Advertisement

Breast tumor classification using different features of quantitative ultrasound parametric images

  • Soa-Min Hsu
  • Wen-Hung Kuo
  • Fang-Chuan Kuo
  • Yin-Yin LiaoEmail author
Original Article
  • 42 Downloads

Abstract

Rationale and objectives

The ultrasound B-mode-based morphological and texture analysis and Nakagami parametric imaging have been proposed to characterize breast tumors. Since these three feature categories of ultrasonic tissue characterization supply information on different physical characteristics of breast tumors, by combining the above methods is expected to provide more clues for classifying breast tumors.

Materials and methods

To verify the validity of the concept, raw data were obtained from 160 clinical cases. Six different types of morphological-feature parameters, four texture features, and the Nakagami parameter of benignancy and malignancy were extracted for evaluation. The Pearson’s correlation matrix was used to calculate the correlation between different feature parameters. The fuzzy c-means clustering and stepwise regression techniques were utilized to determine the optimal feature set, respectively. The logistic regression, receiver operating characteristic curve, and support vector machine were used to estimate the diagnostic ability.

Results

The best performance was obtained by combining morphological-feature parameter (e.g., standard deviation of the shortest distance), texture feature (e.g., variance), and the Nakagami parameter, with an accuracy of 89.4%, a specificity of 86.3%, a sensitivity of 92.5%, and an area under receiver operating characteristic curve of 0.96. There was no significant difference between using fuzzy c-means clustering, logistic regression, and support vector machine based on the optimal feature set for breast tumors classification.

Conclusion

Therefore, we verified that different physical ultrasonic features are functionally complementary and thus improve the performance in diagnosing breast tumors. Moreover, the optimal feature set had the maximum discriminating performance should be irrelative to the power of classifiers.

Keywords

Breast ultrasound Morphological features Texture features Nakagami parameter Classification 

Notes

Acknowledgements

This work was supported by grants from the National Tsing Hua University (100N2053E1) and the Hungkuang University and Kuang Tien General Hospital (HK-KTOH-105-04). This study was performed in accordance with the Helsinki Declaration and Good Clinical Practice.

Compliance with ethical standards

Conflict of interest

The authors declare no competing financial interests.

References

  1. 1.
    Sehgal CM, Weinstein SP, Arger PH, Conant EF (2006) A review of breast ultrasound. J Mammary Gland Biol Neoplasia 11(2):113–123Google Scholar
  2. 2.
    Kolb TM, Lichy J, Newhouse JH (2002) Newhouse, comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: an analysis of 27,825 patient evaluations. Radiology 225(1):165–175Google Scholar
  3. 3.
    Stavros AT, Thickman D, Rapp CL, Dennis MA, Parker SH, Sisney GA (1995) Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. Radiology 196(1):123–134Google Scholar
  4. 4.
    Joo S, Yang YS, Moon WK, Kim HC (2004) Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features. IEEE Trans Med Imaging 23(10):1292–1300Google Scholar
  5. 5.
    Cheng HD, Shan J, Ju W, Guo Y, Zhang L (2010) Automated breast cancer detection and classification using ultrasound images: a survey. Pattern Recognit 43(1):299–317Google Scholar
  6. 6.
    Moon WK, Lo CM, Cho N, Chang JM, Huang CS, Chen JH, Chang RF (2013) Computer-aided diagnosis of breast masses using quantified BI-RADS findings. Comput Methods Programs Biomed 111(1):84–92Google Scholar
  7. 7.
    Huang Q, Luo Y, Zhang Q (2017) Breast ultrasound image segmentation: a survey. Int J Comput Assist Radiol Surg 12(3):493–507Google Scholar
  8. 8.
    Rahbar G, Sie AC, Hansen GC, Prince JS, Melany ML, Reynolds HE, Jackson VP, Sayre JW, Bassett LW (1999) Benign versus malignant solid breast masses: US differentiation. Radiology 213(3):889–894Google Scholar
  9. 9.
    Chen DR, Chien CL, Kuo YF (2015) Computer-aided assessment of tumor grade for breast cancer in ultrasound images. Comput Math Methods Med 2015:914091Google Scholar
  10. 10.
    Chou YH, Tiu CM, Hung GS, Wu SC, Chang TY, Chiang HK (2001) Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis. Ultrasound Med Biol 27(11):1493–1498Google Scholar
  11. 11.
    Alvarenga AV, Infantosi AF, Pereira WC, Azevedo CM (2012) Assessing the combined performance of texture and morphological parameters in distinguishing breast tumors in ultrasound images. Med Phys 39(12):7350–7358Google Scholar
  12. 12.
    Haralick RM, Shanugam K, Dinstein I (1973) Texture features for image classification. IEEE Trans Syst Man Cybernet SMC 3(6):610–621Google Scholar
  13. 13.
    Garra BS, Krasner BH, Horii SC, Ascher S, Mun SK, Zeman RK (1993) Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysi. Ultrason Imaging 15(4):267–285Google Scholar
  14. 14.
    Sivaramakrishna R, Powell KA, Lieber ML, Chilcote WA, Shekhar R (2002) Texture analysis of lesions in breast ultrasound images. Comput Med Imaging Graph 26(5):303–307Google Scholar
  15. 15.
    Chen DR, Chang RF, Kuo WJ, Chen MC, Huang YL (2002) Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound Med Biol 28(10):1301–1310Google Scholar
  16. 16.
    Chen SJ, Cheng KS, Dai YC, Sun YN, Chen YT, Chang KY, Hsu WC, Chang TW (2005) The representations of sonographic image texture for breast cancer using co-occurrence matrix. J Med Biol Eng 25(4):193–199Google Scholar
  17. 17.
    Wu WJ, Moon WK (2008) Ultrasound breast tumor image computer-aided diagnosis with texture and morphological features. Acad Radiol 15(7):873–880Google Scholar
  18. 18.
    Thijssen JM (1989) Ultrasonic tissue characterization and echographic imaging. Phys Med Biol 34(11):1667–1674Google Scholar
  19. 19.
    Insana MF, Wagner RF, Brown DG, Hall TJ (1990) Describing small-scale structure in random media using pulse-echo ultrasound. J Acoust Soc Am 87(1):179–192Google Scholar
  20. 20.
    Shankar PM, Reid JM, Ortega H, Piccoli CW, Goldberg BB (1993) Use of non-Rayleigh statistics for the identification of tumors in ultrasonic B-scans of the breast. IEEE Trans Med Imaging 12(4):687–692Google Scholar
  21. 21.
    Shankar PM, Dumane VA, Reid JM, Genis V, Forsberg F, Piccoli CW, Goldberg BB (2001) Classification of ultrasonic B-mode images of breast masses using Nakagami distribution. IEEE Trans Ultrason Ferroelectr Freq Control 48(2):569–580Google Scholar
  22. 22.
    Tsui PH, Wang SH, Huang CC, Chiu CY (2005) Quantitative analysis of noise influence on the detection of scatterer concentration by Nakagami parameter. J Med Biol Eng 25(2):45–51Google Scholar
  23. 23.
    Tsui PH, Yeh CK, Chang CC, Liao YY (2008) Classification of breast masses by ultrasonic Nakagami imaging: a feasibility study. Phys Med Biol 53(21):6027–6044Google Scholar
  24. 24.
    Tsui PH, Liao YY, Chang CC, Kuo WH, Chang KJ, Yeh CK (2010) Classification of benign and malignant breast tumors by 2-d analysis based on contour description and scatterer characterization. IEEE Trans Med Imaging 29(2):513–522Google Scholar
  25. 25.
    Liao YY, Tsui PH, Li CH, Chang KJ, Kuo WH, Chang CC, Yeh CK (2011) Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images. Med Phys 38(4):2198–2207Google Scholar
  26. 26.
    Aldrich J (1995) Correlations genuine and spurious in pearson and yule. Statist Sci 10(4):364–376Google Scholar
  27. 27.
    Bezdek JC, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203Google Scholar
  28. 28.
    Schaefer G, Závišek M, Nakashima T (2009) Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recognit 42(6):1133–1137Google Scholar
  29. 29.
    Draper N, Smith H (1981) Applied regression analysis. Wiley, New YorkGoogle Scholar
  30. 30.
    Sahiner B, Chan HP, Roubidoux MA, Hadjiiski LM, Helvie MA, Paramagul C, Bailey J, Nees AV, Blane C (2007) Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy. Radiology 242(3):716–724Google Scholar
  31. 31.
    Tsui PH, Chang CC (2007) Imaging local scatterer concentrations by the Nakagami statistical model. Ultrasound Med Biol 33(4):608–619Google Scholar
  32. 32.
    Soh LK, Tsatsoulis C (1999) Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sensing 37(2):780–795Google Scholar
  33. 33.
    Liao YY, Wu JC, Li CH, Yeh CK (2011) Texture feature analysis for breast ultrasound image enhancement. Ultrason Imaging 33(4):264–278Google Scholar
  34. 34.
    Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36Google Scholar
  35. 35.
    Huang YL, Chen DR (2005) Support vector machines in sonography application to decision making in the diagnosis of breast cancer. Clin Imaging 29(3):179–184Google Scholar
  36. 36.
    Hendrix MJ, Seftor EA, Kirschmann DA, Seftor RE (2000) Molecular biology of breast cancer metastasis: molecular expression of vascular markers by aggressive breast cancer cells. Breast Cancer Res 2(6):417–422Google Scholar
  37. 37.
    Chen CY, Chiou HJ, Chou SY, Chiou SY, Wang HK, Chou YH, Chiang HK (2009) Computer-aided diagnosis of soft-tissue tumors using sonographic morphologic and texture features. Acad Radiol 16(12):1531–1538Google Scholar
  38. 38.
    Chang RF, Wu WJ, Moon WK, Chen DR (2005) Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Res Treat 89(2):179–185Google Scholar
  39. 39.
    Gómez W, Leija L, Alvarenga AV, Infantosi AF, Pereira WC (2010) Computerized lesion segmentation of breast ultrasound based on marker-controlled watershed transformation. Med Phys 37(1):82–95Google Scholar
  40. 40.
    Dash M, Liu H (1997) Feature selection for classification. Intell Data Anal 1(3):131–156Google Scholar
  41. 41.
    Balleyguier C, Ciolovan L, Ammari S, Canale S, Sethom S, Al Rouhbane R, Vielh P, Dromain C (2013) Breast elastography: the technical process and its applications. Diagn Interv Imaging 94(5):503–513Google Scholar
  42. 42.
    Klotz T, Boussion V, Kwiatkowski F, Dieu-de Fraissinette V, Bailly-Glatre A, Lemery S, Boyer L (2014) Shear wave elastography contribution in ultrasound diagnosis management of breast lesions. Diagn Interv Imaging 95(9):813–824Google Scholar
  43. 43.
    Skerl K, Cochran S, Evans A (2017) First step to facilitate long-term and multi-centre studies of shear wave elastography in solid breast lesions using a computer-assisted algorithm. Int J Comput Assist Radiol Surg 12(9):1533–1542Google Scholar
  44. 44.
    Lo CM, Lai YC, Chou YH, Chang RF (2015) Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging. Comput Methods Programs Biomed 122(3):354–361Google Scholar

Copyright information

© CARS 2019

Authors and Affiliations

  1. 1.Department of RadiologyKuang Tien General HospitalTaichungTaiwan
  2. 2.Department of SurgeryNational Taiwan University HospitalTaipeiTaiwan
  3. 3.Department of Physical TherapyHungkuang UniversityTaichungTaiwan
  4. 4.Department of Biomedical EngineeringHungkuang UniversityTaichungTaiwan, ROC

Personalised recommendations