Skip to main content

Advertisement

SpringerLink
Log in

Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose To improve the computer-aided diagnosis of breast lesions, by designing a pattern recognition system (PR-system) on commercial graphics processing unit (GPU) cards using parallel programming and textural information from multimodality imaging.

Material and methods Patients with histologically verified breast lesions underwent both ultrasound (US) and digital mammography (DM), lesions were outlined on the images by an experienced radiologist, and textural features were calculated. The PR-system was designed to provide highest possible precision by programming in parallel the multiprocessors of the NVIDIA’s GPU cards, GeForce 8800GT or 580GTX, and using the CUDA programming framework and C++. The PR-system was built around the probabilistic neural network classifier, and its performance was evaluated by a re-substitution method, for estimating the system’s highest accuracy, and by the external cross-validation method, for assessing the PR-system’s unbiased accuracy to new, “unseen” by the system, data.

Results Classification accuracies for discriminating malignant from benign lesions were as follows: 85.5 % using US-features alone, 82.3 % employing DM features alone, and 93.5 % combining US and DM features. Mean accuracy to new “unseen” data for the combined US and DM features was 81 %. Those classification accuracies were about 10 % higher than accuracies achieved on a single CPU, using sequential programming methods, and 150-fold faster.

Conclusion The proposed PR-system improves breast-lesion discrimination accuracy, it may be redesigned on site when new verified data are incorporated in its depository, and it may serve as a second opinion tool in a clinical environment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Laine HR, Tukeva T, Mikkola P et al (1996) Assessment of mammography and ultrasound examination in the diagnosis of breast cancer. Eur J Ultrasound 3(1):9–14

    Article  Google Scholar 

  2. Tang J, Rangayyan RM, Xu J et al (2009) Computer-aided detection and diagnosis of breast cancer with mammography: recent advances. IEEE Trans Inf Technol Biomed 13(2):236–251

    Article  PubMed  Google Scholar 

  3. Humphrey LL, Helfand M, Chan BK et al (2002) Breast cancer screening: a summary of the evidence for the U.S. Preventive Services Task Force. Ann Intern Med 137((5 Part 1)):347–360

    Article  PubMed  Google Scholar 

  4. Majid AS, de Paredes ES, Doherty RD et al (2003) Missed breast carcinoma: pitfalls and pearls. Radiographics 23(4):881–895

    Article  PubMed  Google Scholar 

  5. Wang X, Lederman D, Tan J et al (2010) Computerized detection of breast tissue asymmetry depicted on bilateral mammograms: a preliminary study of breast risk stratification. Acad Radiol 17(10):1234–1241

    Article  PubMed  Google Scholar 

  6. Farber R (2011) CUDA application design and development. Morgan Kaufmann, Los Altos, CA

  7. Evers K (2001) Diagnostic breast imaging. Am J Roentgenol 177(5):1094

    Article  Google Scholar 

  8. Harms SE (1999) Technical report of the international working group on breast MRI. J Magn Reson Imaging 10(6):979

    Article  PubMed  Google Scholar 

  9. Bird RE, Wallace TW, Yankaskas BC (1992) Analysis of cancers missed at screening mammography. Radiology 184(3):613–617

    PubMed  CAS  Google Scholar 

  10. Beam CA, Layde PM, Sullivan DC (1996) Variability in the interpretation of screening mammograms by US radiologists. Findings from a national sample. Arch Intern Med 156(2):209–213

    Article  PubMed  CAS  Google Scholar 

  11. Sardanelli F, Podo F, D’Agnolo G et al (2007) Multicenter comparative multimodality surveillance of women at genetic-familial high risk for breast cancer (HIBCRIT study): interim results. Radiology 242(3):698–715

    Article  PubMed  Google Scholar 

  12. Lee JM, Halpern EF, Rafferty EA et al (2009) Evaluating the correlation between film mammography and MRI for screening women with increased breast cancer risk. Acad Radiol 16(11):1323–1328

    Article  PubMed  Google Scholar 

  13. Houssami N, Ciatto S (2011) The evolving role of new imaging methods in breast screening. Prev Med 53(3):123–126

    Article  PubMed  Google Scholar 

  14. Malvindi MA, Greco A, Conversano F et al (2011) Magnetic/silica nanocomposites as dual-mode contrast agents for combined magnetic resonance imaging and ultrasonography. Adv Funct Mater 21(13):2548–2555

    Article  CAS  Google Scholar 

  15. Soloperto G, Conversano F, Greco A et al (2012) Advanced spectral analyses for real-time automatic echographic tissue-typing of simulated tumor masses at different compression stages. IEEE Trans Ultrason Ferroelectr Freq Control 59(12):2692–2701

    Article  PubMed  Google Scholar 

  16. Yuan Y, Giger ML, Li H et al (2010) Multimodality computer-aided breast cancer diagnosis with FFDM and DCE-MRI. Acad Radiol 17(9):1158–1167

    Article  PubMed  Google Scholar 

  17. Drukker K, Horsch K, Giger ML (2005) Multimodality computerized diagnosis of breast lesions using mammography and sonography. Acad Radiol 12(8):970–979

    Article  PubMed  Google Scholar 

  18. Sahiner B, Chan HP, Hadjiiski LM et al (2009) Multi-modality CADx: ROC study of the effect on radiologists’ accuracy in characterizing breast masses on mammograms and 3D ultrasound images. Acad Radiol 16(7):810–818

    Article  PubMed  Google Scholar 

  19. Horsch K, Giger ML, Vyborny CJ et al (2006) Classification of breast lesions with multimodality computer-aided diagnosis: observer study results on an independent clinical data set. Radiology 240(2):357–368

    Article  PubMed  Google Scholar 

  20. Theodoridis S, Koutroumbas K (2008) Pattern recognition, 4th edn. Academic Press, San Diego

    Google Scholar 

  21. Xu F, Mueller K (2007) Real-time 3D computed tomographic reconstruction using commodity graphics hardware. Phys Med Biol 52(12):3405–3419

    Article  PubMed  Google Scholar 

  22. Ruiz A, Sertel O, Ujaldon M et al (2009) Stroma classification for neuroblastoma on graphics processors. Int J Data Min Bioinform 3(3):280–298

    Article  PubMed  Google Scholar 

  23. Lapeer RJ, Shah SK, Rowland RS (2010) An optimised radial basis function algorithm for fast non-rigid registration of medical images. Comput Biol Med 40(1):1–7

    Article  PubMed  CAS  Google Scholar 

  24. Shams R, Sadeghi P, Kennedy R et al (2010) Parallel computation of mutual information on the GPU with application to real-time registration of 3D medical images. Comput Methods Programs Biomed 99(2):133–146

    Article  PubMed  Google Scholar 

  25. Dai Y, Tian J, Dong D et al (2010) Real-time visualized freehand 3D ultrasound reconstruction based on GPU. IEEE Trans Inf Technol Biomed 14(6):1338–1345

    Article  PubMed  Google Scholar 

  26. Sidiropoulos K, Glotsos D, Kostopoulos S et al (2012) Real time decision support system for diagnosis of rare cancers, trained in parallel, on a graphics processing unit. Comput Biol Med 42(4):376–386

    Article  PubMed  Google Scholar 

  27. Kirk DB, W-mW Hwu (2010) Programming massively parallel processors: a hands-on approach. Morgan Kaufmann, Amsterdam

    Google Scholar 

  28. BI-RADS Breast Imaging Reporting and Data System Breast Imaging Atlas (2003) American College of Radiology. Reston, VA

  29. Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Sys Man Cyb 3:610–621

    Article  Google Scholar 

  30. Galloway MM (1975) Texture analysis using gray-level run lengths. Comput Graph Image Process 4:172–179

    Article  Google Scholar 

  31. Gose E, Johnsonbaugh R, Jost S (1996) Pattern recognition and image analysis. Prentice Hall PTR, New Jersey

    Google Scholar 

  32. Gonzalez R, Woods R (2002) Digital image processing. 2nd edn. Addison-Wesley Pub, NY

  33. Specht DF (1990) Probabilistic neural networks. Neural Netw 3:109–118

    Article  Google Scholar 

  34. Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley, Hoboken, NJ

    Book  Google Scholar 

  35. Kecman V (2001) Learning and soft computing: Support vector machines, Neural Networks, and Fuzzy logic models. MIT Press, Cambridge, pp 121–184

  36. Gunal S, Gerek ON, Ece DG et al (2009) The search for optimal feature set in power quality event classification. Expert Syst Appl 36(7):10266–10273

    Article  Google Scholar 

  37. Ambroise C, McLachlan GJ (2002) Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci USA 99(10):6562–6566

    Article  PubMed  CAS  Google Scholar 

  38. Romero E, Sopena JM (2008) Performing feature selection with multilayer perceptrons. IEEE Trans Neural Netw 19(3):431–441

    Article  PubMed  Google Scholar 

  39. Ahmed N, Rao KR (1975) Orthogonal transforms for digital signal processing. Springer, Berlin

    Book  Google Scholar 

  40. Oh K-S, Jung K (2004) GPU implementation of neural networks. Pattern Recognit 37(6):1311–1314

    Article  Google Scholar 

  41. Beliakov G, Li G (2012) Improving the speed and stability of the k-nearest neighbors method. Pattern Recognit Lett 33(10):1296–1301

    Article  Google Scholar 

  42. Pang WM, Qin J, Lu Y et al (2011) Accelerating simultaneous algebraic reconstruction technique with motion compensation using CUDA-enabled GPU. Int J Comput Assist Radiol Surg 6(2):187–199

    Article  PubMed  Google Scholar 

  43. Santhanam AP, Min Y, Neelakkantan H et al (2012) A multi-GPU real-time dose simulation software framework for lung radiotherapy. Int J Comput Assist Radiol Surg 7(5):705–719

    Article  PubMed  CAS  Google Scholar 

  44. Foley D (1972) Considerations of sample and feature size. IEEE Trans Inf Theory 18(5):618–626

    Article  Google Scholar 

  45. Karahaliou AN, Boniatis IS, Skiadopoulos SG et al (2008) Breast cancer diagnosis: analyzing texture of tissue surrounding microcalcifications. IEEE Trans Inf Technol Biomed 12(6):731–738

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

The first author was supported by a grant from the Greek State Scholarships Foundation (IKY).

Conflict of interest

None.

Author information

Authors and Affiliations

  1. School of Engineering and Design, Brunel University West London, Uxbridge, Middlesex, UB8 3PH, UK

    Konstantinos P. Sidiropoulos & John T. Stonham

  2. Medical Image and Signal Processing (medisp) Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Egaleo, 122 10, Athens, Greece

    Spiros A. Kostopoulos, Dimitris T. Glotsos, Emmanouil I. Athanasiadis & Dionisis A. Cavouras

  3. Delta Digital Diagnostic Center, Semitelou 6, 11528 , Athens, Greece

    Nikos D. Dimitropoulos

Authors
  1. Konstantinos P. Sidiropoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Spiros A. Kostopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dimitris T. Glotsos
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Emmanouil I. Athanasiadis
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nikos D. Dimitropoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. John T. Stonham
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Dionisis A. Cavouras
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dionisis A. Cavouras.

Appendices

Appendix A

See Tables 9 and 10.

Table 9 GPU specifications
Full size table
Table 10 List of textural features employed in the current study for DM and US
Full size table

Appendix B

figure a1

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sidiropoulos, K.P., Kostopoulos, S.A., Glotsos, D.T. et al. Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images. Int J CARS 8, 547–560 (2013). https://doi.org/10.1007/s11548-013-0813-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-013-0813-y

Keywords

Search

Navigation