Implementation of high-dimensional feature map for segmentation of MR images

Renjie He; Balasrinivasa Rao Sajja; Ponnada A. Narayana

doi:10.1007/s10439-005-5888-3

Implementation of high-dimensional feature map for segmentation of MR images

Renjie He, Balasrinivasa Rao Sajja, Ponnada A. Narayana

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (≥3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.

Original language	English (US)
Pages (from-to)	1439-1448
Number of pages	10
Journal	Annals of biomedical engineering
Volume	33
Issue number	10
DOIs	https://doi.org/10.1007/s10439-005-5888-3
State	Published - Oct 2005
Externally published	Yes

Keywords

Feature map
Feature space
KNN classification
MRI
Multispectral segmentation

ASJC Scopus subject areas

Biomedical Engineering

Access to Document

10.1007/s10439-005-5888-3

Cite this

@article{3c2137b2a14441fdb13a0d1e825fc128,

title = "Implementation of high-dimensional feature map for segmentation of MR images",

abstract = "A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (≥3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.",

keywords = "Feature map, Feature space, KNN classification, MRI, Multispectral segmentation",

author = "Renjie He and Sajja, {Balasrinivasa Rao} and Narayana, {Ponnada A.}",

note = "Funding Information: This work is supported by the National Institutes of Health Grant R01 EB02095. We thank Dr. Jerry Wolinsky for providing access to the images on the MS patients and the validated AFFIRMATIVE data sets and identifying the training seeds used for generating the feature maps. We also thank Dr. Rakesh Gupta for performing the manual classification based on the FSE and FLAIR images. We acknowledge Dr. Sushmita Datta for developing part of the analysis software and Ms. Meghana Mehta for her help with segmentation.",

year = "2005",

month = oct,

doi = "10.1007/s10439-005-5888-3",

language = "English (US)",

volume = "33",

pages = "1439--1448",

journal = "Annals of Biomedical Engineering",

issn = "0090-6964",

publisher = "Springer Netherlands",

number = "10",

}

TY - JOUR

T1 - Implementation of high-dimensional feature map for segmentation of MR images

AU - He, Renjie

AU - Sajja, Balasrinivasa Rao

AU - Narayana, Ponnada A.

N1 - Funding Information: This work is supported by the National Institutes of Health Grant R01 EB02095. We thank Dr. Jerry Wolinsky for providing access to the images on the MS patients and the validated AFFIRMATIVE data sets and identifying the training seeds used for generating the feature maps. We also thank Dr. Rakesh Gupta for performing the manual classification based on the FSE and FLAIR images. We acknowledge Dr. Sushmita Datta for developing part of the analysis software and Ms. Meghana Mehta for her help with segmentation.

PY - 2005/10

Y1 - 2005/10

N2 - A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (≥3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.

AB - A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (≥3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.

KW - Feature map

KW - Feature space

KW - KNN classification

KW - MRI

KW - Multispectral segmentation

UR - http://www.scopus.com/inward/record.url?scp=27244433678&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27244433678&partnerID=8YFLogxK

U2 - 10.1007/s10439-005-5888-3

DO - 10.1007/s10439-005-5888-3

M3 - Article

C2 - 16240091

AN - SCOPUS:27244433678

SN - 0090-6964

VL - 33

SP - 1439

EP - 1448

JO - Annals of Biomedical Engineering

JF - Annals of Biomedical Engineering

IS - 10

ER -

Implementation of high-dimensional feature map for segmentation of MR images

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this