Application of texture analysis in the differential diagnosis of benign and malignant thyroid nodules: Comparison with gray-scale ultrasound and elastography

Soo Yeon Kim, Eunkyung Kim, Hee Jung Moon, Jung Hyun Yoon, jinyoung kwak

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

OBJECTIVE. The purposes of this study were to investigate the optimal subset for texture analysis by use of a histogram and cooccurrence matrix in the differential diagnosis of benign and malignant thyroid nodules and to compare the results with those of gray-scale ultrasound and elastography. MATERIALS AND METHODS. From a retrospective search of an institutional database between June and November 2009, 633 solid nodules 5 mm or larger from 613 patients who underwent gray-scale ultrasound and elastography and subsequent ultrasound-guided fine-needle aspiration were included in this study. Each nodule was categorized as probably benign or suspicious of being malignant according to findings at gray-scale ultrasound and elastography. Histogram parameters (mean, SD, skewness, kurtosis, and entropy) and cooccurrence matrix parameters (contrast, correlation, uniformity, homogeneity, and entropy) were extracted from gray-scale ultrasound and elastographic images. The diagnostic performances of gray-scale ultrasound, elastography, and texture analysis for differentiating thyroid nodules were evaluated. RESULTS. Gray-scale ultrasound had the best diagnostic performance with an ROC AUC (Az) of 0.809 among all parameters. Elastography had significantly poorer performance (Az = 0.646) than gray-scale ultrasound (p < 0.001). Mean extracted from gray-scale ultrasound had the highest Az (0.675) among all histogram and cooccurrence matrix parameters extracted from gray-scale ultrasound and elastographic images. However, mean and the combination of mean and gray-scale ultrasound had poorer performance than gray-scale ultrasound alone. CONCLUSION. Using texture analysis does not improve diagnostic performance in the evaluation of thyroid cancers.

Original languageEnglish
Pages (from-to)W343-W351
JournalAmerican Journal of Roentgenology
Volume205
Issue number3
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Elasticity Imaging Techniques
Thyroid Nodule
Differential Diagnosis
Entropy
Fine Needle Biopsy
Thyroid Neoplasms
Area Under Curve
Databases

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

@article{acfece44bf1041a18798b6410606bd66,
title = "Application of texture analysis in the differential diagnosis of benign and malignant thyroid nodules: Comparison with gray-scale ultrasound and elastography",
abstract = "OBJECTIVE. The purposes of this study were to investigate the optimal subset for texture analysis by use of a histogram and cooccurrence matrix in the differential diagnosis of benign and malignant thyroid nodules and to compare the results with those of gray-scale ultrasound and elastography. MATERIALS AND METHODS. From a retrospective search of an institutional database between June and November 2009, 633 solid nodules 5 mm or larger from 613 patients who underwent gray-scale ultrasound and elastography and subsequent ultrasound-guided fine-needle aspiration were included in this study. Each nodule was categorized as probably benign or suspicious of being malignant according to findings at gray-scale ultrasound and elastography. Histogram parameters (mean, SD, skewness, kurtosis, and entropy) and cooccurrence matrix parameters (contrast, correlation, uniformity, homogeneity, and entropy) were extracted from gray-scale ultrasound and elastographic images. The diagnostic performances of gray-scale ultrasound, elastography, and texture analysis for differentiating thyroid nodules were evaluated. RESULTS. Gray-scale ultrasound had the best diagnostic performance with an ROC AUC (Az) of 0.809 among all parameters. Elastography had significantly poorer performance (Az = 0.646) than gray-scale ultrasound (p < 0.001). Mean extracted from gray-scale ultrasound had the highest Az (0.675) among all histogram and cooccurrence matrix parameters extracted from gray-scale ultrasound and elastographic images. However, mean and the combination of mean and gray-scale ultrasound had poorer performance than gray-scale ultrasound alone. CONCLUSION. Using texture analysis does not improve diagnostic performance in the evaluation of thyroid cancers.",
author = "Kim, {Soo Yeon} and Eunkyung Kim and Moon, {Hee Jung} and Yoon, {Jung Hyun} and jinyoung kwak",
year = "2015",
month = "1",
day = "1",
doi = "10.2214/AJR.14.13825",
language = "English",
volume = "205",
pages = "W343--W351",
journal = "American Journal of Roentgenology",
issn = "0361-803X",
publisher = "American Roentgen Ray Society",
number = "3",

}

Application of texture analysis in the differential diagnosis of benign and malignant thyroid nodules : Comparison with gray-scale ultrasound and elastography. / Kim, Soo Yeon; Kim, Eunkyung; Moon, Hee Jung; Yoon, Jung Hyun; kwak, jinyoung.

In: American Journal of Roentgenology, Vol. 205, No. 3, 01.01.2015, p. W343-W351.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of texture analysis in the differential diagnosis of benign and malignant thyroid nodules

T2 - Comparison with gray-scale ultrasound and elastography

AU - Kim, Soo Yeon

AU - Kim, Eunkyung

AU - Moon, Hee Jung

AU - Yoon, Jung Hyun

AU - kwak, jinyoung

PY - 2015/1/1

Y1 - 2015/1/1

N2 - OBJECTIVE. The purposes of this study were to investigate the optimal subset for texture analysis by use of a histogram and cooccurrence matrix in the differential diagnosis of benign and malignant thyroid nodules and to compare the results with those of gray-scale ultrasound and elastography. MATERIALS AND METHODS. From a retrospective search of an institutional database between June and November 2009, 633 solid nodules 5 mm or larger from 613 patients who underwent gray-scale ultrasound and elastography and subsequent ultrasound-guided fine-needle aspiration were included in this study. Each nodule was categorized as probably benign or suspicious of being malignant according to findings at gray-scale ultrasound and elastography. Histogram parameters (mean, SD, skewness, kurtosis, and entropy) and cooccurrence matrix parameters (contrast, correlation, uniformity, homogeneity, and entropy) were extracted from gray-scale ultrasound and elastographic images. The diagnostic performances of gray-scale ultrasound, elastography, and texture analysis for differentiating thyroid nodules were evaluated. RESULTS. Gray-scale ultrasound had the best diagnostic performance with an ROC AUC (Az) of 0.809 among all parameters. Elastography had significantly poorer performance (Az = 0.646) than gray-scale ultrasound (p < 0.001). Mean extracted from gray-scale ultrasound had the highest Az (0.675) among all histogram and cooccurrence matrix parameters extracted from gray-scale ultrasound and elastographic images. However, mean and the combination of mean and gray-scale ultrasound had poorer performance than gray-scale ultrasound alone. CONCLUSION. Using texture analysis does not improve diagnostic performance in the evaluation of thyroid cancers.

AB - OBJECTIVE. The purposes of this study were to investigate the optimal subset for texture analysis by use of a histogram and cooccurrence matrix in the differential diagnosis of benign and malignant thyroid nodules and to compare the results with those of gray-scale ultrasound and elastography. MATERIALS AND METHODS. From a retrospective search of an institutional database between June and November 2009, 633 solid nodules 5 mm or larger from 613 patients who underwent gray-scale ultrasound and elastography and subsequent ultrasound-guided fine-needle aspiration were included in this study. Each nodule was categorized as probably benign or suspicious of being malignant according to findings at gray-scale ultrasound and elastography. Histogram parameters (mean, SD, skewness, kurtosis, and entropy) and cooccurrence matrix parameters (contrast, correlation, uniformity, homogeneity, and entropy) were extracted from gray-scale ultrasound and elastographic images. The diagnostic performances of gray-scale ultrasound, elastography, and texture analysis for differentiating thyroid nodules were evaluated. RESULTS. Gray-scale ultrasound had the best diagnostic performance with an ROC AUC (Az) of 0.809 among all parameters. Elastography had significantly poorer performance (Az = 0.646) than gray-scale ultrasound (p < 0.001). Mean extracted from gray-scale ultrasound had the highest Az (0.675) among all histogram and cooccurrence matrix parameters extracted from gray-scale ultrasound and elastographic images. However, mean and the combination of mean and gray-scale ultrasound had poorer performance than gray-scale ultrasound alone. CONCLUSION. Using texture analysis does not improve diagnostic performance in the evaluation of thyroid cancers.

UR - http://www.scopus.com/inward/record.url?scp=84942597730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942597730&partnerID=8YFLogxK

U2 - 10.2214/AJR.14.13825

DO - 10.2214/AJR.14.13825

M3 - Article

C2 - 26295671

AN - SCOPUS:84942597730

VL - 205

SP - W343-W351

JO - American Journal of Roentgenology

JF - American Journal of Roentgenology

SN - 0361-803X

IS - 3

ER -