Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines

Yuxiang Chen; Thomas Hrabe; Stefan Pfeffer; Olivier Pauly; Diana Mateus; Nassir Navab; Friedrich Förster

doi:10.1109/ISBI.2012.6235823

Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines

Yuxiang Chen, Thomas Hrabe, Stefan Pfeffer, Olivier Pauly, Diana Mateus, Nassir Navab, Friedrich Förster

Informatics 16 - Chair of Computer Aided Medical Procedures

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

17 Scopus citations

Abstract

Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a 3-step supervised learning approach: (i) pre-detection of candidates, (ii) feature calculation, and (iii) final decision using a support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, and (ii) rotation invariant features derived from spherical harmonics. Experiments conducted on both simulated and experimental tomograms show that our approach outperforms the state-of-the-art method.

Original language	English
Title of host publication	2012 9th IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI 2012 - Proceedings
Pages	1373-1376
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2012.6235823
State	Published - 2012
Event	2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Barcelona, Spain Duration: 2 May 2012 → 5 May 2012

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012
Country/Territory	Spain
City	Barcelona
Period	2/05/12 → 5/05/12

Keywords

Cryo-electron tomography
spherical harmonics
support vector machines
template matching

Access to Document

10.1109/ISBI.2012.6235823

Cite this

Chen, Y., Hrabe, T., Pfeffer, S., Pauly, O., Mateus, D., Navab, N., & Förster, F. (2012). Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings (pp. 1373-1376). Article 6235823 (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2012.6235823

@inproceedings{07120352cedd452f83f4fd7672b33edd,

title = "Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines",

abstract = "Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a 3-step supervised learning approach: (i) pre-detection of candidates, (ii) feature calculation, and (iii) final decision using a support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, and (ii) rotation invariant features derived from spherical harmonics. Experiments conducted on both simulated and experimental tomograms show that our approach outperforms the state-of-the-art method.",

keywords = "Cryo-electron tomography, spherical harmonics, support vector machines, template matching",

author = "Yuxiang Chen and Thomas Hrabe and Stefan Pfeffer and Olivier Pauly and Diana Mateus and Nassir Navab and Friedrich F{\"o}rster",

year = "2012",

doi = "10.1109/ISBI.2012.6235823",

language = "English",

isbn = "9781457718588",

series = "Proceedings - International Symposium on Biomedical Imaging",

pages = "1373--1376",

booktitle = "2012 9th IEEE International Symposium on Biomedical Imaging",

note = "2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 ; Conference date: 02-05-2012 Through 05-05-2012",

}

Chen, Y, Hrabe, T, Pfeffer, S, Pauly, O, Mateus, D, Navab, N & Förster, F 2012, Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines. in 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings., 6235823, Proceedings - International Symposium on Biomedical Imaging, pp. 1373-1376, 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012, Barcelona, Spain, 2/05/12. https://doi.org/10.1109/ISBI.2012.6235823

Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines. / Chen, Yuxiang; Hrabe, Thomas; Pfeffer, Stefan et al.
2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. 2012. p. 1373-1376 6235823 (Proceedings - International Symposium on Biomedical Imaging).

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

TY - GEN

T1 - Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines

AU - Chen, Yuxiang

AU - Hrabe, Thomas

AU - Pfeffer, Stefan

AU - Pauly, Olivier

AU - Mateus, Diana

AU - Navab, Nassir

AU - Förster, Friedrich

PY - 2012

Y1 - 2012

N2 - Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a 3-step supervised learning approach: (i) pre-detection of candidates, (ii) feature calculation, and (iii) final decision using a support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, and (ii) rotation invariant features derived from spherical harmonics. Experiments conducted on both simulated and experimental tomograms show that our approach outperforms the state-of-the-art method.

AB - Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a 3-step supervised learning approach: (i) pre-detection of candidates, (ii) feature calculation, and (iii) final decision using a support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, and (ii) rotation invariant features derived from spherical harmonics. Experiments conducted on both simulated and experimental tomograms show that our approach outperforms the state-of-the-art method.

KW - Cryo-electron tomography

KW - spherical harmonics

KW - support vector machines

KW - template matching

UR - http://www.scopus.com/inward/record.url?scp=84864833729&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2012.6235823

DO - 10.1109/ISBI.2012.6235823

M3 - Conference contribution

AN - SCOPUS:84864833729

SN - 9781457718588

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1373

EP - 1376

BT - 2012 9th IEEE International Symposium on Biomedical Imaging

T2 - 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012

Y2 - 2 May 2012 through 5 May 2012

ER -

Chen Y, Hrabe T, Pfeffer S, Pauly O, Mateus D, Navab N et al. Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. 2012. p. 1373-1376. 6235823. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2012.6235823

Detection and identification of macromolecular complexes in cryo-electron tomograms using support vector machines

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this