Neuron recognition with hidden neural network random fields

X. Chang, M. D. Kim, R. Stephens, T. Qu, S. Gulyanon, Akira Chiba, G. Tsechpenakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We model neuron morphology with a hidden Conditional Random Field variant, a hidden Neural Network Random Field, for part-based classification. We aim at identifying the diverse morphologies of individual motor neurons in the Drosophila larvae, and understanding underlying principles of synaptic connectivity in a motor circuit. The motivation of our work is the bottom-up reconstruction of the Drosophila connectome, ie., fully annotated neuronal circuits where neurons and synapses are automatically not only traced but also identified. We use images depicting single neurons labeled with green fluorescent protein (GFP) and serially imaged with laser scanning confocal microscopy. In our approach, we consider that each neuron has already been partitioned into its structurally significant parts, namely soma, axon, and dendrites, and their (latent) labels are known. We demonstrate the accuracy of our approach using wild-type motor neurons in the larval ventral nerve cord, and make comparisons with existing methods, including our previous work.

Original languageEnglish (US)
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages266-269
Number of pages4
ISBN (Print)9781467319591
StatePublished - Jul 29 2014
Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duration: Apr 29 2014May 2 2014

Other

Other2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
CountryChina
CityBeijing
Period4/29/145/2/14

Fingerprint

Neurons
Neural networks
Motor Neurons
Drosophila
Connectome
Carisoprodol
Dendrites
Green Fluorescent Proteins
Confocal Microscopy
Synapses
Larva
Axons
Networks (circuits)
Confocal microscopy
Labels
Proteins
Scanning
Lasers

Keywords

  • Drosophila
  • Hidden conditional random fields
  • Neuron morphology
  • Part-based classification

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Chang, X., Kim, M. D., Stephens, R., Qu, T., Gulyanon, S., Chiba, A., & Tsechpenakis, G. (2014). Neuron recognition with hidden neural network random fields. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 266-269). [6867860] Institute of Electrical and Electronics Engineers Inc..

Neuron recognition with hidden neural network random fields. / Chang, X.; Kim, M. D.; Stephens, R.; Qu, T.; Gulyanon, S.; Chiba, Akira; Tsechpenakis, G.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 266-269 6867860.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chang, X, Kim, MD, Stephens, R, Qu, T, Gulyanon, S, Chiba, A & Tsechpenakis, G 2014, Neuron recognition with hidden neural network random fields. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6867860, Institute of Electrical and Electronics Engineers Inc., pp. 266-269, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 4/29/14.
Chang X, Kim MD, Stephens R, Qu T, Gulyanon S, Chiba A et al. Neuron recognition with hidden neural network random fields. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 266-269. 6867860
Chang, X. ; Kim, M. D. ; Stephens, R. ; Qu, T. ; Gulyanon, S. ; Chiba, Akira ; Tsechpenakis, G. / Neuron recognition with hidden neural network random fields. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 266-269
@inproceedings{491517eb8fe34a9b8592542602bd65cd,
title = "Neuron recognition with hidden neural network random fields",
abstract = "We model neuron morphology with a hidden Conditional Random Field variant, a hidden Neural Network Random Field, for part-based classification. We aim at identifying the diverse morphologies of individual motor neurons in the Drosophila larvae, and understanding underlying principles of synaptic connectivity in a motor circuit. The motivation of our work is the bottom-up reconstruction of the Drosophila connectome, ie., fully annotated neuronal circuits where neurons and synapses are automatically not only traced but also identified. We use images depicting single neurons labeled with green fluorescent protein (GFP) and serially imaged with laser scanning confocal microscopy. In our approach, we consider that each neuron has already been partitioned into its structurally significant parts, namely soma, axon, and dendrites, and their (latent) labels are known. We demonstrate the accuracy of our approach using wild-type motor neurons in the larval ventral nerve cord, and make comparisons with existing methods, including our previous work.",
keywords = "Drosophila, Hidden conditional random fields, Neuron morphology, Part-based classification",
author = "X. Chang and Kim, {M. D.} and R. Stephens and T. Qu and S. Gulyanon and Akira Chiba and G. Tsechpenakis",
year = "2014",
month = "7",
day = "29",
language = "English (US)",
isbn = "9781467319591",
pages = "266--269",
booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Neuron recognition with hidden neural network random fields

AU - Chang, X.

AU - Kim, M. D.

AU - Stephens, R.

AU - Qu, T.

AU - Gulyanon, S.

AU - Chiba, Akira

AU - Tsechpenakis, G.

PY - 2014/7/29

Y1 - 2014/7/29

N2 - We model neuron morphology with a hidden Conditional Random Field variant, a hidden Neural Network Random Field, for part-based classification. We aim at identifying the diverse morphologies of individual motor neurons in the Drosophila larvae, and understanding underlying principles of synaptic connectivity in a motor circuit. The motivation of our work is the bottom-up reconstruction of the Drosophila connectome, ie., fully annotated neuronal circuits where neurons and synapses are automatically not only traced but also identified. We use images depicting single neurons labeled with green fluorescent protein (GFP) and serially imaged with laser scanning confocal microscopy. In our approach, we consider that each neuron has already been partitioned into its structurally significant parts, namely soma, axon, and dendrites, and their (latent) labels are known. We demonstrate the accuracy of our approach using wild-type motor neurons in the larval ventral nerve cord, and make comparisons with existing methods, including our previous work.

AB - We model neuron morphology with a hidden Conditional Random Field variant, a hidden Neural Network Random Field, for part-based classification. We aim at identifying the diverse morphologies of individual motor neurons in the Drosophila larvae, and understanding underlying principles of synaptic connectivity in a motor circuit. The motivation of our work is the bottom-up reconstruction of the Drosophila connectome, ie., fully annotated neuronal circuits where neurons and synapses are automatically not only traced but also identified. We use images depicting single neurons labeled with green fluorescent protein (GFP) and serially imaged with laser scanning confocal microscopy. In our approach, we consider that each neuron has already been partitioned into its structurally significant parts, namely soma, axon, and dendrites, and their (latent) labels are known. We demonstrate the accuracy of our approach using wild-type motor neurons in the larval ventral nerve cord, and make comparisons with existing methods, including our previous work.

KW - Drosophila

KW - Hidden conditional random fields

KW - Neuron morphology

KW - Part-based classification

UR - http://www.scopus.com/inward/record.url?scp=84927924486&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927924486&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781467319591

SP - 266

EP - 269

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -