Structure-based neuron retrieval across drosophila brains

Florian Ganglberger, Florian Schulze, L. Tirián, Alexey Novikov, Barry Dickson, Katja Bühler, Georg Langs

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Comparing local neural structures across large sets of examples is crucial when studying gene functions, and their effect in the Drosophila brain. The current practice of aligning brain volume data to a joint reference frame is based on the neuropil. However, even after alignment neurons exhibit residual location and shape variability that, together with image noise, hamper direct quantitative comparison and retrieval of similar structures on an intensity basis. In this paper, we propose and evaluate an image-based retrieval method for neurons, relying on local appearance, which can cope with spatial variability across the population. For an object of interest marked in a query case, the method ranks cases drawn from a large data set based on local neuron appearance in confocal microscopy data. The approach is based on capturing the orientation of neurons based on structure tensors and expanding this field via Gradient Vector Flow. During retrieval, the algorithm compares fields across cases, and calculates a corresponding ranking of most similar cases with regard to the local structure of interest. Experimental results demonstrate that the similarity measure and ranking mechanisms yield high precision and recall in realistic search scenarios.

Original languageEnglish
Pages (from-to)423-434
Number of pages12
JournalNeuroinformatics
Volume12
Issue number3
DOIs
Publication statusPublished - 2014

Fingerprint

Drosophila
Neurons
Brain
Neuropil
Confocal microscopy
Confocal Microscopy
Tensors
Genes
Joints
Population

Keywords

  • Drosophila
  • Gradient vector flow
  • Neuron retrieval
  • Similarity measure
  • Structure tensor

ASJC Scopus subject areas

  • Neuroscience(all)
  • Information Systems
  • Software
  • Medicine(all)

Cite this

Ganglberger, F., Schulze, F., Tirián, L., Novikov, A., Dickson, B., Bühler, K., & Langs, G. (2014). Structure-based neuron retrieval across drosophila brains. Neuroinformatics, 12(3), 423-434. https://doi.org/10.1007/s12021-014-9219-4

Structure-based neuron retrieval across drosophila brains. / Ganglberger, Florian; Schulze, Florian; Tirián, L.; Novikov, Alexey; Dickson, Barry; Bühler, Katja; Langs, Georg.

In: Neuroinformatics, Vol. 12, No. 3, 2014, p. 423-434.

Research output: Contribution to journalArticle

Ganglberger, F, Schulze, F, Tirián, L, Novikov, A, Dickson, B, Bühler, K & Langs, G 2014, 'Structure-based neuron retrieval across drosophila brains', Neuroinformatics, vol. 12, no. 3, pp. 423-434. https://doi.org/10.1007/s12021-014-9219-4
Ganglberger F, Schulze F, Tirián L, Novikov A, Dickson B, Bühler K et al. Structure-based neuron retrieval across drosophila brains. Neuroinformatics. 2014;12(3):423-434. https://doi.org/10.1007/s12021-014-9219-4
Ganglberger, Florian ; Schulze, Florian ; Tirián, L. ; Novikov, Alexey ; Dickson, Barry ; Bühler, Katja ; Langs, Georg. / Structure-based neuron retrieval across drosophila brains. In: Neuroinformatics. 2014 ; Vol. 12, No. 3. pp. 423-434.
@article{c013e74a82f04757abef52bcac614217,
title = "Structure-based neuron retrieval across drosophila brains",
abstract = "Comparing local neural structures across large sets of examples is crucial when studying gene functions, and their effect in the Drosophila brain. The current practice of aligning brain volume data to a joint reference frame is based on the neuropil. However, even after alignment neurons exhibit residual location and shape variability that, together with image noise, hamper direct quantitative comparison and retrieval of similar structures on an intensity basis. In this paper, we propose and evaluate an image-based retrieval method for neurons, relying on local appearance, which can cope with spatial variability across the population. For an object of interest marked in a query case, the method ranks cases drawn from a large data set based on local neuron appearance in confocal microscopy data. The approach is based on capturing the orientation of neurons based on structure tensors and expanding this field via Gradient Vector Flow. During retrieval, the algorithm compares fields across cases, and calculates a corresponding ranking of most similar cases with regard to the local structure of interest. Experimental results demonstrate that the similarity measure and ranking mechanisms yield high precision and recall in realistic search scenarios.",
keywords = "Drosophila, Gradient vector flow, Neuron retrieval, Similarity measure, Structure tensor",
author = "Florian Ganglberger and Florian Schulze and L. Tiri{\'a}n and Alexey Novikov and Barry Dickson and Katja B{\"u}hler and Georg Langs",
year = "2014",
doi = "10.1007/s12021-014-9219-4",
language = "English",
volume = "12",
pages = "423--434",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Humana Press",
number = "3",

}

TY - JOUR

T1 - Structure-based neuron retrieval across drosophila brains

AU - Ganglberger, Florian

AU - Schulze, Florian

AU - Tirián, L.

AU - Novikov, Alexey

AU - Dickson, Barry

AU - Bühler, Katja

AU - Langs, Georg

PY - 2014

Y1 - 2014

N2 - Comparing local neural structures across large sets of examples is crucial when studying gene functions, and their effect in the Drosophila brain. The current practice of aligning brain volume data to a joint reference frame is based on the neuropil. However, even after alignment neurons exhibit residual location and shape variability that, together with image noise, hamper direct quantitative comparison and retrieval of similar structures on an intensity basis. In this paper, we propose and evaluate an image-based retrieval method for neurons, relying on local appearance, which can cope with spatial variability across the population. For an object of interest marked in a query case, the method ranks cases drawn from a large data set based on local neuron appearance in confocal microscopy data. The approach is based on capturing the orientation of neurons based on structure tensors and expanding this field via Gradient Vector Flow. During retrieval, the algorithm compares fields across cases, and calculates a corresponding ranking of most similar cases with regard to the local structure of interest. Experimental results demonstrate that the similarity measure and ranking mechanisms yield high precision and recall in realistic search scenarios.

AB - Comparing local neural structures across large sets of examples is crucial when studying gene functions, and their effect in the Drosophila brain. The current practice of aligning brain volume data to a joint reference frame is based on the neuropil. However, even after alignment neurons exhibit residual location and shape variability that, together with image noise, hamper direct quantitative comparison and retrieval of similar structures on an intensity basis. In this paper, we propose and evaluate an image-based retrieval method for neurons, relying on local appearance, which can cope with spatial variability across the population. For an object of interest marked in a query case, the method ranks cases drawn from a large data set based on local neuron appearance in confocal microscopy data. The approach is based on capturing the orientation of neurons based on structure tensors and expanding this field via Gradient Vector Flow. During retrieval, the algorithm compares fields across cases, and calculates a corresponding ranking of most similar cases with regard to the local structure of interest. Experimental results demonstrate that the similarity measure and ranking mechanisms yield high precision and recall in realistic search scenarios.

KW - Drosophila

KW - Gradient vector flow

KW - Neuron retrieval

KW - Similarity measure

KW - Structure tensor

UR - http://www.scopus.com/inward/record.url?scp=84904743784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904743784&partnerID=8YFLogxK

U2 - 10.1007/s12021-014-9219-4

DO - 10.1007/s12021-014-9219-4

M3 - Article

VL - 12

SP - 423

EP - 434

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

IS - 3

ER -