Skip to main content
SpringerLink
Log in

Segmentation of Prostate in MRI Images Using Depth Separable Convolution Operations

  • Conference paper
  • First Online:
Intelligent Human Computer Interaction (IHCI 2020)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12615))

Included in the following conference series:

Abstract

The segmentation of the prostate gland into two sub-regions, namely, the central gland (CG) and the peripheral zone (PZ) is crucial for the prostate cancer (PCa) diagnosis. The nature and occurrence of cancer occurred in the prostate is substantially different in both zones. Magnetic resonance imaging modality (MRI) is a clinically primary tool for computer-based assessment and remediation of various cancer types such as PCa. In this paper, we evaluated DeeplabV3+ model on T2W MRI scans using the I2CVB dataset, which is designed in an encoder-decoder style for the zonal segmentation of prostate regions. An important feature of DeeplabV3+ is the depth-wise separable convolutions, which allow more information to be extracted from images as it uses filters with different dilation rates. Prior to being fed to the deep neural network, image pre-processing techniques are applied, including image resizing, cropping, and denoising. The DeeplabV3+ model performance is evaluated using the Dice similarity coefficient (DSC) metric and compared with the vanilla U-Net architecture. Results show that the encoder-decoder network having depth-wise separable convolutions performed better prostate segmentation than the network with standard convolution operations with the DSC value of 70.1% in PZ and 81.5% in CG zone.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Aldoj, N., Biavati, F., Rutz, M., Michallek, F., Stober, S., Dewey, M.: Automatic prostate and prostate zones segmentation of magnetic resonance images using convolutional neural networks (2019)

    Google Scholar 

  2. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49

    Chapter  Google Scholar 

  3. Chi, Y., et al.: A compact method for prostate zonal segmentation on multiparametric MRIs. In: Medical Imaging 2014: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 9036, p. 90360N. International Society for Optics and Photonics (2014)

    Google Scholar 

  4. Choi, Y.J., Kim, J.K., Kim, N., Kim, K.W., Choi, E.K., Cho, K.S.: Functional MR imaging of prostate cancer. Radiographics 27(1), 63–75 (2007)

    Article  Google Scholar 

  5. Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)

    Google Scholar 

  6. Clark, T., Zhang, J., Baig, S., Wong, A., Haider, M.A., Khalvati, F.: Fully automated segmentation of prostate whole gland and transition zone in diffusion-weighted MRI using convolutional neural networks. J. Med. Imaging 4(4), 041307 (2017)

    Article  Google Scholar 

  7. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)

    Article  MathSciNet  Google Scholar 

  8. Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764–773 (2017)

    Google Scholar 

  9. Haffner, J., et al.: Peripheral zone prostate cancers: location and intraprostatic patterns of spread at histopathology. The Prostate 69(3), 276–282 (2009)

    Article  Google Scholar 

  10. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  11. Jensen, C., et al.: Prostate zonal segmentation in 1.5 T and 3T T2W MRI using a convolutional neural network. J. Med. Imaging 6(1), 014501 (2019)

    Google Scholar 

  12. Khan, Z., Yahya, N., Alsaih, K., Ali, S.S.A., Meriaudeau, F.: Evaluation of deep neural networks for semantic segmentation of prostate in T2W MRI. Sensors 20(11), 3183 (2020)

    Article  Google Scholar 

  13. Khan, Z., Yahya, N., Alsaih, K., Meriaudeau, F.: Zonal segmentation of prostate T2W-MRI using atrous convolutional neural network. In: 2019 IEEE Student Conference on Research and Development (SCOReD), pp. 95–99. IEEE (2019)

    Google Scholar 

  14. Kingma, D., Adam, B.J.: A method for stochastic optimization. arxiv preprint arxiv: 14126980 (2014). Cited on p. 50

  15. Klein, S., Van Der Heide, U.A., Lips, I.M., Van Vulpen, M., Staring, M., Pluim, J.P.: Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med. Phys. 35(4), 1407–1417 (2008)

    Article  Google Scholar 

  16. Langerak, T.R., van der Heide, U.A., Kotte, A.N., Viergever, M.A., Van Vulpen, M., Pluim, J.P.: Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (SIMPLE). IEEE Trans. Med. Imaging 29(12), 2000–2008 (2010)

    Article  Google Scholar 

  17. Leake, J.L., et al.: Prostate MRI: access to and current practice of prostate MRI in the united states. J. Am. Coll. Radiol. 11(2), 156–160 (2014)

    Article  Google Scholar 

  18. Lemaître, G., Martí, R., Freixenet, J., Vilanova, J.C., Walker, P.M., Meriaudeau, F.: Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput. Biol. Med. 60, 8–31 (2015)

    Article  Google Scholar 

  19. Lemaitre, G., Martí, R., Rastgoo, M., Mériaudeau, F.: Computer-aided detection for prostate cancer detection based on multi-parametric magnetic resonance imaging. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3138–3141. IEEE (2017)

    Google Scholar 

  20. Litjens, G.J.S.: Computerized detection of cancer in multi-parametric prostate MRI. Ph.D. thesis, Radboud University, Nijmegen, Netherlands (2015)

    Google Scholar 

  21. Martin, S., Troccaz, J., Daanen, V.: Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model. Med. Phys. 37(4), 1579–1590 (2010)

    Article  Google Scholar 

  22. Muller, B.G., et al.: Prostate cancer: interobserver agreement and accuracy with the revised prostate imaging reporting and data system at multiparametric MR imaging. Radiology 277(3), 741–750 (2015)

    Article  Google Scholar 

  23. Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621 (2017)

  24. Qiu, W., Yuan, J., Ukwatta, E., Sun, Y., Rajchl, M., Fenster, A.: Dual optimization based prostate zonal segmentation in 3D MR images. Med. Image Anal. 18(4), 660–673 (2014)

    Article  Google Scholar 

  25. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  26. Scheenen, T.W., Rosenkrantz, A.B., Haider, M.A., Fütterer, J.J.: Multiparametric magnetic resonance imaging in prostate cancer management: current status and future perspectives. Invest. Radiol. 50(9), 594–600 (2015)

    Article  Google Scholar 

  27. Sekou, T.B., Hidane, M., Olivier, J., Cardot, H.: From patch to image segmentation using fully convolutional networks-application to retinal images. arXiv preprint arXiv:1904.03892 (2019)

  28. Siegel, R.L., Miller, K.D., Jemal, A.: Cancer statistics, 2019. CA: Cancer J. Clin. 69(1), 7–34 (2019)

    Google Scholar 

  29. Toth, R., Madabhushi, A.: Multifeature landmark-free active appearance models: application to prostate MRI segmentation. IEEE Trans. Med. Imaging 31(8), 1638–1650 (2012)

    Article  Google Scholar 

  30. Villeirs, G.M., De Meerleer, G.O.: Magnetic resonance imaging (MRI) anatomy of the prostate and application of MRI in radiotherapy planning. Eur. J. Radiol. 63(3), 361–368 (2007)

    Article  Google Scholar 

  31. Wang, Z., Liu, C., Cheng, D., Wang, L., Yang, X., Cheng, K.T.: Automated detection of clinically significant prostate cancer in MP-MRI images based on an end-to-end deep neural network. IEEE Trans. Med. Imaging 37(5), 1127–1139 (2018)

    Article  Google Scholar 

  32. Zhang, J., Baig, S., Wong, A., Haider, M.A., Khalvati, F.: A local ROI-specific atlas-based segmentation of prostate gland and transitional zone in diffusion MRI. J. Comput. Vis. Imaging Syst. 2(1), 1–3 (2016)

    Google Scholar 

Download references

Acknowledgment

This project is supported by the Yayasan Universiti Teknologi PETRONAS (YUTP) research fund under grant number 015LC0-292.

Author information

Authors and Affiliations

  1. Centre for Intelligent and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS (UTP), Seri Iskandar, Malaysia

    Zia Khan, Norashikin Yahya & Khaled Alsaih

  2. ImViA/IFTIM, University of Bourgogne Franche-Comté, Besançon, France

    Fabrice Meriaudeau

Authors
  1. Zia Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Norashikin Yahya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Khaled Alsaih
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fabrice Meriaudeau
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Norashikin Yahya .

Editor information

Editors and Affiliations

  1. Woosong University, Daejeon, Korea (Republic of)

    Madhusudan Singh

  2. Dongseo University, Busan, Korea (Republic of)

    Dae-Ki Kang

  3. Keimyung University, Daegu, Korea (Republic of)

    Jong-Ha Lee

  4. Indian Institute of Information Technoloy, Allahabad, India

    Uma Shanker Tiwary

  5. Hankuk University of Foreign Studies, Yongin, Korea (Republic of)

    Dhananjay Singh

  6. Pukyong National University, Busan, Korea (Republic of)

    Wan-Young Chung

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Khan, Z., Yahya, N., Alsaih, K., Meriaudeau, F. (2021). Segmentation of Prostate in MRI Images Using Depth Separable Convolution Operations. In: Singh, M., Kang, DK., Lee, JH., Tiwary, U.S., Singh, D., Chung, WY. (eds) Intelligent Human Computer Interaction. IHCI 2020. Lecture Notes in Computer Science(), vol 12615. Springer, Cham. https://doi.org/10.1007/978-3-030-68449-5_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-68449-5_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-68448-8

  • Online ISBN: 978-3-030-68449-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation