Prostate Cancer Detection Using Image-Based Features in Dynamic Contrast Enhanced MRI

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12722)


Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE MRI) provides valuable information in prostate cancer detection. Existing computer-aided detection methods focus on estimating the DCE curves as pharmacokinetic models and directly calculating the perfusion-related measurements from the DCE signals. Substantial image content contained in DCE MRI series, which captures the spatio-temporal pattern receives less attention. This work aims to investigate the performance of the image-based features extracted from DCE MRI on prostate cancer detection. Various image-based features are extracted from DCE MRI series. Their performance on prostate cancer detection is compared with features extracted from the pharmacokinetic models and the perfusion-related measurements. Features are concatenated and feature selection is applied to reduce the feature dimensionality and improve cancer detection performance. Evaluation is based on a publicly available dataset. Using image-based features outperforms using either the features extracted from the pharmacokinetic models or the perfusion-related measurements. By applying feature selection to the aggregation of all features, the performance of prostate cancer detection achieves 0.821, for the area under the receiver operating characteristics curve. This study demonstrates that compared with the commonly used pharmacokinetic models and the perfusion-related features, image-based features provide an additional contribution to prostate cancer detection and can potentially be used as an alternative approach to model DCE MRI.


Prostate cancer detection Image-based features DCE MRI 


  1. 1.
    Siegel, R., Ma, J., Zou, Z., Jemal, A.: Cancer statistics. CA: Can. J. Clin. 64(1), 9–29 (2014)Google Scholar
  2. 2.
    Siegel, R., Naishadham, D., Jemal, A.: Cancer statistics. CA: Can. J. Clin. 63(1), 11–30 (2013)Google Scholar
  3. 3.
    Chou, R., Croswell, J.M., Dana, T., et al.: Screening for prostate cancer: a review of the evidence for the US preventive services task force. Ann. Internal Med. 155(11), 762–771 (2011)CrossRefGoogle Scholar
  4. 4.
    Hricak, H., Dooms, G.C., McNeal, J.E., et al.: MR imaging of the prostate gland: normal anatomy. Am. J. Roentgenol. 148(1), 51–58 (1987)CrossRefGoogle Scholar
  5. 5.
    Barentsz, J.O., Richenberg, J., Clements, R., et al.: ESUR prostate MR guidelines 2012. Eur. Radiol. 22(4), 746–757 (2012)CrossRefGoogle Scholar
  6. 6.
    Weinreb, J.C., Barentsz, J.O., Choyke, P.L., et al.: 2016. PI-RADS prostate imaging-reporting and data system: 2015, version 2. Eur. Urol. 69(1), 16–40 (2016)Google Scholar
  7. 7.
    Moore, C.M., Ridout, A., Emberton, M.: The role of MRI in active surveillance of prostate cancer. Curr. Opin. Urol. 23(3), 261–267 (2013)CrossRefGoogle Scholar
  8. 8.
    Kim, C.K., Park, B.K., Kim, B.: Localization of prostate cancer using 3T MRI: comparison of T2-weighted and dynamic contrast-enhanced imaging. J. Comput. Assist. Tomogr. 30(1), 7–11 (2006)Google Scholar
  9. 9.
    Khalifa, F., Soliman, A., El-Baz, A., et al.: Models and methods for analyzing DCE-MRI: A review. Med. Phys. 41, 124301 (2014)Google Scholar
  10. 10.
    Sung, Y.S., Kwon, H.J., Park, B.W., et al.: Prostate cancer detection on dynamic contrast-enhanced MRI: computer-aided diagnosis versus single perfusion parameter maps. Am. J. Roentgenol. 197(5), 1122–1129 (2011)Google Scholar
  11. 11.
    Brix, G., Semmler, W., Port, R., Schad, L.R., Layer, G., Lorenz, W.J.: Pharmacokinetic parameters in CNS Gd-DTPA enhanced MR imaging. J. Comput. Assis. Tomogr. 15(4), 621–628 (1991)Google Scholar
  12. 12.
    Tofts, P.S., Kermode, A.G.: Measurement of the blood-brain barrier permeability and leakage space using dynamic MR imaging. 1. Fundamental concepts. Magn. Reson. Med. 17(2), 357–367 (1991)Google Scholar
  13. 13.
    Hoffmann, U., Brix, G., Knopp, M.V., et al.: Pharmacokinetic mapping of the breast: a new method for dynamic MR mammography. Magn. Reson. Med. 33(4), 506–514 (1995)Google Scholar
  14. 14.
    Gliozzi, A.S., Mazzetti, S., Delsanto, P.P., Regge, D., Stasi, M.: Phenomenological universalities: a novel tool for the analysis of dynamic contrast enhancement in magnetic resonance imaging. Phys. Med. Biol. 56(3), 573 (2011)CrossRefGoogle Scholar
  15. 15.
    Rampun, A., Zheng, L., Malcolm, P., Tiddeman, B., Zwiggelaar, R.: Computer-aided detection of prostate cancer in T2-weighted MRI within the peripheral zone. Phys. Med. Biol. 61(13), 4796–4825 (2016)CrossRefGoogle Scholar
  16. 16.
    Trigui, R., Mitéran, J., Walker, P.M., Sellami, L., Hamida, A.B.: Automatic classification and localization of prostate cancer using multi-parametric MRI/MRS. Biomed. Sig. Process. Control 31, 189–198 (2017)CrossRefGoogle Scholar
  17. 17.
    Niaf, E., Rouvière, O., Mège-Lechevallier, F., Bratan, F., Lartizien, C.: Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys. Med. Biol. 57(12), 3833 (2012)Google Scholar
  18. 18.
    Lemaître, G.: Computer-Aided Diagnosis for Prostate Cancer using Multi-Parametric Magnetic Resonance Imaging. Doctoral dissertation 2016, Universite de Bourgogne, Universitat de Girona, pp. 109–116 (2016)Google Scholar
  19. 19.
    Cover, T.M.: Elements of Information Theory, pp. 12–23. Wiley, New Delhi (2006)Google Scholar
  20. 20.
    Kybic, J., Thévenaz, P., Unser, M.: Multiresolution spline warping for EPI registration. In: Proceedings of the SPIE: Mathematical Imaging-Wavelet Applications in Signal and Image Processing 1999, Denver, Colorado, vol. 3813, pp. 571–579 (1999)Google Scholar
  21. 21.
    Scharr, H.: Optimal operators in digital image processing. Doctoral dissertation 2000. Repertus Carola University, Heidelberg, Germany (2000)Google Scholar
  22. 22.
    Kirsch, R.A.: Computer determination of the constituent structure of biological images. Comput. Biomed. Res. 4(3), 315–328 (1971)Google Scholar
  23. 23.
    Kovesi, P.: Image features from phase congruency. Videre: J. Comput. Vis. Res. 1(3), 1–26 (1999)Google Scholar
  24. 24.
    Gabor, D.: Theory of communication. Part 1: The analysis of information. J. Inst. Electr. Eng. Part III: Radio Commun. Eng. 93(26), 429–441 (1946)Google Scholar
  25. 25.
    Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recogn. 29(1), 51–59 (1996)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.School of Information Science and EngineeringShandong Normal UniversityJinanChina
  2. 2.School of Medicine, Department of Infection, Immunity and Cardiovascular DiseaseSheffield UniversitySheffieldUK
  3. 3.Department of Computer ScienceAberystwyth UniversityAberystwythUK

Personalised recommendations