Advertisement

European Radiology

, Volume 29, Issue 4, pp 1978–1985 | Cite as

Computer-aided diagnosis system for thyroid nodules on ultrasonography: diagnostic performance and reproducibility based on the experience level of operators

  • Eun Young Jeong
  • Hye Lin Kim
  • Eun Ju HaEmail author
  • Seon Young Park
  • Yoon Joo Cho
  • Miran Han
Head and Neck

Abstract

Purpose

To evaluate the diagnostic performance and reproducibility of a computer-aided diagnosis (CAD) system for thyroid cancer diagnosis using ultrasonography (US) based on the operator’s experience.

Materials and methods

Between July 2016 and October 2016, 76 consecutive patients with 100 thyroid nodules (≥ 1.0 cm) were prospectively included. An experienced radiologist performed the US examinations with a real-time CAD system integrated into the US machine, and three operators with different levels of US experience (0–5 years) independently applied the CAD system. We compared the diagnostic performance of the CAD system based on the operators’ experience and calculated the interobserver agreement for cancer diagnosis and in terms of each US descriptor.

Results

The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the CAD system were 88.6, 83.9, 81.3, 90.4, and 86.0%, respectively. The sensitivity and accuracy of the CAD system were not significantly different from those of the radiologist (p > 0.05), while the specificity was higher for the experienced radiologist (p = 0.016). For the less-experienced operators, the sensitivity was 68.8–73.8%, specificity 74.1–88.5%, PPV 68.9–73.3%, NPV 72.7–80.0%, and accuracy 71.0–75.0%. The less-experienced operators showed lower sensitivity and accuracy than those for the experienced radiologist. The interobserver agreement was substantial for the final diagnosis and each US descriptor, and moderate for the margin and composition.

Conclusions

The CAD system may have a potential role in the thyroid cancer diagnosis. However, operator dependency still remains and needs improvement.

Key Points

• The sensitivity and accuracy of the CAD system did not differ significantly from those of the experienced radiologist (88.6% vs. 84.1%, p = 0.687; 86.0% vs. 91.0%, p = 0.267) while the specificity was significantly higher for the experienced radiologist (83.9% vs. 96.4%, p = 0.016).

• However, the diagnostic performance varied according to the operator’s experience (sensitivity 70.5–88.6%, accuracy 72.0–86.0%) and they were lower for the less-experienced operators than for the experienced radiologist.

• The interobserver agreement was substantial for the final diagnosis and each US descriptor and moderate for the margin and composition.

Keywords

Artificial intelligence Fine-needle aspiration Thyroid nodule Thyroid cancer Ultrasonography 

Abbreviations

AUC

Area under receiver operating characteristic curve

CAD

Computer-aided diagnosis

CI

Confidence interval

FNA

Fine-needle aspiration

NPV

Negative predictive value

PPV

Positive predictive value

PTC

Papillary thyroid carcinoma

ROC

Receiver operating characteristic

US

Ultrasonography

Notes

Funding

The authors state that this work was supported by the National Research Foundation of Korea (# 2017R1C1B5016217).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Eun Ju Ha.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from all patients before they underwent US.

Ethical approval

This study was approved by our institutional review board.

Methodology

• Prospective case-control study

References

  1. 1.
    Haugen BR (2017) 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: what is new and what has changed? Cancer 123:372–381CrossRefGoogle Scholar
  2. 2.
    Shin JH, Baek JH, Chung J et al (2016) Ultrasonography diagnosis and imaging-based management of thyroid nodules: revised Korean Society of Thyroid Radiology Consensus Statement and Recommendations. Korean J Radiol 17:370–395CrossRefGoogle Scholar
  3. 3.
    Choi SH, Kim EK, Kwak JY, Kim MJ, Son EJ (2010) Interobserver and intraobserver variations in ultrasound assessment of thyroid nodules. Thyroid 20:167–172CrossRefGoogle Scholar
  4. 4.
    Kim HG, Kwak JY, Kim EK, Choi SH, Moon HJ (2012) Man to man training: can it help improve the diagnostic performances and interobserver variabilities of thyroid ultrasonography in residents? Eur J Radiol 81:e352–e356CrossRefGoogle Scholar
  5. 5.
    Park CS, Kim SH, Jung SL et al (2010) Observer variability in the sonographic evaluation of thyroid nodules. J Clin Ultrasound 38:287–293Google Scholar
  6. 6.
    Park SH, Kim SJ, Kim EK, Kim MJ, Son EJ, Kwak JY (2009) Interobserver agreement in assessing the sonographic and elastographic features of malignant thyroid nodules. AJR Am J Roentgenol 193:W416–W423CrossRefGoogle Scholar
  7. 7.
    Kim SH, Park CS, Jung SL et al (2010) Observer variability and the performance between faculties and residents: US criteria for benign and malignant thyroid nodules. Korean J Radiol 11:149–155CrossRefGoogle Scholar
  8. 8.
    Acharya UR, Sree SV, Krishnan MM et al (2014) Computer-aided diagnostic system for detection of Hashimoto thyroiditis on ultrasound images from a Polish population. J Ultrasound Med 33:245–253CrossRefGoogle Scholar
  9. 9.
    Chang Y, Paul AK, Kim N et al (2016) Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: a comparison with radiologist-based assessments. Med Phys 43:554CrossRefGoogle Scholar
  10. 10.
    Choi YJ, Baek JH, Park HS et al (2017) A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of thyroid nodules on ultrasound: initial clinical assessment. Thyroid 27:546–552CrossRefGoogle Scholar
  11. 11.
    Li LN, Ouyang JH, Chen HL, Liu DY (2012) A computer aided diagnosis system for thyroid disease using extreme learning machine. J Med Syst 36:3327–3337CrossRefGoogle Scholar
  12. 12.
    Lim KJ, Choi CS, Yoon DY et al (2008) Computer-aided diagnosis for the differentiation of malignant from benign thyroid nodules on ultrasonography. Acad Radiol 15:853–858CrossRefGoogle Scholar
  13. 13.
    Fleiss JL (1971) Measuring nominal scale agreement among many raters. Psychol Bull 76:378–382CrossRefGoogle Scholar
  14. 14.
    Kundel HL, Polansky M (2003) Measurement of observer agreement. Radiology 228:303–308CrossRefGoogle Scholar
  15. 15.
    Chen KY, Chen CN, Wu MH et al (2014) Computerized quantification of ultrasonic heterogeneity in thyroid nodules. Ultrasound Med Biol 40:2581–2589CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  1. 1.Department of RadiologyAjou University School of MedicineSuwonSouth Korea

Personalised recommendations