Fractal-based arteriovenous malformations detection in brain magnetic resonance images

Salim Lahmiri, Mounir Boukadoum, Antonio Di Ieva

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

A new fractal-based methodology to detect cerebral arteriovenous malformations (AVM) in brain magnetic resonance images (MRI) is presented. First, the MRI is preprocessed to emphasize edges. Then, the result is split into right and left brain hemisphere components that are converted to one-dimensional signals, for which the Hurst's exponent, the scaling exponent of detrended fluctuation analysis (DFA) and the energy of DFA fluctuations are computed to form a six-component feature vector. Finally, the vector is classified by a support vector machine (SVM). Using ten-fold cross validation and a set of twenty eight normal and twenty eight MR images of patients affected by AVMs, the classification of the corresponding feature vectors by the SVM achieved an accuracy of 98.26%, with a sensitivity of 98.82% and a specificity of 97.69%.

LanguageEnglish
Title of host publicationNEWCAS 2014
Subtitle of host publicationProceedings of the 2014 IEEE 12th International New Circuits and Systems Conference
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages21-24
Number of pages4
ISBN (Electronic)9781479948857, 9781479948864
ISBN (Print)9781479978694
DOIs
Publication statusPublished - 22 Oct 2014
Externally publishedYes
Event2014 12th IEEE International New Circuits and Systems Conference, NEWCAS 2014 - Trois-Rivieres, Canada
Duration: 22 Jun 201425 Jun 2014

Other

Other2014 12th IEEE International New Circuits and Systems Conference, NEWCAS 2014
CountryCanada
CityTrois-Rivieres
Period22/06/1425/06/14

Fingerprint

Magnetic resonance
Fractals
Brain
Support vector machines

Cite this

Lahmiri, S., Boukadoum, M., & Di Ieva, A. (2014). Fractal-based arteriovenous malformations detection in brain magnetic resonance images. In NEWCAS 2014: Proceedings of the 2014 IEEE 12th International New Circuits and Systems Conference (pp. 21-24). Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/NEWCAS.2014.6933975
Lahmiri, Salim ; Boukadoum, Mounir ; Di Ieva, Antonio. / Fractal-based arteriovenous malformations detection in brain magnetic resonance images. NEWCAS 2014: Proceedings of the 2014 IEEE 12th International New Circuits and Systems Conference. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2014. pp. 21-24
@inproceedings{e52c9278adf145858fd1d061053af612,
title = "Fractal-based arteriovenous malformations detection in brain magnetic resonance images",
abstract = "A new fractal-based methodology to detect cerebral arteriovenous malformations (AVM) in brain magnetic resonance images (MRI) is presented. First, the MRI is preprocessed to emphasize edges. Then, the result is split into right and left brain hemisphere components that are converted to one-dimensional signals, for which the Hurst's exponent, the scaling exponent of detrended fluctuation analysis (DFA) and the energy of DFA fluctuations are computed to form a six-component feature vector. Finally, the vector is classified by a support vector machine (SVM). Using ten-fold cross validation and a set of twenty eight normal and twenty eight MR images of patients affected by AVMs, the classification of the corresponding feature vectors by the SVM achieved an accuracy of 98.26{\%}, with a sensitivity of 98.82{\%} and a specificity of 97.69{\%}.",
author = "Salim Lahmiri and Mounir Boukadoum and {Di Ieva}, Antonio",
year = "2014",
month = "10",
day = "22",
doi = "10.1109/NEWCAS.2014.6933975",
language = "English",
isbn = "9781479978694",
pages = "21--24",
booktitle = "NEWCAS 2014",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
address = "United States",

}

Lahmiri, S, Boukadoum, M & Di Ieva, A 2014, Fractal-based arteriovenous malformations detection in brain magnetic resonance images. in NEWCAS 2014: Proceedings of the 2014 IEEE 12th International New Circuits and Systems Conference. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 21-24, 2014 12th IEEE International New Circuits and Systems Conference, NEWCAS 2014, Trois-Rivieres, Canada, 22/06/14. https://doi.org/10.1109/NEWCAS.2014.6933975

Fractal-based arteriovenous malformations detection in brain magnetic resonance images. / Lahmiri, Salim; Boukadoum, Mounir; Di Ieva, Antonio.

NEWCAS 2014: Proceedings of the 2014 IEEE 12th International New Circuits and Systems Conference. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 21-24.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Fractal-based arteriovenous malformations detection in brain magnetic resonance images

AU - Lahmiri, Salim

AU - Boukadoum, Mounir

AU - Di Ieva, Antonio

PY - 2014/10/22

Y1 - 2014/10/22

N2 - A new fractal-based methodology to detect cerebral arteriovenous malformations (AVM) in brain magnetic resonance images (MRI) is presented. First, the MRI is preprocessed to emphasize edges. Then, the result is split into right and left brain hemisphere components that are converted to one-dimensional signals, for which the Hurst's exponent, the scaling exponent of detrended fluctuation analysis (DFA) and the energy of DFA fluctuations are computed to form a six-component feature vector. Finally, the vector is classified by a support vector machine (SVM). Using ten-fold cross validation and a set of twenty eight normal and twenty eight MR images of patients affected by AVMs, the classification of the corresponding feature vectors by the SVM achieved an accuracy of 98.26%, with a sensitivity of 98.82% and a specificity of 97.69%.

AB - A new fractal-based methodology to detect cerebral arteriovenous malformations (AVM) in brain magnetic resonance images (MRI) is presented. First, the MRI is preprocessed to emphasize edges. Then, the result is split into right and left brain hemisphere components that are converted to one-dimensional signals, for which the Hurst's exponent, the scaling exponent of detrended fluctuation analysis (DFA) and the energy of DFA fluctuations are computed to form a six-component feature vector. Finally, the vector is classified by a support vector machine (SVM). Using ten-fold cross validation and a set of twenty eight normal and twenty eight MR images of patients affected by AVMs, the classification of the corresponding feature vectors by the SVM achieved an accuracy of 98.26%, with a sensitivity of 98.82% and a specificity of 97.69%.

UR - http://www.scopus.com/inward/record.url?scp=84914701276&partnerID=8YFLogxK

U2 - 10.1109/NEWCAS.2014.6933975

DO - 10.1109/NEWCAS.2014.6933975

M3 - Conference proceeding contribution

SN - 9781479978694

SP - 21

EP - 24

BT - NEWCAS 2014

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

ER -

Lahmiri S, Boukadoum M, Di Ieva A. Fractal-based arteriovenous malformations detection in brain magnetic resonance images. In NEWCAS 2014: Proceedings of the 2014 IEEE 12th International New Circuits and Systems Conference. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2014. p. 21-24 https://doi.org/10.1109/NEWCAS.2014.6933975