Advertisement

Diagnosis of Prostate Cancer with Support Vector Machine Using Multiwavelength Photoacoustic Images

  • Aniket BorkarEmail author
  • Saugata Sinha
  • Nikhil Dhengre
  • Bhargava Chinni
  • Vikram Dogra
  • Navalgund Rao
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1022)

Abstract

Photoacoustic (PA) imaging is an emerging soft tissue imaging modality which can be potentially used for the detection of prostate cancer. Computer-aided diagnosis tools help in further enhancing the detection process by assisting the physiologist in the interpretation of medical data. In this study, we aim to classify the malignant and nonmalignant prostate tissue using a support vector machine algorithm applied to the multiwavelength PA data obtained from human patients. The performance comparison between two feature sets, one consisting of multiwavelength PA image pixel values and the other consisting of chromophore concentration values are reported. While chromophore concentration values detected malignant prostate cancer more efficiently, the PA image pixels detected the nonmalignant prostate specimens with higher accuracy. This study shows that multiwavelength PA image data can be efficiently used with the support vector machine algorithm for prostate cancer detection.

Keywords

Photoacoustic imaging Prostate cancer Support vector machine 

References

  1. 1.
  2. 2.
  3. 3.
    Halpern, E.J.: Contrast-enhanced ultrasound imaging of prostate cancer. Rev. Urol. 8(Suppl 1), S29 (2006)MathSciNetGoogle Scholar
  4. 4.
    Presti Jr., J.C.: Prostate biopsy: current status and limitations. Rev. Urol. 9(3), 93 (2007)Google Scholar
  5. 5.
    Brock, M., von Bodman, C., Palisaar, R.J., Löppenberg, B., Sommerer, F., Deix, T., Noldus, J., Eggert, T.: The impact of real-time elastography guiding a systematic prostate biopsy to improve cancer detection rate: a prospective study of 353 patients. J. Urol. 187(6), 2039–2043 (2012)CrossRefGoogle Scholar
  6. 6.
    Yi, A., Kim, J.K., Park, S.H., Kim, K.W., Kim, H.S., Kim, J.H., Eun, H.W., Cho, K.S.: Contrast-enhanced sonography for prostate cancer detection in patients with indeterminate clinical findings. Am. J. Roentgenol. 186(5), 1431–1435 (2006)CrossRefGoogle Scholar
  7. 7.
    Beard, P.: Biomedical photoacoustic imaging. Interface Focus, pp. 602–631 (2011)Google Scholar
  8. 8.
    Valluru, K.S., Chinni, B.K., Rao, N.A., Bhatt, S., Dogra, V.S.: Basics and clinical applications of photoacoustic imaging. Ultrasound Clin. 4(3), 403–429 (2009)CrossRefGoogle Scholar
  9. 9.
    Wang, L.V.: Photoacoustic Imaging and Spectroscopy. CRC Press, Boca Raton (2009)Google Scholar
  10. 10.
    Hu, S., Wang, L.V.: Photoacoustic imaging and characterization of the microvasculature. J. Biomed. Opt. 15(1), 011101 (2010)CrossRefGoogle Scholar
  11. 11.
    Moradi, M., Abolmaesumi, P., Isotalo, P.A., Siemens, D.R., Sauerbrei, E.E., Mousavi, P.: Detection of prostate cancer from RF ultrasound echo signals using fractal analysis. In: 28th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, 2006. EMBS’06, pp. 2400–2403. IEEE (2006)Google Scholar
  12. 12.
    Reda, I., Shalaby, A., Khalifa, F., Elmogy, M., Aboulfotouh, A., El-Ghar, M.A., Hosseini-Asl, E., Werghi, N., Keynton, R., El-Baz, A.: Computer-aided diagnostic tool for early detection of prostate cancer. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2668–2672. IEEE (2016)Google Scholar
  13. 13.
    Lee, H.J., Hwang, S.I., Han, S.m., Park, S.H., Kim, S.H., Cho, J.Y., Seong, C.G., Choe, G.: Image-based clinical decision support for transrectal ultrasound in the diagnosis of prostate cancer: comparison of multiple logistic regression, artificial neural network, and support vector machine. Eur. Radiol. 20(6), 1476–1484 (2010)Google Scholar
  14. 14.
    Mohapatra, P., Chakravarty, S.: Modified PSO based feature selection for microarray data classification. In: Power, Communication and Information Technology Conference (PCITC), 2015 IEEE, pp. 703–709. IEEE (2015)Google Scholar
  15. 15.
    Botoca, C., Bardan, R., Botoca, M., Alexa, F.: Organ confinement of prostate cancer: neural networks assisted prediction. In: International Conference on Advancements of Medicine and Health Care through Technology, pp. 287–290. Springer (2009)Google Scholar
  16. 16.
    Albashish, D., Sahran, S., Abdullah, A., Adam, A., Shukor, N.A., Pauzi, S.H.M.: Multi-scoring feature selection method based on SVM-RFE for prostate cancer diagnosis. In: 2015 International Conference on Electrical Engineering and Informatics (ICEEI), pp. 682–686. IEEE (2015)Google Scholar
  17. 17.
    Chiu, J.S., Wang, Y.F., Su, Y.C., Wei, L.H., Liao, J.G., Li, Y.C.: Artificial neural network to predict skeletal metastasis in patients with prostate cancer. J. Med. Syst. 33(2), 91 (2009)CrossRefGoogle Scholar
  18. 18.
    Chang, C.Y., Hu, H.Y., Tsai, Y.S.: Prostate cancer detection in dynamic MRIs. In: 2015 IEEE International Conference on Digital Signal Processing (DSP), pp. 1279–1282. IEEE (2015)Google Scholar
  19. 19.
    Çinar, M., Engin, M., Engin, E.Z., Atesçi, Y.Z.: Early prostate cancer diagnosis by using artificial neural networks and support vector machines. Expert Syst. Appl. 36(3), 6357–6361 (2009)CrossRefGoogle Scholar
  20. 20.
    Sinha, S., Rao, N.A., Chinni, B.K., Dogra, V.S.: Evaluation of frequency domain analysis of a multiwavelength photoacoustic signal for differentiating malignant from benign and normal prostates: ex vivo study with human prostates. J. Ultrasound Med. 35(10), 2165–2177 (2016)CrossRefGoogle Scholar
  21. 21.
    Sinha, S., Rao, N., Chinni, B., Moalem, J., Giampolli, E., Dogra, V.: Differentiation between malignant and normal human thyroid tissue using frequency analysis of multispectral photoacoustic images. In: 2013 IEEE on Image Processing Workshop (WNYIPW), Western New York, pp. 5–8. IEEE (2013)Google Scholar
  22. 22.
    Sinha, S., Rao, N.A., Valluru, K.S., Chinni, B.K., Dogra, V.S., Helguera, M.: Frequency analysis of multispectral photoacoustic images for differentiating malignant region from normal region in excised human prostate. In: Medical Imaging 2014: Ultrasonic Imaging and Tomography, vol. 9040, p. 90400P. International Society for Optics and Photonics (2014)Google Scholar
  23. 23.
    Dogra, V.S., Chinni, B.K., Valluru, K.S., Joseph, J.V., Ghazi, A., Yao, J.L., Evans, K., Messing, E.M., Rao, N.A.: Multispectral photoacoustic imaging of prostate cancer: preliminary ex-vivo results. J. Clin. Imaging Sci. 3 (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Aniket Borkar
    • 1
    Email author
  • Saugata Sinha
    • 1
  • Nikhil Dhengre
    • 1
  • Bhargava Chinni
    • 2
  • Vikram Dogra
    • 2
  • Navalgund Rao
    • 2
  1. 1.Department of Electronics and Communication EngineeringVisvesvaraya National Institute of TechnologyNagpurIndia
  2. 2.Department of Imaging ScienceUniversity of Rochester Medical CenterRochesterUSA

Personalised recommendations