A new support vector machine method for medical image classification

Research output: A Conference proceeding or a Chapter in BookConference contribution

5 Citations (Scopus)

Abstract

One of the important problems in medical imaging is two-class classification, for example determination of benign from malignant cases in breast cancer treatment. In this paper we present a new support vector machine method for two-class medical image classification. The key idea of this method is to construct an optimal hypersphere such that both the interior margin between the surface of this sphere and the normal data, and the exterior margin between this surface and the abnormal data are as large as possible. The proposed method is easily implemented and can reduce both false positive and false negative error rates to obtain very good classification results. Experiments were performed on three medical image data sets to evaluate the proposed method.
Original languageEnglish
Title of host publication2010 2nd European Workshop on Visual Information Processing (EUVIP)
Place of PublicationUSA
PublisherIEEE
Pages165-170
Number of pages6
ISBN (Print)9781424472871
DOIs
Publication statusPublished - 2010
Event2nd European Workshop on Visual Information Processing: EUVIP 2010 - Paris, France
Duration: 5 Jul 20107 Jul 2010

Conference

Conference2nd European Workshop on Visual Information Processing: EUVIP 2010
CountryFrance
CityParis
Period5/07/107/07/10

Fingerprint

Image classification
Support vector machines
Oncology
Medical imaging
Experiments

Cite this

Tran, D., Ma, W., & Sharma, D. (2010). A new support vector machine method for medical image classification. In 2010 2nd European Workshop on Visual Information Processing (EUVIP) (pp. 165-170). USA: IEEE. https://doi.org/10.1109/EUVIP.2010.5699139
Tran, Dat ; Ma, Wanli ; Sharma, Dharmendra. / A new support vector machine method for medical image classification. 2010 2nd European Workshop on Visual Information Processing (EUVIP). USA : IEEE, 2010. pp. 165-170
@inproceedings{4ef33e04016643579fbb20632e86410f,
title = "A new support vector machine method for medical image classification",
abstract = "One of the important problems in medical imaging is two-class classification, for example determination of benign from malignant cases in breast cancer treatment. In this paper we present a new support vector machine method for two-class medical image classification. The key idea of this method is to construct an optimal hypersphere such that both the interior margin between the surface of this sphere and the normal data, and the exterior margin between this surface and the abnormal data are as large as possible. The proposed method is easily implemented and can reduce both false positive and false negative error rates to obtain very good classification results. Experiments were performed on three medical image data sets to evaluate the proposed method.",
author = "Dat Tran and Wanli Ma and Dharmendra Sharma",
year = "2010",
doi = "10.1109/EUVIP.2010.5699139",
language = "English",
isbn = "9781424472871",
pages = "165--170",
booktitle = "2010 2nd European Workshop on Visual Information Processing (EUVIP)",
publisher = "IEEE",

}

Tran, D, Ma, W & Sharma, D 2010, A new support vector machine method for medical image classification. in 2010 2nd European Workshop on Visual Information Processing (EUVIP). IEEE, USA, pp. 165-170, 2nd European Workshop on Visual Information Processing: EUVIP 2010, Paris, France, 5/07/10. https://doi.org/10.1109/EUVIP.2010.5699139

A new support vector machine method for medical image classification. / Tran, Dat; Ma, Wanli; Sharma, Dharmendra.

2010 2nd European Workshop on Visual Information Processing (EUVIP). USA : IEEE, 2010. p. 165-170.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A new support vector machine method for medical image classification

AU - Tran, Dat

AU - Ma, Wanli

AU - Sharma, Dharmendra

PY - 2010

Y1 - 2010

N2 - One of the important problems in medical imaging is two-class classification, for example determination of benign from malignant cases in breast cancer treatment. In this paper we present a new support vector machine method for two-class medical image classification. The key idea of this method is to construct an optimal hypersphere such that both the interior margin between the surface of this sphere and the normal data, and the exterior margin between this surface and the abnormal data are as large as possible. The proposed method is easily implemented and can reduce both false positive and false negative error rates to obtain very good classification results. Experiments were performed on three medical image data sets to evaluate the proposed method.

AB - One of the important problems in medical imaging is two-class classification, for example determination of benign from malignant cases in breast cancer treatment. In this paper we present a new support vector machine method for two-class medical image classification. The key idea of this method is to construct an optimal hypersphere such that both the interior margin between the surface of this sphere and the normal data, and the exterior margin between this surface and the abnormal data are as large as possible. The proposed method is easily implemented and can reduce both false positive and false negative error rates to obtain very good classification results. Experiments were performed on three medical image data sets to evaluate the proposed method.

U2 - 10.1109/EUVIP.2010.5699139

DO - 10.1109/EUVIP.2010.5699139

M3 - Conference contribution

SN - 9781424472871

SP - 165

EP - 170

BT - 2010 2nd European Workshop on Visual Information Processing (EUVIP)

PB - IEEE

CY - USA

ER -

Tran D, Ma W, Sharma D. A new support vector machine method for medical image classification. In 2010 2nd European Workshop on Visual Information Processing (EUVIP). USA: IEEE. 2010. p. 165-170 https://doi.org/10.1109/EUVIP.2010.5699139