Computerized Detection and Quantification of Microcalcifications in Thyroid Nodules

Kuen Yuan Chen, Chiung Nien Chen, Ming Hsun Wu, Ming Chih Ho, Hao Chih Tai, Wen Chang Huang, Yuan Chang Chung, Argon Chen, King Jen Chang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

To improve the ultrasonographic detection rates of thyroid cancers with microcalcifications, we propose to enhance the sensitivity of sonographic calcifications detection and to avoid interobserver variation by a computerized quantification method in a prospective setting. A total of 227 participants with 258 nodules were evaluated. Among them, two nodules were excluded for suspicious aspiration cytology results without pathologic proof. Among the remaining 256 nodules, the diagnosis of 181 nodules was verified by surgical pathology and the diagnosis of 75 was based on fine needle aspiration (FNA) biopsy results. There were 173 benign thyroid nodules and 83 malignant thyroid nodules, which included 74 papillary carcinomas. Patient clinical data were collected and the presence of calcifications on conventional gray-scale ultrasound images was retrospectively reviewed by a thyroid specialist. Quantification of cystic components and calcifications was automatically performed by a proprietary program (AmCAD-UT) implemented with methods proposed in this article. The calcification index (CI) was calculated after the cystic component was excluded. The CI between benign and malignant nodules diagnosed by combined FNA biopsy and surgical pathology results (total number, 256) showed a significant difference (p < 0.0001, AUC = 0.746). Furthermore, we excluded patients without surgical pathology results for further validation and the CI between benign and malignant nodules confirmed by pathology results (total number, 181) showed a significant difference (p < 0.0001, AUC = 0.763). To learn whether our computer program increased our diagnostic capabilities, we analyzed human investigators and their abilities to detect and evaluate. In this study, calcifications were noted in 48.19% (40 of 83) of malignant thyroid nodules and in 10.98% (19 of 173) of benign nodules. This new computer-aided diagnosis method to evaluate the sonographic calcifications of thyroid nodules is a more sensitive and more objective method. It can provide better sensitivity than conventional methods in the diagnosis of thyroid malignancies containing microcalcifications.

Original languageEnglish
Pages (from-to)870-878
Number of pages9
JournalUltrasound in Medicine and Biology
Volume37
Issue number6
DOIs
Publication statusPublished - Jun 1 2011
Externally publishedYes

Fingerprint

Calcinosis
Thyroid Nodule
nodules
calcification
Surgical Pathology
Fine Needle Biopsy
pathology
Area Under Curve
Thyroid Gland
Observer Variation
Papillary Carcinoma
Thyroid Neoplasms
Cell Biology
needles
vacuum
Software
Research Personnel
Pathology
cancer
cytology

Keywords

  • Calcification index
  • Computer-aided diagnosis
  • Microcalcifications
  • Thyroid cancer

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Biophysics
  • Acoustics and Ultrasonics

Cite this

Computerized Detection and Quantification of Microcalcifications in Thyroid Nodules. / Chen, Kuen Yuan; Chen, Chiung Nien; Wu, Ming Hsun; Ho, Ming Chih; Tai, Hao Chih; Huang, Wen Chang; Chung, Yuan Chang; Chen, Argon; Chang, King Jen.

In: Ultrasound in Medicine and Biology, Vol. 37, No. 6, 01.06.2011, p. 870-878.

Research output: Contribution to journalArticle

Chen, Kuen Yuan ; Chen, Chiung Nien ; Wu, Ming Hsun ; Ho, Ming Chih ; Tai, Hao Chih ; Huang, Wen Chang ; Chung, Yuan Chang ; Chen, Argon ; Chang, King Jen. / Computerized Detection and Quantification of Microcalcifications in Thyroid Nodules. In: Ultrasound in Medicine and Biology. 2011 ; Vol. 37, No. 6. pp. 870-878.
@article{2dab2d1fb67a45db8736bff4dd9d40cf,
title = "Computerized Detection and Quantification of Microcalcifications in Thyroid Nodules",
abstract = "To improve the ultrasonographic detection rates of thyroid cancers with microcalcifications, we propose to enhance the sensitivity of sonographic calcifications detection and to avoid interobserver variation by a computerized quantification method in a prospective setting. A total of 227 participants with 258 nodules were evaluated. Among them, two nodules were excluded for suspicious aspiration cytology results without pathologic proof. Among the remaining 256 nodules, the diagnosis of 181 nodules was verified by surgical pathology and the diagnosis of 75 was based on fine needle aspiration (FNA) biopsy results. There were 173 benign thyroid nodules and 83 malignant thyroid nodules, which included 74 papillary carcinomas. Patient clinical data were collected and the presence of calcifications on conventional gray-scale ultrasound images was retrospectively reviewed by a thyroid specialist. Quantification of cystic components and calcifications was automatically performed by a proprietary program (AmCAD-UT) implemented with methods proposed in this article. The calcification index (CI) was calculated after the cystic component was excluded. The CI between benign and malignant nodules diagnosed by combined FNA biopsy and surgical pathology results (total number, 256) showed a significant difference (p < 0.0001, AUC = 0.746). Furthermore, we excluded patients without surgical pathology results for further validation and the CI between benign and malignant nodules confirmed by pathology results (total number, 181) showed a significant difference (p < 0.0001, AUC = 0.763). To learn whether our computer program increased our diagnostic capabilities, we analyzed human investigators and their abilities to detect and evaluate. In this study, calcifications were noted in 48.19{\%} (40 of 83) of malignant thyroid nodules and in 10.98{\%} (19 of 173) of benign nodules. This new computer-aided diagnosis method to evaluate the sonographic calcifications of thyroid nodules is a more sensitive and more objective method. It can provide better sensitivity than conventional methods in the diagnosis of thyroid malignancies containing microcalcifications.",
keywords = "Calcification index, Computer-aided diagnosis, Microcalcifications, Thyroid cancer",
author = "Chen, {Kuen Yuan} and Chen, {Chiung Nien} and Wu, {Ming Hsun} and Ho, {Ming Chih} and Tai, {Hao Chih} and Huang, {Wen Chang} and Chung, {Yuan Chang} and Argon Chen and Chang, {King Jen}",
year = "2011",
month = "6",
day = "1",
doi = "10.1016/j.ultrasmedbio.2011.03.002",
language = "English",
volume = "37",
pages = "870--878",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "6",

}

TY - JOUR

T1 - Computerized Detection and Quantification of Microcalcifications in Thyroid Nodules

AU - Chen, Kuen Yuan

AU - Chen, Chiung Nien

AU - Wu, Ming Hsun

AU - Ho, Ming Chih

AU - Tai, Hao Chih

AU - Huang, Wen Chang

AU - Chung, Yuan Chang

AU - Chen, Argon

AU - Chang, King Jen

PY - 2011/6/1

Y1 - 2011/6/1

N2 - To improve the ultrasonographic detection rates of thyroid cancers with microcalcifications, we propose to enhance the sensitivity of sonographic calcifications detection and to avoid interobserver variation by a computerized quantification method in a prospective setting. A total of 227 participants with 258 nodules were evaluated. Among them, two nodules were excluded for suspicious aspiration cytology results without pathologic proof. Among the remaining 256 nodules, the diagnosis of 181 nodules was verified by surgical pathology and the diagnosis of 75 was based on fine needle aspiration (FNA) biopsy results. There were 173 benign thyroid nodules and 83 malignant thyroid nodules, which included 74 papillary carcinomas. Patient clinical data were collected and the presence of calcifications on conventional gray-scale ultrasound images was retrospectively reviewed by a thyroid specialist. Quantification of cystic components and calcifications was automatically performed by a proprietary program (AmCAD-UT) implemented with methods proposed in this article. The calcification index (CI) was calculated after the cystic component was excluded. The CI between benign and malignant nodules diagnosed by combined FNA biopsy and surgical pathology results (total number, 256) showed a significant difference (p < 0.0001, AUC = 0.746). Furthermore, we excluded patients without surgical pathology results for further validation and the CI between benign and malignant nodules confirmed by pathology results (total number, 181) showed a significant difference (p < 0.0001, AUC = 0.763). To learn whether our computer program increased our diagnostic capabilities, we analyzed human investigators and their abilities to detect and evaluate. In this study, calcifications were noted in 48.19% (40 of 83) of malignant thyroid nodules and in 10.98% (19 of 173) of benign nodules. This new computer-aided diagnosis method to evaluate the sonographic calcifications of thyroid nodules is a more sensitive and more objective method. It can provide better sensitivity than conventional methods in the diagnosis of thyroid malignancies containing microcalcifications.

AB - To improve the ultrasonographic detection rates of thyroid cancers with microcalcifications, we propose to enhance the sensitivity of sonographic calcifications detection and to avoid interobserver variation by a computerized quantification method in a prospective setting. A total of 227 participants with 258 nodules were evaluated. Among them, two nodules were excluded for suspicious aspiration cytology results without pathologic proof. Among the remaining 256 nodules, the diagnosis of 181 nodules was verified by surgical pathology and the diagnosis of 75 was based on fine needle aspiration (FNA) biopsy results. There were 173 benign thyroid nodules and 83 malignant thyroid nodules, which included 74 papillary carcinomas. Patient clinical data were collected and the presence of calcifications on conventional gray-scale ultrasound images was retrospectively reviewed by a thyroid specialist. Quantification of cystic components and calcifications was automatically performed by a proprietary program (AmCAD-UT) implemented with methods proposed in this article. The calcification index (CI) was calculated after the cystic component was excluded. The CI between benign and malignant nodules diagnosed by combined FNA biopsy and surgical pathology results (total number, 256) showed a significant difference (p < 0.0001, AUC = 0.746). Furthermore, we excluded patients without surgical pathology results for further validation and the CI between benign and malignant nodules confirmed by pathology results (total number, 181) showed a significant difference (p < 0.0001, AUC = 0.763). To learn whether our computer program increased our diagnostic capabilities, we analyzed human investigators and their abilities to detect and evaluate. In this study, calcifications were noted in 48.19% (40 of 83) of malignant thyroid nodules and in 10.98% (19 of 173) of benign nodules. This new computer-aided diagnosis method to evaluate the sonographic calcifications of thyroid nodules is a more sensitive and more objective method. It can provide better sensitivity than conventional methods in the diagnosis of thyroid malignancies containing microcalcifications.

KW - Calcification index

KW - Computer-aided diagnosis

KW - Microcalcifications

KW - Thyroid cancer

UR - http://www.scopus.com/inward/record.url?scp=79956097361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956097361&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2011.03.002

DO - 10.1016/j.ultrasmedbio.2011.03.002

M3 - Article

VL - 37

SP - 870

EP - 878

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 6

ER -