Characterization of the Major Histopathological Components of Thyroid Nodules Using Sonographic Textural Features for Clinical Diagnosis and Management

Shao Jer Chen, Sung Nien Yu, Jeh En Tzeng, Yen Ting Chen, Ku Yaw Chang, Kuo-Sheng Cheng, Fu Tsung Hsiao, Chang Kuo Wei

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

In this study, the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules was objectively quantified to facilitate clinical diagnosis and management. A total of 157 regions-of-interest thyroid ultrasound image was recruited in the study. The sonographic system used was the GE LOGIQ 700), (General Electric Healthcare, Chalfant St. Giles, UK). The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, ReliefF was used as a feature selector. Among the various textural features, the sum average value derived from co-occurrence matrix can well reflect echogenicity and can effectively differentiate between follicles and fibrosis base thyroid nodules. Fibrosis shows lowest echogenicity and lowest difference sum average value. Enlarged follicles show highest echogenicity and difference sum average values. Papillary cancer or follicular tumors show the difference sum average values and echogenicity between. The rule of thumb for the echogenicity is that the more follicles are mixed in, the higher the echo of the follicular tumor and papillary cancer will be and vice versa for fibrosis mixed. Areas with intermediate and lower echo should address the possibility of follicular or papillary neoplasm mixed with either follicles or fibrosis. These areas provide more cellular information for ultrasound guided aspiration (E-mail: a120930@tzuchi.com.tw).

Original languageEnglish
Pages (from-to)201-208
Number of pages8
JournalUltrasound in Medicine and Biology
Volume35
Issue number2
DOIs
Publication statusPublished - 2009 Feb 1

Fingerprint

fibrosis
Thyroid Nodule
nodules
Fibrosis
Neoplasms
echoes
tumors
cancer
Thyroid Gland
neoplasms
selectors
lesions
acquisition
textures
occurrences
vacuum
Delivery of Health Care
estimates
matrices

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Chen, Shao Jer ; Yu, Sung Nien ; Tzeng, Jeh En ; Chen, Yen Ting ; Chang, Ku Yaw ; Cheng, Kuo-Sheng ; Hsiao, Fu Tsung ; Wei, Chang Kuo. / Characterization of the Major Histopathological Components of Thyroid Nodules Using Sonographic Textural Features for Clinical Diagnosis and Management. In: Ultrasound in Medicine and Biology. 2009 ; Vol. 35, No. 2. pp. 201-208.
@article{48f48926eb7c4ae3bd75e58c6722c911,
title = "Characterization of the Major Histopathological Components of Thyroid Nodules Using Sonographic Textural Features for Clinical Diagnosis and Management",
abstract = "In this study, the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules was objectively quantified to facilitate clinical diagnosis and management. A total of 157 regions-of-interest thyroid ultrasound image was recruited in the study. The sonographic system used was the GE LOGIQ 700), (General Electric Healthcare, Chalfant St. Giles, UK). The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, ReliefF was used as a feature selector. Among the various textural features, the sum average value derived from co-occurrence matrix can well reflect echogenicity and can effectively differentiate between follicles and fibrosis base thyroid nodules. Fibrosis shows lowest echogenicity and lowest difference sum average value. Enlarged follicles show highest echogenicity and difference sum average values. Papillary cancer or follicular tumors show the difference sum average values and echogenicity between. The rule of thumb for the echogenicity is that the more follicles are mixed in, the higher the echo of the follicular tumor and papillary cancer will be and vice versa for fibrosis mixed. Areas with intermediate and lower echo should address the possibility of follicular or papillary neoplasm mixed with either follicles or fibrosis. These areas provide more cellular information for ultrasound guided aspiration (E-mail: a120930@tzuchi.com.tw).",
author = "Chen, {Shao Jer} and Yu, {Sung Nien} and Tzeng, {Jeh En} and Chen, {Yen Ting} and Chang, {Ku Yaw} and Kuo-Sheng Cheng and Hsiao, {Fu Tsung} and Wei, {Chang Kuo}",
year = "2009",
month = "2",
day = "1",
doi = "10.1016/j.ultrasmedbio.2008.08.017",
language = "English",
volume = "35",
pages = "201--208",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "2",

}

Characterization of the Major Histopathological Components of Thyroid Nodules Using Sonographic Textural Features for Clinical Diagnosis and Management. / Chen, Shao Jer; Yu, Sung Nien; Tzeng, Jeh En; Chen, Yen Ting; Chang, Ku Yaw; Cheng, Kuo-Sheng; Hsiao, Fu Tsung; Wei, Chang Kuo.

In: Ultrasound in Medicine and Biology, Vol. 35, No. 2, 01.02.2009, p. 201-208.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characterization of the Major Histopathological Components of Thyroid Nodules Using Sonographic Textural Features for Clinical Diagnosis and Management

AU - Chen, Shao Jer

AU - Yu, Sung Nien

AU - Tzeng, Jeh En

AU - Chen, Yen Ting

AU - Chang, Ku Yaw

AU - Cheng, Kuo-Sheng

AU - Hsiao, Fu Tsung

AU - Wei, Chang Kuo

PY - 2009/2/1

Y1 - 2009/2/1

N2 - In this study, the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules was objectively quantified to facilitate clinical diagnosis and management. A total of 157 regions-of-interest thyroid ultrasound image was recruited in the study. The sonographic system used was the GE LOGIQ 700), (General Electric Healthcare, Chalfant St. Giles, UK). The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, ReliefF was used as a feature selector. Among the various textural features, the sum average value derived from co-occurrence matrix can well reflect echogenicity and can effectively differentiate between follicles and fibrosis base thyroid nodules. Fibrosis shows lowest echogenicity and lowest difference sum average value. Enlarged follicles show highest echogenicity and difference sum average values. Papillary cancer or follicular tumors show the difference sum average values and echogenicity between. The rule of thumb for the echogenicity is that the more follicles are mixed in, the higher the echo of the follicular tumor and papillary cancer will be and vice versa for fibrosis mixed. Areas with intermediate and lower echo should address the possibility of follicular or papillary neoplasm mixed with either follicles or fibrosis. These areas provide more cellular information for ultrasound guided aspiration (E-mail: a120930@tzuchi.com.tw).

AB - In this study, the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules was objectively quantified to facilitate clinical diagnosis and management. A total of 157 regions-of-interest thyroid ultrasound image was recruited in the study. The sonographic system used was the GE LOGIQ 700), (General Electric Healthcare, Chalfant St. Giles, UK). The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, ReliefF was used as a feature selector. Among the various textural features, the sum average value derived from co-occurrence matrix can well reflect echogenicity and can effectively differentiate between follicles and fibrosis base thyroid nodules. Fibrosis shows lowest echogenicity and lowest difference sum average value. Enlarged follicles show highest echogenicity and difference sum average values. Papillary cancer or follicular tumors show the difference sum average values and echogenicity between. The rule of thumb for the echogenicity is that the more follicles are mixed in, the higher the echo of the follicular tumor and papillary cancer will be and vice versa for fibrosis mixed. Areas with intermediate and lower echo should address the possibility of follicular or papillary neoplasm mixed with either follicles or fibrosis. These areas provide more cellular information for ultrasound guided aspiration (E-mail: a120930@tzuchi.com.tw).

UR - http://www.scopus.com/inward/record.url?scp=58649123353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58649123353&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2008.08.017

DO - 10.1016/j.ultrasmedbio.2008.08.017

M3 - Article

C2 - 19010588

AN - SCOPUS:58649123353

VL - 35

SP - 201

EP - 208

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 2

ER -