English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Book Chapter

Learning to segment neurons with non-local quality measures

MPS-Authors
/persons/resource/persons94371

Mikula,  Shawn
Department of Biomedical Optics, Max Planck Institute for Medical Research, Max Planck Society;

/persons/resource/persons128986

Denk,  Winfried
Department of Biomedical Optics, Max Planck Institute for Medical Research, Max Planck Society;

Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Kroeger, T., Mikula, S., Denk, W., Koethe, U., & Hamprecht, F. A. (2013). Learning to segment neurons with non-local quality measures. In K. Mori, I. Sakuma, Y. Sato, C. Barillot, & N. Navab (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013 (pp. 419-427). Berlin Heidelberg: Springer-Verlag Berlin Heidelberg.


Cite as: https://hdl.handle.net/11858/00-001M-0000-0024-C797-5
Abstract
Segmentation schemes such as hierarchical region merging or correllation clustering rely on edge weights between adjacent (super-)voxels. The quality of these edge weights directly affects the quality of the resulting segmentations. Unstructured learning methods seek to minimize the classification error on individual edges. This ignores that a few local mistakes (tiny boundary gaps) can cause catastrophic global segmentation errors. Boundary evidence learning should therefore optimize structured quality criteria such as Rand Error or Variation of Information. We present the first structured learning scheme using a structured loss function; and we introduce a new hierarchical scheme that allows to approximately solve the NP hard prediction problem even for huge volume images. The value of these contributions is demonstrated on two challenging neural circuit reconstruction problems in serial sectioning electron microscopic images with billions of voxels. Our contributions lead to a partitioning quality that improves over the current state of the art