Advertisement

Learning from Noisy Label Statistics: Detecting High Grade Prostate Cancer in Ultrasound Guided Biopsy

  • Shekoofeh AziziEmail author
  • Pingkun Yan
  • Amir Tahmasebi
  • Peter Pinto
  • Bradford Wood
  • Jin Tae Kwak
  • Sheng Xu
  • Baris Turkbey
  • Peter Choyke
  • Parvin Mousavi
  • Purang Abolmaesumi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11073)

Abstract

The ubiquity of noise is an important issue for building computer-aided diagnosis models for prostate cancer biopsy guidance where the histopathology data is sparse and not finely annotated. We propose a solution to alleviate this challenge as a part of Temporal Enhanced Ultrasound (TeUS)-based prostate cancer biopsy guidance method. Specifically, we embed the prior knowledge from the histopathology as the soft labels in a two-stage model, to leverage the problem of diverse label noise in the ground-truth. We then use this information to accurately detect the grade of cancer and also to estimate the length of cancer in the target. Additionally, we create a Bayesian probabilistic version of our network, which allows evaluation of model uncertainty that can lead to any possible misguidance during the biopsy procedure. In an in vivo study with 155 patients, we analyze data from 250 suspicious cancer foci obtained during fusion biopsy. We achieve the average area under the curve of 0.84 for cancer grading and mean squared error of 0.12 in the estimation of tumor in biopsy core length.

Keywords

Temporal enhanced ultrasound Prostate cancer Recurrent neural networks 

References

  1. 1.
    Ahmed, H.U., et al.: Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS). Lancet 389(10071), 815–822 (2017)CrossRefGoogle Scholar
  2. 2.
    Azizi, S., Bayat, S., Abolmaesumi, P., Mousavi, P., et al.: Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations. IJCARS 12(8), 1293–1305 (2017)Google Scholar
  3. 3.
    Azizi, S., et al.: Classifying cancer grades using temporal ultrasound for transrectal prostate biopsy. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 653–661. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46720-7_76CrossRefGoogle Scholar
  4. 4.
    Azizi, S., Mousavi, P., et al.: Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study. Int. J. CARS 11, 947 (2016).  https://doi.org/10.1007/s11548-016-1395-2CrossRefGoogle Scholar
  5. 5.
    Azizi, S., et al.: Ultrasound-based detection of prostate cancer using automatic feature selection with deep belief networks. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 70–77. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24571-3_9CrossRefGoogle Scholar
  6. 6.
    Bayat, S., Azizi, S., Daoud, M., et al.: Investigation of physical phenomena underlying temporal enhanced ultrasound as a new diagnostic imaging technique: theory and simulations. IEEE Trans. UFFC 65(3), 400–410 (2017)CrossRefGoogle Scholar
  7. 7.
    Feleppa, E., Porter, C., Ketterling, J., Dasgupta, S., Ramachandran, S., Sparks, D.: Recent advances in ultrasonic tissue-type imaging of the prostate. In: André, M.P. (ed.) Acoustical imaging, vol. 28, pp. 331–339. Springer, Dordrecht (2007).  https://doi.org/10.1007/1-4020-5721-0_35CrossRefGoogle Scholar
  8. 8.
    Frénay, B., Verleysen, M.: Classification in the presence of label noise. IEEE Trans. Neural Netw. Learn. Syst. 25(5), 845–869 (2014)CrossRefGoogle Scholar
  9. 9.
    Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Machine Learning, pp. 1050–1059 (2016)Google Scholar
  10. 10.
    Kasivisvanathan, V.: Prostate evaluation for clinically important disease: Sampling using image-guidance or not? (PRECISION). Eur. Urol. Suppl. 17(2), e1716–e1717 (2018)CrossRefGoogle Scholar
  11. 11.
    Llobet, R., Pérez-Cortés, J.C., Toselli, A.H.: Computer-aided detection of prostate cancer. Int. J. Med. Inf. 76(7), 547–556 (2007)CrossRefGoogle Scholar
  12. 12.
    Moradi, M., Abolmaesumi, P., Siemens, D.R., Sauerbrei, E.E., Boag, A.H., Mousavi, P.: Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series. IEEE TBME 56(9), 2214–2224 (2009)Google Scholar
  13. 13.
    Nelson, E.D., Slotoroff, C.B., Gomella, L.G., Halpern, E.J.: Targeted biopsy of the prostate: the impact of color doppler imaging and elastography on prostate cancer detection and Gleason score. Urology 70(6), 1136–1140 (2007)CrossRefGoogle Scholar
  14. 14.
    Siddiqui, M.M., et al.: Comparison of MR/US fusion-guided biopsy with US-guided biopsy for the diagnosis of prostate cancer. JAMA 313(4), 390–397 (2015)CrossRefGoogle Scholar
  15. 15.
    Singer, E.A., Kaushal, A., et al.: Active surveillance for prostate cancer: past, present and future. Curr. Opin. Oncol. 24(3), 243–250 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Shekoofeh Azizi
    • 1
    Email author
  • Pingkun Yan
    • 2
  • Amir Tahmasebi
    • 3
  • Peter Pinto
    • 4
  • Bradford Wood
    • 4
  • Jin Tae Kwak
    • 5
  • Sheng Xu
    • 4
  • Baris Turkbey
    • 4
  • Peter Choyke
    • 4
  • Parvin Mousavi
    • 6
  • Purang Abolmaesumi
    • 1
  1. 1.University of British ColumbiaVancouverCanada
  2. 2.Rensselaer Polytechnic InstituteTroyUSA
  3. 3.Philips Research North AmericaCambridgeUSA
  4. 4.National Institutes of HealthBethesdaUSA
  5. 5.Sejong UniversitySeoulKorea
  6. 6.Queen’s UniversityKingstonCanada

Personalised recommendations