Tags

Type your tag names separated by a space and hit enter

Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model.
Comput Biol Med. 2008 Mar; 38(3):379-90.CB

Abstract

In this paper, an approach is proposed for fully automatic segmentation of MS lesions in fluid attenuated inversion recovery (FLAIR) Magnetic Resonance (MR) images. The proposed approach, based on a Bayesian classifier, utilizes the adaptive mixtures method (AMM) and Markov random field (MRF) model to obtain and upgrade the class conditional probability density function (CCPDF) and the a priori probability of each class. To compare the performance of the proposed approach with those of previous approaches including manual segmentation, the similarity criteria of different slices related to 20 MS patients were calculated. Also, volumetric comparison of lesions volume between the fully automated segmentation and the gold standard was performed using correlation coefficient (CC). The results showed a better performance for the proposed approach, compared to those of previous works.

Links

Publisher Full Text (DOI)

Authors+Show Affiliations

Khayati R
Biomedical Engineering Faculty, Amirkabir University of Technology, Tehran, Iran.
Vafadust M
No affiliation info available
Towhidkhah F
No affiliation info available
Nabavi M
No affiliation info available

MeSH

AdultAlgorithmsBayes TheoremFalse Negative ReactionsFalse Positive ReactionsFemaleHumansImage Interpretation, Computer-AssistedMagnetic Resonance ImagingMaleMarkov ChainsModels, StatisticalMultiple SclerosisProbabilityReproducibility of Results

Pub Type(s)

Journal Article

Language

eng

PubMed ID

18262511

Citation

Khayati, Rasoul, et al. "Fully Automatic Segmentation of Multiple Sclerosis Lesions in Brain MR FLAIR Images Using Adaptive Mixtures Method and Markov Random Field Model." Computers in Biology and Medicine, vol. 38, no. 3, 2008, pp. 379-90.
Khayati R, Vafadust M, Towhidkhah F, et al. Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model. Comput Biol Med. 2008;38(3):379-90.
Khayati, R., Vafadust, M., Towhidkhah, F., & Nabavi, M. (2008). Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model. Computers in Biology and Medicine, 38(3), 379-90. https://doi.org/10.1016/j.compbiomed.2007.12.005
Khayati R, et al. Fully Automatic Segmentation of Multiple Sclerosis Lesions in Brain MR FLAIR Images Using Adaptive Mixtures Method and Markov Random Field Model. Comput Biol Med. 2008;38(3):379-90. PubMed PMID: 18262511.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model. AU - Khayati,Rasoul, AU - Vafadust,Mansur, AU - Towhidkhah,Farzad, AU - Nabavi,Massood, Y1 - 2008/02/11/ PY - 2007/01/04/received PY - 2007/12/18/revised PY - 2007/12/19/accepted PY - 2008/2/12/pubmed PY - 2008/6/20/medline PY - 2008/2/12/entrez SP - 379 EP - 90 JF - Computers in biology and medicine JO - Comput Biol Med VL - 38 IS - 3 N2 - In this paper, an approach is proposed for fully automatic segmentation of MS lesions in fluid attenuated inversion recovery (FLAIR) Magnetic Resonance (MR) images. The proposed approach, based on a Bayesian classifier, utilizes the adaptive mixtures method (AMM) and Markov random field (MRF) model to obtain and upgrade the class conditional probability density function (CCPDF) and the a priori probability of each class. To compare the performance of the proposed approach with those of previous approaches including manual segmentation, the similarity criteria of different slices related to 20 MS patients were calculated. Also, volumetric comparison of lesions volume between the fully automated segmentation and the gold standard was performed using correlation coefficient (CC). The results showed a better performance for the proposed approach, compared to those of previous works. SN - 0010-4825 UR - https://www.unboundmedicine.com/medline/citation/18262511/Fully_automatic_segmentation_of_multiple_sclerosis_lesions_in_brain_MR_FLAIR_images_using_adaptive_mixtures_method_and_Markov_random_field_model_ DB - PRIME DP - Unbound Medicine ER -