Advertisement

European Archives of Oto-Rhino-Laryngology

, Volume 274, Issue 7, pp 2891–2897 | Cite as

Computer-aided diagnosis of malignant or benign thyroid nodes based on ultrasound images

  • Qin Yu
  • Tao Jiang
  • Aiyun ZhouEmail author
  • Lili Zhang
  • Cheng Zhang
  • Pan Xu
Head and Neck

Abstract

The objective of this study is to evaluate the diagnostic value of combination of artificial neural networks (ANN) and support vector machine (SVM)-based CAD systems in differentiating malignant from benign thyroid nodes with gray-scale ultrasound images. Two morphological and 65 texture features extracted from regions of interest in 610 2D-ultrasound thyroid node images from 543 patients (207 malignant, 403 benign) were used to develop the ANN and SVM models. Tenfold cross validation evaluated their performance; the best models showed accuracy of 99% for ANN and 100% for SVM. From 50 thyroid node ultrasound images from 45 prospectively enrolled patients, the ANN model showed sensitivity, specificity, positive and negative predictive values, Youden index, and accuracy of 88.24, 90.91, 83.33, 93.75, 79.14, and 90.00%, respectively, the SVM model 76.47, 90.91, 81.25, 88.24, 67.38, and 86.00%, respectively, and in combination 100.00, 87.88, 80.95, 100.00, 87.88, and 92.00%, respectively. Both ANN and SVM had high value in classifying thyroid nodes. In combination, the sensitivity increased but specificity decreased. This combination might provide a second opinion for radiologists dealing with difficult to diagnose thyroid node ultrasound images.

Keywords

Thyroid neoplasms Diagnosis Computer-assisted Ultrasonography 

Notes

Compliance with ethical standards

Funding

None.

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

References

  1. 1.
    Pellegriti G, Frasca F, Regalbuto C, Squatrito S, Vigneri R (2013) Worldwide increasing incidence of thyroid cancer: update on epidemiology and risk factors. J Cancer Epidemiol 2013:965212. doi: 10.1155/2013/965212 CrossRefPubMedPubMedCentralGoogle Scholar
  2. 2.
    Haugen BR, Alexander EK, Bible KC, Doherty GM, Mandel SJ, Nikiforov YE, Pacini F, Randolph GW, Sawka AM, Schlumberger M, Schuff KG, Sherman SI, Sosa JA, Steward DL, Tuttle RM, Wartofsky L (2016) 2015 American thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer. Thyroid 26:1–133. doi: 10.1089/thy.2015.0020 CrossRefPubMedPubMedCentralGoogle Scholar
  3. 3.
    Iannuccilli JD, Cronan JJ, Monchik JM (2004) Risk for malignancy of thyroid nodules as assessed by sonographic criteria: the need for biopsy. J Ultrasound Med Off J Am Inst Ultrasound Med 23:1455–1464CrossRefGoogle Scholar
  4. 4.
    Carneiro-Pla D (2013) Ultrasound elastography in the evaluation of thyroid nodules for thyroid cancer. Curr Opin Oncol 25:1–5. doi: 10.1097/CCO.0b013e32835a87c8 CrossRefPubMedGoogle Scholar
  5. 5.
    Calvete AC, Mestre JD, Gonzalez JM, Martinez ES, Sala BT, Zambudio AR (2014) Acoustic radiation force impulse imaging for evaluation of the thyroid gland. J Ultrasound Med 33:1031–1040. doi: 10.7863/ultra.33.6.1031 CrossRefPubMedGoogle Scholar
  6. 6.
    Huang YL, Chen DR, Jiang YR, Kuo SJ, Wu HK, Moon WK (2008) Computer-aided diagnosis using morphological features for classifying breast lesions on ultrasound. Ultrasound Obstet Gynecol 32:565–572. doi: 10.1002/uog.5205 CrossRefPubMedGoogle Scholar
  7. 7.
    Min-Chun Y, Woo Kyung M, Wang YC, Min Sun B, Chiun-Sheng H, Jeon-Hor C, Ruey-Feng C (2013) Robust texture analysis using multi-resolution gray-scale invariant features for breast sonographic tumor diagnosis. IEEE Trans Med Imaging 32:2262–2273. doi: 10.1109/tmi.2013.2279938 CrossRefGoogle Scholar
  8. 8.
    Abe Y, Hanai KM, Ohkubo Y, Hasizume T, Kakizaki T, Nakamura M, Niki N, Eguchi K, Fujino T, Moriyama N (2005) A computer-aided diagnosis (CAD) system in lung cancer screening with computed tomography. Anticancer Res 25:483–488PubMedGoogle Scholar
  9. 9.
    de Carvalho Filho AO, Silva AC, de Paiva AC, Nunes RA, Gattass M (2016) Computer-aided diagnosis system for lung nodules based on computed tomography using shape analysis, a genetic algorithm, and SVM. Med Biol Eng Comput. doi: 10.1007/s11517-016-1577-7 PubMedGoogle Scholar
  10. 10.
    Xu SY, Zhan WW, Wang WH (2015) Evaluation of thyroid nodules by a scoring and categorizing method based on sonographic features. J Ultrasound Med 34:2179–2185. doi: 10.7863/ultra.14.11041 CrossRefPubMedGoogle Scholar
  11. 11.
    Horvath E, Majlis S, Rossi R, Franco C, Niedmann JP, Castro A, Dominguez M (2009) An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management. J Clin Endocrinol Metab 94:1748–1751. doi: 10.1210/jc.2008-1724 CrossRefPubMedGoogle Scholar
  12. 12.
    Park JY, Lee HJ, Jang HW, Kim HK, Yi JH, Lee W, Kim SH (2009) A proposal for a thyroid imaging reporting and data system for ultrasound features of thyroid carcinoma. Thyroid 19:1257–1264. doi: 10.1089/thy.2008.0021 CrossRefPubMedGoogle Scholar
  13. 13.
    Kwak JY, Han KH, Yoon JH, Moon HJ, Son EJ, Park SH, Jung HK, Choi JS, Kim BM, Kim EK (2011) Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk. Radiology 260:892–899. doi: 10.1148/radiol.11110206 CrossRefPubMedGoogle Scholar
  14. 14.
    Ardakani AA, Gharbali A, Mohammadi A (2015) Classification of benign and malignant thyroid nodules using wavelet texture analysis of sonograms. J Ultrasound Med 34:1983–1989. doi: 10.7863/ultra.14.09057 CrossRefPubMedGoogle Scholar
  15. 15.
    Acharya UR, Swapna G, Sree SV, Molinari F, Gupta S, Bardales RH, Witkowska A, Suri JS (2014) A review on ultrasound-based thyroid cancer tissue characterization and automated classification. Technol Cancer Res Treat 13:289–301. doi: 10.7785/tcrt.2012.500381 PubMedGoogle Scholar
  16. 16.
    Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imaging 25:987–1010CrossRefPubMedGoogle Scholar
  17. 17.
    Wu CM, Chen YC, Hsieh KS (1992) Texture features for classification of ultrasonic images. IEEE Trans Med Imaging 11:141–152CrossRefPubMedGoogle Scholar
  18. 18.
    Wang L, He L, Mishra A, Li C (2009) Active contours driven by local Gaussian distribution fitting energy. Signal Process 89:2435–2447. doi: 10.1016/j.sigpro.2009.03.014 CrossRefGoogle Scholar
  19. 19.
    Haralick RM, Shanmugam K, Dinstein IH (1975) Texture features for image classification. IEEE Trans SMC Syst Man Cybern 3:610–621Google Scholar
  20. 20.
    Weszka JS, Dyer CR, Rosenfeld A (1976) A comparative study of texture measures for terrain classification. IEEE Trans Syst Man Cybern 6:269–285CrossRefGoogle Scholar
  21. 21.
    Amadasun M, King R (1989) Textural features corresponding to textural properties. IEEE Trans SMC Syst Man Cybern 19:1264–1274CrossRefGoogle Scholar
  22. 22.
    Tang X (1998) Texture information in run-length matrices. IEEE Tran Image Process Publ IEEE Signal Process Soc 7:1602–1609CrossRefGoogle Scholar
  23. 23.
    Liu Y, Wu H, Zhou Q, Gou J, Xu J, Liu Y, Chen Q (2016) Diagnostic value of conventional ultrasonography combined with contrast-enhanced ultrasonography in thyroid imaging reporting and data system (TI-RADS) 3 and 4 thyroid micronodules. Med Sci Monit 22:3086–3094. doi: 10.12659/msm.897011 CrossRefPubMedPubMedCentralGoogle Scholar
  24. 24.
    Srinivas MN, Amogh VN, Gautam MS, Prathyusha IS, Vikram NR, Retnam MK, Balakrishna BV, Kudva N (2016) A prospective study to evaluate the reliability of thyroid imaging reporting and data system in differentiation between benign and malignant thyroid lesions. J Clin Imaging Sci 6:5. doi: 10.4103/2156-7514.177551 CrossRefPubMedPubMedCentralGoogle Scholar
  25. 25.
    Soh LK, Tsatsoulis C (1999) Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens 37:780–795CrossRefGoogle Scholar
  26. 26.
    Lim KJ, Choi CS, Yoon DY, Chang SK, Kim KK, Han H, Kim SS, Lee J, Jeon YH (2008) Computer-aided diagnosis for the differentiation of malignant from benign thyroid nodules on ultrasonography. Acad Radiol 15:853–858. doi: 10.1016/j.acra.2007.12.022 CrossRefPubMedGoogle Scholar
  27. 27.
    Chang Y, Paul AK, Kim N, Baek JH, Choi YJ, Ha EJ, Lee KD, Lee HS, Shin D, Kim N (2016) Computer-aided diagnosis for classifying benign versus malignant thyroid nodules based on ultrasound images: a comparison with radiologist-based assessments. Med Phys 43:554. doi: 10.1118/1.4939060 CrossRefPubMedGoogle Scholar
  28. 28.
    Chen KY, Chen CN, Wu MH, Ho MC, Tai HC, Kuo WH, Huang WC, Wang YH, Chen A, Chang KJ (2014) Computerized quantification of ultrasonic heterogeneity in thyroid nodules. Ultrasound Med Biol 40:2581–2589. doi: 10.1016/j.ultrasmedbio.2014.06.009 CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Qin Yu
    • 1
  • Tao Jiang
    • 1
  • Aiyun Zhou
    • 1
    Email author
  • Lili Zhang
    • 1
  • Cheng Zhang
    • 1
  • Pan Xu
    • 1
  1. 1.Department of UltrasonographyThe First Affiliated Hospital of Nanchang UniversityNanchangChina

Personalised recommendations