Advertisement

Augmenting MRI–transrectal ultrasound-guided prostate biopsy with temporal ultrasound data: a clinical feasibility study

  • Farhad ImaniEmail author
  • Bo Zhuang
  • Amir Tahmasebi
  • Jin Tae Kwak
  • Sheng Xu
  • Harsh Agarwal
  • Shyam Bharat
  • Nishant Uniyal
  • Ismail Baris Turkbey
  • Peter Choyke
  • Peter Pinto
  • Bradford Wood
  • Mehdi Moradi
  • Parvin Mousavi
  • Purang Abolmaesumi
Original Article

Abstract

Purpose

In recent years, fusion of multi-parametric MRI (mp-MRI) with transrectal ultrasound (TRUS)-guided biopsy has enabled targeted prostate biopsy with improved cancer yield. Target identification is solely based on information from mp-MRI, which is subsequently transferred to the subject coordinates through an image registration approach. mp-MRI has shown to be highly sensitive to detect higher-grade prostate cancer, but suffers from a high rate of false positives for lower-grade cancer, leading to unnecessary biopsies. This paper utilizes a machine-learning framework to further improve the sensitivity of targeted biopsy through analyzing temporal ultrasound data backscattered from the prostate tissue.

Methods

Temporal ultrasound data were acquired during targeted fusion prostate biopsy from suspicious cancer foci identified in mp-MRI. Several spectral features, representing the signature of backscattered signal from the tissue, were extracted from the temporal ultrasound data. A supervised support vector machine classification model was trained to relate the features to the result of histopathology analysis of biopsy cores obtained from cancer foci. The model was used to predict the label of biopsy cores for mp-MRI-identified targets in an independent group of subjects.

Results

Training of the classier was performed on data obtained from 35 biopsy cores. A fivefold cross-validation strategy was utilized to examine the consistency of the selected features from temporal ultrasound data, where we achieved the classification accuracy and area under receiver operating characteristic curve of 94 % and 0.98, respectively. Subsequently, an independent group of 25 biopsy cores was used for validation of the model, in which mp-MRI had identified suspicious cancer foci. Using the trained model, we predicted the tissue pathology using temporal ultrasound data: 16 out of 17 benign cores, as well as all three higher-grade cancer cores, were correctly identified.

Conclusion

The results show that temporal analysis of ultrasound data is potentially an effective approach to complement mp-MRI–TRUS-guided prostate cancer biopsy, specially to reduce the number of unnecessary biopsies and to reliably identify higher-grade cancers.

Keywords

Temporal ultrasound data Cancer diagnosis Prostate cancer 

Notes

Acknowledgments

The authors would like to acknowledge the help of Jochen Kruecker and Pingkun Yan for assisting with the experiments. This work was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Canadian Institutes of Health Research (CIHR).

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Barentsz J, Richenberg J, Clements R, Choyke P, Verma S, Villeirs G, Rouviere O, Logager V, Futterer J (2012) ESUR prostate MR guidelines. Eur Radiol 22(4):746–757CrossRefPubMedCentralPubMedGoogle Scholar
  2. 2.
    Daoud M, Mousavi P, Imani F, Rohling R, Abolmaesumi P (2013) Tissue classification using ultrasound-induced variations in acoustic backscattering features. IEEE Trans Biomed Eng 60(2):310–320CrossRefPubMedGoogle Scholar
  3. 3.
    Feleppa E, Porter C, Ketterling J, Dasgupta S, Ramachandran S, Sparks D (2007) Recent advances in ultrasonic tissue-type imaging of the prostate. Acoust Imaging 28:331–339Google Scholar
  4. 4.
    Futterer J, Heijmink S, Scheenen T, Veltman J, Huisman H, Vos P, Hulsbergen-Van C, Witjes J, Krabbe P, Heerschap A, Barentsz J (2006) Prostate cancer localization with dynamic contrast-enhanced MR imaging and proton MR spectroscopic imaging. Radiology 241(2):449–458CrossRefPubMedGoogle Scholar
  5. 5.
    Goossen T, Wijkstra H (2003) Transrectal ultrasound imaging and prostate cancer. Arch Ital Urol Androl 75(1):68–74PubMedGoogle Scholar
  6. 6.
    Hricak H, Choyke P, Eberhardt S, Leibel S, Scardino P (2007) Imaging prostate cancer: a multidisciplinary perspective. Radiology 243(1):28–53CrossRefPubMedGoogle Scholar
  7. 7.
    Imani F, Abolmaesumi P, Gibson E, Khojasteh A, Gaed M, Moussa M, Gomez J, Romagnoli C, Siemens D, Leveridge M, Chang S, Fenster A, Ward A, Mousavi P (2013) Ultrasound-based characterization of prostate cancer: an in vivo clinical feasibility study. In: Medical image computing and computer-assisted intervention, pp 279–286Google Scholar
  8. 8.
    Imani F, Abolmaesumi P, Wu M, Lasso A, Burdette E, Ghoshal G, Heffter T, Williams E, Neubauer P, Fichtinger G, Mousavi P (2013) Ultrasound-guided characterization of interstitial ablated tissue using RF time series: feasibility study. IEEE Trans Biomed Eng 60(6):1608–18CrossRefPubMedGoogle Scholar
  9. 9.
    Krucker J, Xu S, Glossop N, Guion P, Choyke P, Ocak I, Singh AK, Wood BJ (2007) Fusion of realtime transrectal ultrasound with pre-acquired MRI for multi-modality prostate imaging. In: SPIE, p 650912Google Scholar
  10. 10.
    Lin H, Lin C, Weng R (2003) A note on platt’s probabilistic outputs for support vector machines. Technical report, Department of Computer Science, National Taiwan University, vol 68, pp 267–276Google Scholar
  11. 11.
    Margel D, Yap S, Lawrentschuk N, Klotz L, Haider M, Hersey K, Finelli A, Zlotta A, Trachtenberg J, Fleshner N (2012) Impact of multiparametric endorectal coil prostate magnetic resonance imaging on disease reclassification among active surveillance candidates: a prospective cohort study. J Urol 187(4):1247–1252CrossRefPubMedGoogle Scholar
  12. 12.
    Marks L, Young S, Natarajan S (2013) MRI-ultrasound fusion for guidance of targeted prostate biopsy. Curr Opin Urol 23(1):43–50CrossRefPubMedCentralPubMedGoogle Scholar
  13. 13.
    Miyagawa T, Tsutsumi M, Matsumura T, Kawazoe N, Ishikawa S, Shimokama T, Miyanaga N, Akaza H (2009) Real-time elastography for the diagnosis of prostate cancer: evaluation of elastographic moving images. Jpn J Clin Oncol 39(6):394–398CrossRefPubMedGoogle Scholar
  14. 14.
    Moradi M, Abolmaesumi P, Mousavi P (2010) Tissue typing using ultrasound RF time series: experiments with animal tissue samples. J Med Phys 37(8):4401–4413CrossRefGoogle Scholar
  15. 15.
    Moradi M, Abolmaesumi P, Siemens DR, Sauerbrei EE, Boag A, Mousavi P (2009) Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series. IEEE Trans Biomed Eng 56(9):2214–2223CrossRefPubMedGoogle Scholar
  16. 16.
    Moradi M, Mahdavi S, Nir G, Jones E, Goldenberg S, Salcudean S (2013) Ultrasound RF time series for tissue typing: first in vivo clinical results. In: SPIE 8670, Medical Imaging, pp 86701I1–86701I8Google Scholar
  17. 17.
    Moradi M, Mahdavi S, Nir G, Mohareri O, Koupparis A, Gagnon L, Casey R, Ischia J, Jones E, Goldenberg S, Salcudean S (2014) Multiparametric 3D in vivo ultrasound vibroelastography imaging of prostate cancer: preliminary results. Med Phys 41(7):073505-1–073505-12CrossRefGoogle Scholar
  18. 18.
    Moradi M, Mousavi P, Abolmaesumi P (2007) Computer-aided diagnosis of prostate cancer with emphasis on ultrasound-based approaches: a review. Ultrasound Med Biol 33(7):1010–1028CrossRefPubMedGoogle Scholar
  19. 19.
    Ophir J, Garra B, Kallel F, Konofagou E, Krouskop T, Righetti R, Varghese T (2000) Elastographic imaging. Ultrasound Med Biol 26:S23–S29CrossRefPubMedGoogle Scholar
  20. 20.
    Pallwein L, Mitterberger M, Struve P, Pinggera G, Horninger W, Bartsch G, Aigner F, Lorenz A, Pedross F, Frauscher F (2007) Real-time elastography for detecting prostate cancer: preliminary experience. BJU Int 100(1):42–46CrossRefPubMedGoogle Scholar
  21. 21.
    Pinto P, Chung P, Rastinehad A (2011) Ultrasound fusion guided prostate biopsy improves cancer detection following transrectal ultrasound biopsy and correlates with multiparametric magnetic resonance. J Urol 186(4):1281–1285CrossRefPubMedCentralPubMedGoogle Scholar
  22. 22.
    Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Larg Margin Classif 10(3):61–74Google Scholar
  23. 23.
    Rapiti E, Schaffar R, Iselin C, Miralbell R, Pelte M, Weber D, Zanetti R, Neyroud-Caspar I, Bouchardy C (2013) Importance and determinants of Gleason score undergrading on biopsy sample of prostate cancer in a population-based study. BMC Urol 13:13–19CrossRefGoogle Scholar
  24. 24.
    Scheipers U, Ermert H, Sommerfeld H, Garcia-Schurmann M, Senge T, Philippou S (2003) Ultrasonic multifeature tissue characterization for prostate diagnostics. Ultrasound Med Biol 29(8):1137–1149CrossRefPubMedGoogle Scholar
  25. 25.
    Turkbey B, Pinto P, Mani H, Bernardo M, Pang Y, McKinney Y, Khurana K, Ravizzini G, Albert P, Merino M, Choyke P (2010) Prostate cancer: value of multiparametric MR imaging at 3 T for detection histopathologic correlation. Radiology 255(1):89–99CrossRefPubMedCentralPubMedGoogle Scholar
  26. 26.
    Turkbey B, Shah V, Pang Y, Bernardo M, Xu S, Kruecker J, Locklin J, Baccala AJ, Rastinehad A, Merino M, Shih J, Wood B, Pinto P, Choyke P (2011) Is apparent diffusion coefficient associated with clinical risk scores for prostate cancers that are visible on 3-T mr images? Radiology 258(2):488–495CrossRefPubMedCentralPubMedGoogle Scholar
  27. 27.
    Uniyal N, Imani F, Tahmasebi A, Agarwal H, Bharat S, Yan P, Kruecker J, Kwak JT, Xu S, Wood B, Pinto P, Turkbey B, Choyke P, Abolmaesumi P, Mousavi P, Moradi M (2014) Ultrasound-based prediction of prostate cancer in MRI-guided biopsy. In: Medical image computing and computer-assisted intervention workshop on clinical image-based proceduresGoogle Scholar
  28. 28.
    Xie S, Li H, Du J, Xia J, Guo Y, Xin M, Li F (2013) Influence of serum prostate-specific antigen (PSA) level, prostate volume, and PSA density on prostate cancer detection with contrast-enhanced sonography using contrast-tuned imaging technology. J Ultrasound Med 32(5):741–748CrossRefPubMedGoogle Scholar
  29. 29.
    Xu S, Kruecker J, Guion P, Glossop N, Neeman Z, Choyke P, Singh AK, Wood B (2007) Closed-loop control in fused MR-TRUS image-guided prostate biopsy. In: Medical image computing and computer-assisted intervention, pp 128–135Google Scholar
  30. 30.
    Xu S, Kruecker J, Turkbey B, Glossop N, Singh AK, Choyke P, Pinto P, Wood B (2008) Real-time MRI-TRUS fusion for guidance of targeted prostate biopsies. Comput Aided Surg 13(5):255–264CrossRefPubMedCentralPubMedGoogle Scholar

Copyright information

© CARS 2015

Authors and Affiliations

  • Farhad Imani
    • 1
    Email author
  • Bo Zhuang
    • 1
  • Amir Tahmasebi
    • 2
  • Jin Tae Kwak
    • 3
  • Sheng Xu
    • 3
  • Harsh Agarwal
    • 2
  • Shyam Bharat
    • 2
  • Nishant Uniyal
    • 1
  • Ismail Baris Turkbey
    • 3
  • Peter Choyke
    • 3
  • Peter Pinto
    • 3
  • Bradford Wood
    • 3
  • Mehdi Moradi
    • 1
  • Parvin Mousavi
    • 4
  • Purang Abolmaesumi
    • 1
  1. 1.Department of Electrical and Computer EngineeringThe University of British ColumbiaVancouverCanada
  2. 2.Philips Research North AmericaNYUSA
  3. 3.National Institutes of HealthBethesdaMDUSA
  4. 4.School of ComputingQueen’s UniversityKingstonCanada

Personalised recommendations