEM images of neuropil by a graphical model over supervoxel boundaries

Andres, B., Koethe, U., Kroeger, T., Helmstaedter, M., Briggman, K. L., Denk, W., et al. (2012). 3D segmentation of SBFSEM images of neuropil by a graphical model over supervoxel boundaries. Medical Image Analysis, 16(4), 796-805. doi:10.1016/j.media.2011.11.004,.

Item is

Basic

show hide
Genre: Journal Article
Alternative Title : 3D segmentation of SBFSEM images of neuropil by a graphical model over supervoxel boundaries

Files

show Files
hide Files
:
MedicalImageAnal_16_2012_796.pdf (Any fulltext), 3MB
 
File Permalink:
-
Name:
MedicalImageAnal_16_2012_796.pdf
Description:
-
Visibility:
Restricted (Max Planck Institute for Medical Research, MHMF; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Andres, Bjoern, Author
Koethe, Ullrich, Author
Kroeger, Thorben, Author
Helmstaedter, Moritz1, Author              
Briggman, Kevin L., Author
Denk, Winfried2, Author              
Hamprecht, Fred A., Author
Affiliations:
1Department of Cell Physiology, Max Planck Institute for Medical Research, Max Planck Society, ou_1497701              
2Department of Biomedical Optics, Max Planck Institute for Medical Research, Max Planck Society, ou_1497699              

Content

show
hide
Free keywords: Segmentation; Circuit reconstruction; SBFSEM; Graphical model; Random forest
 Abstract: The segmentation of large volume images of neuropil acquired by serial sectioning electron microscopy is an important step toward the 3D reconstruction of neural circuits. The only cue provided by the data at hand is boundaries between otherwise indistinguishable objects. This indistinguishability, combined with the boundaries becoming very thin or faint in places, makes the large body of work on region−based segmentation methods inapplicable. On the other hand, boundary−based methods that exploit purely local evidence do not reach the extremely high accuracy required by the application domain that cannot tolerate the global topological errors arising from false local decisions. As a consequence, we propose a supervoxel merging method that arrives at its decisions in a non−local fashion, by posing and approximately solving a joint combinatorial optimization problem over all faces between supervoxels. The use of supervoxels allows the extraction of expressive geometric features. These are used by the higher−order potentials in a graphical model that assimilate knowledge about the geometry of neural surfaces by automated training on a gold standard. The scope of this improvement is demonstrated on the benchmark dataset E1088 (Helmstaedter et al., 2011) of 7.5 billion voxels from the inner plexiform layer of rabbit retina. We provide C++ source code for annotation, geometry extraction, training and inference

Details

show
hide
Language(s): eng - English
 Dates: 2009-07-312011-11-222011-12-192012-05-01
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Medical Image Analysis
  Other : Med. Image Anal.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: London : Elsevier
Pages: - Volume / Issue: 16 (4) Sequence Number: - Start / End Page: 796 - 805 Identifier: ISSN: 1361-8415
CoNE: https://pure.mpg.de/cone/journals/resource/954927741859