Journal of Medical Systems

, Volume 36, Issue 3, pp 1271–1281 | Cite as

ΤND: A Thyroid Nodule Detection System for Analysis of Ultrasound Images and Videos

  • Eystratios G. KeramidasEmail author
  • Dimitris Maroulis
  • Dimitris K. Iakovidis


In this paper, we present a computer-aided-diagnosis (CAD) system prototype, named TND (Thyroid Nodule Detector), for the detection of nodular tissue in ultrasound (US) thyroid images and videos acquired during thyroid US examinations. The proposed system incorporates an original methodology that involves a novel algorithm for automatic definition of the boundaries of the thyroid gland, and a novel approach for the extraction of noise resilient image features effectively representing the textural and the echogenic properties of the thyroid tissue. Through extensive experimental evaluation on real thyroid US data, its accuracy in thyroid nodule detection has been estimated to exceed 95%. These results attest to the feasibility of the clinical application of TND, for the provision of a second more objective opinion to the radiologists by exploiting image evidences.


Computer-aided-diagnosis Thyroid Nodule Ultrasound 



We would like to thank EUROMEDICA S.A., Greece for the provision of the medical images. We would also like to thank N. Dimitropoulos, M.D. and G. Legakis, M.D. for their continuous support and advice. This work was supported by the Greek General Secretariat of Research and Technology (25%), the European Social Fund (75%), and the private sector, under the framework of Measure 8.3 of E.P. Antagonistikotita—3rd European Support Framework—PENED 2003 (grant no. 03-ED-662).


  1. 1.
    Welker, M., Orlov, D., Thyroid Nodules. American Family Physician, 67, 2003.Google Scholar
  2. 2.
    Raeth, U., Schlaps, D., Limberg, B., Zuna, I., Lorenz, A., Kaick, G., Lorenz, W. J., and Kommerell, B., Diagnostic accuracy of computerized B-scan texture analysis and conventional ultrasonography in diffuse parenchymal and malignant liver disease. J Clin Ultrasound 13:87–99, 1985.CrossRefGoogle Scholar
  3. 3.
    Abe, C., Kahn, C. E., Doi, K., and Katsuragawa, S., Computer-aided detection of diffuse liver disease in ultrasound images. Investig Radiol 27:71–77, 1992.CrossRefGoogle Scholar
  4. 4.
    Kadah, Y. M., Farag, A. A., Zurada, J. M., Badawi, A. M., and Youssef, A. M., Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Trans Med Imaging 15:466–478, 1996.CrossRefGoogle Scholar
  5. 5.
    Horsch, K., Giger, M. L., Vyborny, C. J., and Venta, L. A., Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography. Acad Radiol 11:272–280, 2004.CrossRefGoogle Scholar
  6. 6.
    Joo, S., Yang, Y. S., Moon, W. K., and Kim, H. C., Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features. IEEE Trans Med Imaging 23:1292–1300, 2004.CrossRefGoogle Scholar
  7. 7.
    Kuo, W. J., Chang, R. F., Moon, W. K., Lee, C. C., and Chen, D. R., Computer-aided diagnosis of breast tumors with different US systems. Acad. Radiology 9:793–799, 2002.CrossRefGoogle Scholar
  8. 8.
    Huynen, A., Giesen, R., De La Rosette, J., Aarnink, R., Debruyne, F., and Wijkstra, H., Analysis of ultrasonographic prostate images for the detection of prostatic carcinoma: the automated urologic diagnostic expert system. Ultrasound Med Biol 20:1–10, 1994.CrossRefGoogle Scholar
  9. 9.
    Rosette, J., Computerized analysis of transrectal ultrasonography images in the detection of prostate carcinoma. Br J Urol 75:485–491, 1995.CrossRefGoogle Scholar
  10. 10.
    Smutek, D., Šara, R., Sucharda, P., Tjahjadi, T., and Švec, M., Image texture analysis of sonograms in chronic inflammations of thyroid gland. Ultrasound Med Biol 29:1531–1543, 2003.CrossRefGoogle Scholar
  11. 11.
    Muzzolini, R., Yang, Y. H., and Pierson, R., Texture characterization using robust statistics. Pattern Recognit 27(1):119–134, 1994.CrossRefGoogle Scholar
  12. 12.
    Haralick, R. M., Dinstein, I., and Shanmugamm, K., Textural features for image classification. IEEE Trans. On Systems, Man and Cybernetics 3(6):610–621, 1973.CrossRefGoogle Scholar
  13. 13.
    Tsantis, S., Cavouras, D., Kalatzis, I., Piliouras, N., Dimitropoulos, N., and Nikiforidis, G., Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk. Ultrasound Med Biology 31:1451–1459, 2005.CrossRefGoogle Scholar
  14. 14.
    Maroulis, D. E., Savelonas, M., Karkanis, S. A., Iakovidis, D. K., Dimitropoulos, N., Computer-Aided Thyroid Nodule Detection in Ultrasound Images, IEEE International Symposium on Computer-Based Medical Systems—CBMS: 271–276, 2005.Google Scholar
  15. 15.
    Mailloux, G., Bertrand, M., Stampfler, R., and Ethier, S., Local histogram information content of ultrasound B-mode echographic texture. Ultrasound Med Biol 11:743–750, 1985.CrossRefGoogle Scholar
  16. 16.
    Mailloux, G., Bertrand, M., Stampfler, R., and Ethier, S., Computer analysis of echographic textures in hashimoto disease of the thyroid. J Clin Ultrasound 14:521–527, 1986.CrossRefGoogle Scholar
  17. 17.
    Morifuji, H., Analysis of ultrasound B-mode histogram in thyroid tumors. Nippon Geka Gakkai Zasshi 90(2):210–221, 1989.Google Scholar
  18. 18.
    Hirning, T., Zuna, I., and Schlaps, D., Quantification and classification of echographic findings the thyroid gland by computerized b-mode texture analysis. Eur J Radiol 9:244–247, 1989.Google Scholar
  19. 19.
    Julesz, B., Textons, the elements of texture perception, and their interactions. Nature 290:91, 1981.CrossRefGoogle Scholar
  20. 20.
    Skouroliakou, C., Lyra, M., Antoniou, A., and Vlahos, L., Quantitative image analysis in sonograms of the thyroid gland. Nucl Instrum Meth Phys 569:606–609, 2006.CrossRefGoogle Scholar
  21. 21.
    Savelonas, M. A., Iakovidis, D. K., Dimitropoulos, N., and Maroulis, D., Computational Characterization of Thyroid Tissue in the Radon Domain, IEEE Internationa Symposium on Computer-Based Medical Systems 189-192, 2007.Google Scholar
  22. 22.
    Keramidas, E. G., Iakovidis, D., Maroulis, D., and Karkanis, S. A., Efficient and effective ultrasound image analysis scheme for thyroid nodule detection. Lect Notes Comput Sci 4633:1052–1060, 2007.CrossRefGoogle Scholar
  23. 23.
    Iakovidis, D. K., Keramidas, E., and Maroulis, D., Fuzzy local binary patterns for ultrasound texture characterization, image analysis and recognition. International Conference (ICIAR 2008) Springer LNCS 5112:750–759, 2008.Google Scholar
  24. 24.
    Wilhjelm, J., Gronholdt, M. L., Wiebe, B., Jespersen, S. K., Hansen, L. K., and Sillesen, H., Quantitative analysis of ultrasound B-mode images of carotid atherosclerotic plaque: correlation with visual classifcation and histological examination. IEEE Trans Med Imaging 17:910–922, 1998.CrossRefGoogle Scholar
  25. 25.
    Rumack, C. M., Wilson, S. R., Charboneau, J. W., Johnson, J. A., Diagnostic Ultrasound, Mosby, ISBN 0323020232, 2004.Google Scholar
  26. 26.
    Maroulis, D. E., Savelonas, M. A., Iakovidis, D. K., Karkanis, S. A., and Dimitropoulos, N., Variable background active contour model for computer-aided delineation of nodules in thyroid ultrasound images. IEEE Trans Inf Technol Biomed 11(5):537–543, 2007.CrossRefGoogle Scholar
  27. 27.
    Chen, D.-R., Chang, R.-F., Wu, W.-J., Moon, W. K., and Wu, W.-L., 3-D breast ultrasound segmentation using active contour model. Ultrasound Med Biol 29(7):1017–1026, 2003.CrossRefGoogle Scholar
  28. 28.
    Hu, N., Downey, D. B., Fenster, A., and Ladak, H. M., Prostate boundary segmentation from 3d ultrasound images. Med Phys 30(7):1648–1659, 2003.CrossRefGoogle Scholar
  29. 29.
    Chiu, B., Freeman, G. H., Salama, M. M. A., and Fenster, A., Prostate segmentation algorithm using dyadic wavelet transform and discrete dynamic contour. Phys Med Biol 49(21):4943–4960, 2004.CrossRefGoogle Scholar
  30. 30.
    Ojala, T., Pietikainen, M., Harwood, D., A comparative study of texture measures with classification based on featured distribution. Pattern Recognition 29, 1996.Google Scholar
  31. 31.
    Petrou, M., and Sevilla, P. G., Image Processing: Dealing With Texture, John Wiley and Sons Ltd, 2006.Google Scholar
  32. 32.
    Jasjit, S., Wilson, D., and Laxminarayan, S., (Eds.) Handbook of Biomedical Image Analysis, 2005, ISBN: 978-0-306-48550-3.Google Scholar
  33. 33.
    Simeone, F. J., Daniel, G. H., and MuLler, P. R., High-resolution real-time sonography. Radiology 155:431–439, 1985.Google Scholar
  34. 34.
    Jawahar, C. V., and Ray, A. K., Fuzzy statistics of digital images. IEEE Signal Process Lett 3:225–227, 1996.CrossRefGoogle Scholar
  35. 35.
    Chapelle, O., Haffner, P., and Vapnik, V. N., Support vector machines for histogram-based image classification. IEEE Trans Neural Netw. IEEE Trans 10:1055–1064, 1999.CrossRefGoogle Scholar
  36. 36.
    Vapnik, V. N., The nature of statistical learning theory. Springer-Verlag, New York, 1995.zbMATHGoogle Scholar
  37. 37.
    Burges, C., A tutorial on support vector machines for pattern recognition, Kluwer Academic Publishers, 1998.Google Scholar
  38. 38.
    Theodoridis, S., and Koutroumbas, K., Pattern Recognition, Academic Press, 2008.Google Scholar
  39. 39.
    Maroulis, D., Iakovidis, D., Karkanis, S., and Karras, D., COLD: a versatile system for detection of colorectal lesions in endoscopic images. Comput Meth Programs Biomed 70:151–166, 2003.CrossRefGoogle Scholar
  40. 40.
    General Electric Healthcare. Ultrasound Imaging System, Voluson 730 Pro. Retrieved August 6 2010,
  41. 41.
    Tomimori, E. K., Camaro, C. Y., Bisi, H., and Medeiros-Neto, G., Combined ultrasongraphic and cytological studies in the diagnosis of thyroid nodules. Biochimie 81:447–452, 1999.CrossRefGoogle Scholar
  42. 42.
    Kaus, M. R., Warfield, S. K., Jolesz, F. A., and Kikinis, R., Segmentation of Meningiomas and Low Grade Gliomas in MRI, International Conference on Medical Image Computing and Computer-Assisted Intervention, 1-10, 1999.Google Scholar
  43. 43.
    Samarasinghe, S., Neural Networks for Applied Sciences and Engineering, Auerbach Publications Boston, USA ISBN:084933375, 2006.Google Scholar
  44. 44.
    Leary, R. H., Rosen, J. B., and Jambeckz, P., An optimal structure-discriminative amino acid index for protein fold recognition. Biophys J 86:411–419, 2004.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Eystratios G. Keramidas
    • 1
    Email author
  • Dimitris Maroulis
    • 1
  • Dimitris K. Iakovidis
    • 2
  1. 1.Department of Informatics and TelecommunicationsUniversity of AthensAthensGreece
  2. 2.Department of Informatics and Computer TechnologyTechnological Educational Institute of LamiaLamiaGreece

Personalised recommendations