Advertisement

Classifying Cancer Grades Using Temporal Ultrasound for Transrectal Prostate Biopsy

  • Shekoofeh AziziEmail author
  • Farhad Imani
  • Jin Tae Kwak
  • Amir Tahmasebi
  • Sheng Xu
  • Pingkun Yan
  • Jochen Kruecker
  • Baris Turkbey
  • Peter Choyke
  • Peter Pinto
  • Bradford Wood
  • Parvin Mousavi
  • Purang Abolmaesumi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9900)

Abstract

We propose a cancer grading approach for transrectal ultrasound-guided prostate biopsy based on analysis of temporal ultrasound signals. Histopathological grading of prostate cancer reports the statistics of cancer distribution in a biopsy core. We propose a coarse-to-fine classification approach, similar to histopathology reporting, that uses statistical analysis and deep learning to determine the distribution of aggressive cancer in ultrasound image regions surrounding a biopsy target. Our approach consists of two steps; in the first step, we learn high-level latent features that maximally differentiate benign from cancerous tissue. In the second step, we model the statistical distribution of prostate cancer grades in the space of latent features. In a study with 197 biopsy cores from 132 subjects, our approach can effectively separate clinically significant disease from low-grade tumors and benign tissue. Further, we achieve the area under the curve of 0.8 for separating aggressive cancer from benign tissue in large tumors.

Keywords

Temporal ultrasound Cancer grading Deep belief network Gaussian mixture model 

References

  1. 1.
    Azizi, S., et al.: US-based detection of PCa using automatic feature selection with deep belief networks. In: MICCAI, pp. 70–77. Springer (2015)Google Scholar
  2. 2.
    Bell, A.J., Sejnowski, T.J.: The independent components of natural scenes are edge filters. Vis. Res. 37(23), 3327–3338 (1997)CrossRefGoogle Scholar
  3. 3.
    Correas, J.M., et al.: PCa: diagnostic performance of real-time shear-wave elastography. Radiology 275(1), 280–289 (2014)CrossRefGoogle Scholar
  4. 4.
    Daoud, M., et al.: Tissue classification using US-induced variations in acoustic backscattering features. IEEE TBME 60(2), 310–320 (2013)MathSciNetGoogle Scholar
  5. 5.
    Epstein, J.I., et al.: Upgrading and downgrading of PCa from biopsy to radical prostatectomy: incidence and predictive factors using the modified Gleason grading system and factoring in tertiary grades. Eur. Urol. 61(5), 1019–1024 (2012)CrossRefGoogle Scholar
  6. 6.
    Feleppa, E., et al.: Recent advances in ultrasonic tissue-type imaging of the prostate. In: Acoustical Imaging, pp. 331–339. Springer (2007)Google Scholar
  7. 7.
    Imani, F., et al.: US-based characterization of PCa using joint independent component analysis. IEEE TBME 62(7), 1796–1804 (2015)Google Scholar
  8. 8.
    Khojaste, A., et al.: Characterization of aggressive PCa using US RF time series. In: SPIE Med. Imaging, p. 94141A (2015)Google Scholar
  9. 9.
    Kuru, T.H., et al.: Critical evaluation of magnetic resonance imaging targeted, transrectal US guided transperineal fusion biopsy for detection of PCa. J. Urol. 190(4), 1380–1386 (2013)CrossRefGoogle Scholar
  10. 10.
    Llobet, R., et al.: Computer-aided detection of PCa. Int. J. Med. Inform. 76(7), 547–556 (2007)CrossRefGoogle Scholar
  11. 11.
    Nelson, E.D., et al.: Targeted biopsy of the prostate: the impact of color Doppler imaging and elastography on PCa detection and Gleason score. Urology 70(6), 1136–1140 (2007)CrossRefGoogle Scholar
  12. 12.
    de Rooij, M., et al.: Accuracy of multiparametric MRI for PCa detection: a meta-analysis. Am. J. Roentgenol. 202(2), 343–351 (2014)CrossRefGoogle Scholar
  13. 13.
    Siddiqui, M.M., et al.: Comparison of MR/US fusion-guided biopsy with US-guided biopsy for the diagnosis of PCa. JAMA 313(4), 390–397 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Vargas, H.A., et al.: Diffusion-weighted endorectal MRI at 3T for PCa: tumor detection and assessment of aggressiveness. Radiology 259(3), 775–784 (2011)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Xu, L., Jordan, M.I.: On convergence properties of the EM algorithm for Gaussian mixtures. Neural Comput. 8(1), 129–151 (1996)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Shekoofeh Azizi
    • 1
    Email author
  • Farhad Imani
    • 1
  • Jin Tae Kwak
    • 5
  • Amir Tahmasebi
    • 2
  • Sheng Xu
    • 3
  • Pingkun Yan
    • 2
  • Jochen Kruecker
    • 2
  • Baris Turkbey
    • 4
  • Peter Choyke
    • 4
  • Peter Pinto
    • 4
  • Bradford Wood
    • 3
  • Parvin Mousavi
    • 6
  • Purang Abolmaesumi
    • 1
  1. 1.The University of British ColumbiaVancouverCanada
  2. 2.Philips Research North AmericaBriarcliff ManorUSA
  3. 3.National Institutes of HealthBethesdaUSA
  4. 4.National Cancer InstituteBethesdaUSA
  5. 5.Sejong UniversityGwangjin-guSouth Korea
  6. 6.Queen’s UniversityKingstonCanada

Personalised recommendations