Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions

U. Raghavendra, U. Rajendra Acharya, Anjan Gudigar, Jen Hong Tan, Hamido Fujita, Yuki Hagiwara, Filippo Molinari, Pailin Kongmebhol, Kwan Hoong Ng

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52%, 90.32% and 98.57% respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.

Original languageEnglish
Pages (from-to)110-120
Number of pages11
JournalUltrasonics
Volume77
DOIs
Publication statusPublished - 01-05-2017

Fingerprint

glands
classifiers
lesions
fractals
endocrine systems
textures
fusion
thyroid gland
ranking
cancer
prototypes
causes
sensitivity
curves

All Science Journal Classification (ASJC) codes

  • Acoustics and Ultrasonics

Cite this

Raghavendra, U. ; Rajendra Acharya, U. ; Gudigar, Anjan ; Hong Tan, Jen ; Fujita, Hamido ; Hagiwara, Yuki ; Molinari, Filippo ; Kongmebhol, Pailin ; Hoong Ng, Kwan. / Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions. In: Ultrasonics. 2017 ; Vol. 77. pp. 110-120.
@article{b3fae26f34d74905b34825ed94c9ecef,
title = "Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions",
abstract = "Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52{\%}, 90.32{\%} and 98.57{\%} respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.",
author = "U. Raghavendra and {Rajendra Acharya}, U. and Anjan Gudigar and {Hong Tan}, Jen and Hamido Fujita and Yuki Hagiwara and Filippo Molinari and Pailin Kongmebhol and {Hoong Ng}, Kwan",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.ultras.2017.02.003",
language = "English",
volume = "77",
pages = "110--120",
journal = "Ultrasonics",
issn = "0041-624X",
publisher = "Elsevier",

}

Raghavendra, U, Rajendra Acharya, U, Gudigar, A, Hong Tan, J, Fujita, H, Hagiwara, Y, Molinari, F, Kongmebhol, P & Hoong Ng, K 2017, 'Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions', Ultrasonics, vol. 77, pp. 110-120. https://doi.org/10.1016/j.ultras.2017.02.003

Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions. / Raghavendra, U.; Rajendra Acharya, U.; Gudigar, Anjan; Hong Tan, Jen; Fujita, Hamido; Hagiwara, Yuki; Molinari, Filippo; Kongmebhol, Pailin; Hoong Ng, Kwan.

In: Ultrasonics, Vol. 77, 01.05.2017, p. 110-120.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions

AU - Raghavendra, U.

AU - Rajendra Acharya, U.

AU - Gudigar, Anjan

AU - Hong Tan, Jen

AU - Fujita, Hamido

AU - Hagiwara, Yuki

AU - Molinari, Filippo

AU - Kongmebhol, Pailin

AU - Hoong Ng, Kwan

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52%, 90.32% and 98.57% respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.

AB - Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52%, 90.32% and 98.57% respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.

UR - http://www.scopus.com/inward/record.url?scp=85013131089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013131089&partnerID=8YFLogxK

U2 - 10.1016/j.ultras.2017.02.003

DO - 10.1016/j.ultras.2017.02.003

M3 - Article

AN - SCOPUS:85013131089

VL - 77

SP - 110

EP - 120

JO - Ultrasonics

JF - Ultrasonics

SN - 0041-624X

ER -