Segmentation of neurons based on one-class classification

Paul Hernandez-Herrera; Manos Papadakis; Ioannis A. Kakadiaris

doi:10.1109/isbi.2014.6868119

Segmentation of neurons based on one-class classification

Paul Hernandez-Herrera, Manos Papadakis, Ioannis A. Kakadiaris

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

In this paper, we propose a novel one-class classification method to segment neurons. First, a new criterion to select a training set consisting of background voxels is proposed. Then, a discriminant function is learned from the training set that allows determining how similar an unlabeled voxel is to the voxels in the background class. Finally, foreground voxels are assigned as those unlabeled voxels that are not classified as background. Our method was qualitatively and quantitatively evaluated on several dataset to demonstrate its ability to accurately and robustly segment neurons.

Original language	English (US)
Title of host publication	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1316-1319
Number of pages	4
ISBN (Electronic)	9781467319591
DOIs	https://doi.org/10.1109/isbi.2014.6868119
State	Published - Jul 29 2014
Event	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China Duration: Apr 29 2014 → May 2 2014

Publication series

Name	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Conference

Conference	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Country/Territory	China
City	Beijing
Period	4/29/14 → 5/2/14

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/isbi.2014.6868119

Cite this

Hernandez-Herrera, P., Papadakis, M., & Kakadiaris, I. A. (2014). Segmentation of neurons based on one-class classification. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 1316-1319). [6868119] (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/isbi.2014.6868119

Segmentation of neurons based on one-class classification. / Hernandez-Herrera, Paul; Papadakis, Manos; Kakadiaris, Ioannis A.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1316-1319 6868119 (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hernandez-Herrera, P, Papadakis, M & Kakadiaris, IA 2014, Segmentation of neurons based on one-class classification. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6868119, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Institute of Electrical and Electronics Engineers Inc., pp. 1316-1319, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 4/29/14. https://doi.org/10.1109/isbi.2014.6868119

Hernandez-Herrera P, Papadakis M, Kakadiaris IA. Segmentation of neurons based on one-class classification. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1316-1319. 6868119. (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014). https://doi.org/10.1109/isbi.2014.6868119

@inproceedings{e50dc882419e4f57b3cd48483b87894b,

title = "Segmentation of neurons based on one-class classification",

abstract = "In this paper, we propose a novel one-class classification method to segment neurons. First, a new criterion to select a training set consisting of background voxels is proposed. Then, a discriminant function is learned from the training set that allows determining how similar an unlabeled voxel is to the voxels in the background class. Finally, foreground voxels are assigned as those unlabeled voxels that are not classified as background. Our method was qualitatively and quantitatively evaluated on several dataset to demonstrate its ability to accurately and robustly segment neurons.",

author = "Paul Hernandez-Herrera and Manos Papadakis and Kakadiaris, {Ioannis A.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 ; Conference date: 29-04-2014 Through 02-05-2014",

year = "2014",

month = jul,

day = "29",

doi = "10.1109/isbi.2014.6868119",

language = "English (US)",

series = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1316--1319",

booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",

address = "United States",

}

TY - GEN

T1 - Segmentation of neurons based on one-class classification

AU - Hernandez-Herrera, Paul

AU - Papadakis, Manos

AU - Kakadiaris, Ioannis A.

PY - 2014/7/29

Y1 - 2014/7/29

N2 - In this paper, we propose a novel one-class classification method to segment neurons. First, a new criterion to select a training set consisting of background voxels is proposed. Then, a discriminant function is learned from the training set that allows determining how similar an unlabeled voxel is to the voxels in the background class. Finally, foreground voxels are assigned as those unlabeled voxels that are not classified as background. Our method was qualitatively and quantitatively evaluated on several dataset to demonstrate its ability to accurately and robustly segment neurons.

AB - In this paper, we propose a novel one-class classification method to segment neurons. First, a new criterion to select a training set consisting of background voxels is proposed. Then, a discriminant function is learned from the training set that allows determining how similar an unlabeled voxel is to the voxels in the background class. Finally, foreground voxels are assigned as those unlabeled voxels that are not classified as background. Our method was qualitatively and quantitatively evaluated on several dataset to demonstrate its ability to accurately and robustly segment neurons.

UR - http://www.scopus.com/inward/record.url?scp=84927924692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927924692&partnerID=8YFLogxK

U2 - 10.1109/isbi.2014.6868119

DO - 10.1109/isbi.2014.6868119

M3 - Conference contribution

AN - SCOPUS:84927924692

T3 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

SP - 1316

EP - 1319

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Y2 - 29 April 2014 through 2 May 2014

ER -

Segmentation of neurons based on one-class classification

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this