A unified approach for lesion segmentation on MRI of multiple sclerosis

B. R. Sajja; S. Datta; R. He; P. A. Narayana

A unified approach for lesion segmentation on MRI of multiple sclerosis

B. R. Sajja, S. Datta, R. He, P. A. Narayana

Research output: Contribution to journal › Conference article › peer-review

Abstract

Accurate determination of lesion volumes on brain MR images is hampered by the presence of a large number of false positive and negative classifications. A strategy that combines parametric and nonparametric techniques is developed and implemented for minimizing the false classifications. Initially, CSF and lesions are segmented using Parzen window classifier. Image processing, morphological operations, and ratio map of proton density (PD) and T2 weighted images are used for minimizing false positives. Lesions are delineated using fuzzy connectedness principle. Contextual information was used for minimizing false negative lesion classifications. Gray and white matter classification is realized using HMRF-EM algorithm.

Original language	English (US)
Pages (from-to)	1778-1781
Number of pages	4
Journal	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume	26 III
State	Published - 2004
Externally published	Yes
Event	Conference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004 - San Francisco, CA, United States Duration: Sep 1 2004 → Sep 5 2004

Keywords

Feature classification
Morphological operators
MRI
Multiple sclerosis
Segmentation

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Cite this

@article{6209268113e340e89e7c774a9485ce9e,

title = "A unified approach for lesion segmentation on MRI of multiple sclerosis",

abstract = "Accurate determination of lesion volumes on brain MR images is hampered by the presence of a large number of false positive and negative classifications. A strategy that combines parametric and nonparametric techniques is developed and implemented for minimizing the false classifications. Initially, CSF and lesions are segmented using Parzen window classifier. Image processing, morphological operations, and ratio map of proton density (PD) and T2 weighted images are used for minimizing false positives. Lesions are delineated using fuzzy connectedness principle. Contextual information was used for minimizing false negative lesion classifications. Gray and white matter classification is realized using HMRF-EM algorithm.",

keywords = "Feature classification, Morphological operators, MRI, Multiple sclerosis, Segmentation",

author = "Sajja, {B. R.} and S. Datta and R. He and Narayana, {P. A.}",

year = "2004",

language = "English (US)",

volume = "26 III",

pages = "1778--1781",

journal = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

issn = "0589-1019",

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

note = "Conference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004 ; Conference date: 01-09-2004 Through 05-09-2004",

}

TY - JOUR

T1 - A unified approach for lesion segmentation on MRI of multiple sclerosis

AU - Sajja, B. R.

AU - Datta, S.

AU - He, R.

AU - Narayana, P. A.

PY - 2004

Y1 - 2004

N2 - Accurate determination of lesion volumes on brain MR images is hampered by the presence of a large number of false positive and negative classifications. A strategy that combines parametric and nonparametric techniques is developed and implemented for minimizing the false classifications. Initially, CSF and lesions are segmented using Parzen window classifier. Image processing, morphological operations, and ratio map of proton density (PD) and T2 weighted images are used for minimizing false positives. Lesions are delineated using fuzzy connectedness principle. Contextual information was used for minimizing false negative lesion classifications. Gray and white matter classification is realized using HMRF-EM algorithm.

AB - Accurate determination of lesion volumes on brain MR images is hampered by the presence of a large number of false positive and negative classifications. A strategy that combines parametric and nonparametric techniques is developed and implemented for minimizing the false classifications. Initially, CSF and lesions are segmented using Parzen window classifier. Image processing, morphological operations, and ratio map of proton density (PD) and T2 weighted images are used for minimizing false positives. Lesions are delineated using fuzzy connectedness principle. Contextual information was used for minimizing false negative lesion classifications. Gray and white matter classification is realized using HMRF-EM algorithm.

KW - Feature classification

KW - Morphological operators

KW - MRI

KW - Multiple sclerosis

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=11144298719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144298719&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:11144298719

SN - 0589-1019

VL - 26 III

SP - 1778

EP - 1781

JO - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

JF - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

T2 - Conference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004

Y2 - 1 September 2004 through 5 September 2004

ER -

A unified approach for lesion segmentation on MRI of multiple sclerosis

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this