Morphological classification of medical images using nonlinear support vector machines

Christos Davatzikos, Dinggang Shen, Zhiqiang Lao, Zhong Xue, Bilge Karacali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The wavelet decomposition of a high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine pattern classification method to the morphological signatures. By considering measurements from the entire image, and not only from isolated anatomical structures, and by using a highly non-linear classifier, this method has achieved very high classification results in a variety of tests.

Original languageEnglish
Title of host publication2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
Pages587-590
Number of pages4
Volume1
Publication statusPublished - 2004 Dec 1
Externally publishedYes
Event2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano - Arlington, VA, United States
Duration: 2004 Apr 152004 Apr 18

Other

Other2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
CountryUnited States
CityArlington, VA
Period04/4/1504/4/18

Fingerprint

Wavelet decomposition
Pattern recognition
Support vector machines
Brain
Classifiers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Davatzikos, C., Shen, D., Lao, Z., Xue, Z., & Karacali, B. (2004). Morphological classification of medical images using nonlinear support vector machines. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano (Vol. 1, pp. 587-590)

Morphological classification of medical images using nonlinear support vector machines. / Davatzikos, Christos; Shen, Dinggang; Lao, Zhiqiang; Xue, Zhong; Karacali, Bilge.

2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. p. 587-590.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Davatzikos, C, Shen, D, Lao, Z, Xue, Z & Karacali, B 2004, Morphological classification of medical images using nonlinear support vector machines. in 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. vol. 1, pp. 587-590, 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano, Arlington, VA, United States, 04/4/15.
Davatzikos C, Shen D, Lao Z, Xue Z, Karacali B. Morphological classification of medical images using nonlinear support vector machines. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1. 2004. p. 587-590
Davatzikos, Christos ; Shen, Dinggang ; Lao, Zhiqiang ; Xue, Zhong ; Karacali, Bilge. / Morphological classification of medical images using nonlinear support vector machines. 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. pp. 587-590
@inproceedings{d5bbd5a38b7b4455b0d869defdc1c9a4,
title = "Morphological classification of medical images using nonlinear support vector machines",
abstract = "The wavelet decomposition of a high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine pattern classification method to the morphological signatures. By considering measurements from the entire image, and not only from isolated anatomical structures, and by using a highly non-linear classifier, this method has achieved very high classification results in a variety of tests.",
author = "Christos Davatzikos and Dinggang Shen and Zhiqiang Lao and Zhong Xue and Bilge Karacali",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "0780383885",
volume = "1",
pages = "587--590",
booktitle = "2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano",

}

TY - GEN

T1 - Morphological classification of medical images using nonlinear support vector machines

AU - Davatzikos, Christos

AU - Shen, Dinggang

AU - Lao, Zhiqiang

AU - Xue, Zhong

AU - Karacali, Bilge

PY - 2004/12/1

Y1 - 2004/12/1

N2 - The wavelet decomposition of a high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine pattern classification method to the morphological signatures. By considering measurements from the entire image, and not only from isolated anatomical structures, and by using a highly non-linear classifier, this method has achieved very high classification results in a variety of tests.

AB - The wavelet decomposition of a high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine pattern classification method to the morphological signatures. By considering measurements from the entire image, and not only from isolated anatomical structures, and by using a highly non-linear classifier, this method has achieved very high classification results in a variety of tests.

UR - http://www.scopus.com/inward/record.url?scp=17144394821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144394821&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:17144394821

SN - 0780383885

SN - 9780780383883

VL - 1

SP - 587

EP - 590

BT - 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano

ER -