Asymmetry analysis of breast thermograms using automated segmentation and texture features

Dayakshini Sathish, Surekha Kamath, Keerthana Prasad, Rajagopal Kadavigere, Roshan J. Martis

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90%, sensitivity of 87.5% and specificity of 92.5% for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.

Original languageEnglish
Pages (from-to)745-752
Number of pages8
JournalSignal, Image and Video Processing
Volume11
Issue number4
DOIs
Publication statusPublished - 01-05-2017

Fingerprint

Statistical tests
Curve fitting
Image analysis
Classifiers
Textures
Polynomials

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{7f32e67972ff45af9cafd6c871638286,
title = "Asymmetry analysis of breast thermograms using automated segmentation and texture features",
abstract = "In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90{\%}, sensitivity of 87.5{\%} and specificity of 92.5{\%} for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.",
author = "Dayakshini Sathish and Surekha Kamath and Keerthana Prasad and Rajagopal Kadavigere and Martis, {Roshan J.}",
year = "2017",
month = "5",
day = "1",
doi = "10.1007/s11760-016-1018-y",
language = "English",
volume = "11",
pages = "745--752",
journal = "Signal, Image and Video Processing",
issn = "1863-1703",
publisher = "Springer London",
number = "4",

}

Asymmetry analysis of breast thermograms using automated segmentation and texture features. / Sathish, Dayakshini; Kamath, Surekha; Prasad, Keerthana; Kadavigere, Rajagopal; Martis, Roshan J.

In: Signal, Image and Video Processing, Vol. 11, No. 4, 01.05.2017, p. 745-752.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Asymmetry analysis of breast thermograms using automated segmentation and texture features

AU - Sathish, Dayakshini

AU - Kamath, Surekha

AU - Prasad, Keerthana

AU - Kadavigere, Rajagopal

AU - Martis, Roshan J.

PY - 2017/5/1

Y1 - 2017/5/1

N2 - In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90%, sensitivity of 87.5% and specificity of 92.5% for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.

AB - In this article, we present a new approach for breast thermogram image analysis by developing a fully automatic segmentation of right and left breast for asymmetry analysis, using shape features of the breast and Polynomial curve fitting. Segmentation results are validated with their respective Ground Truths. Histogram and grey level co-occurrence matrix-based texture features are extracted from the segmented images. Statistical test shows that features are highly significant in detection of breast cancer. We have obtained an accuracy of 90%, sensitivity of 87.5% and specificity of 92.5% for a set of eighty images with forty normal and forty abnormal using SVM RBF classifier.

UR - http://www.scopus.com/inward/record.url?scp=84996939021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996939021&partnerID=8YFLogxK

U2 - 10.1007/s11760-016-1018-y

DO - 10.1007/s11760-016-1018-y

M3 - Article

VL - 11

SP - 745

EP - 752

JO - Signal, Image and Video Processing

JF - Signal, Image and Video Processing

SN - 1863-1703

IS - 4

ER -