Skip to main content

Advertisement

SpringerLink
Log in

Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Automatic and reliable prostate segmentation is an essential prerequisite for assisting the diagnosis and treatment, such as guiding biopsy procedure and radiation therapy. Nonetheless, automatic segmentation is challenging due to the lack of clear prostate boundaries owing to the similar appearance of prostate and surrounding tissues and the wide variation in size and shape among different patients ascribed to pathological changes or different resolutions of images. In this regard, the state-of-the-art includes methods based on a probabilistic atlas, active contour models, and deep learning techniques. However, these techniques have limitations that need to be addressed, such as MRI scans with the same spatial resolution, initialization of the prostate region with well-defined contours and a set of hyperparameters of deep learning techniques determined manually, respectively. Therefore, this paper proposes an automatic and novel coarse-to-fine segmentation method for prostate 3D MRI scans. The coarse segmentation step combines local texture and spatial information using the Intrinsic Manifold Simple Linear Iterative Clustering algorithm and probabilistic atlas in a deep convolutional neural networks model jointly with the particle swarm optimization algorithm to classify prostate and non-prostate tissues. Then, the fine segmentation uses the 3D Chan-Vese active contour model to obtain the final prostate surface. The proposed method has been evaluated on the Prostate 3T and PROMISE12 databases presenting a dice similarity coefficient of 84.86%, relative volume difference of 14.53%, sensitivity of 90.73%, specificity of 99.46%, and accuracy of 99.11%. Experimental results demonstrate the high performance potential of the proposed method compared to those previously published.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

References

  1. American cancer society: key statistics for prostate cancer (2018). https://www.cancer.org/cancer/prostate-cancer/about/key-statistics.html. Accessed: 2018-04-15

  2. Instituto nacional do câncer, tipos de câncer: Próstata (2018). http://www2.inca.gov.br/wps/wcm/connect/tiposdecancer/site/home/prostata. Accessed: 2018-04-15

  3. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282

    Article  PubMed  Google Scholar 

  4. Al-Qunaieer FS, Tizhoosh HR, Rahnamayan S (2014) Multi-resolution level sets with shape priors: a validation report for 2d segmentation of prostate gland in t2w mr images. J Digit Imaging 27(6):833–847

    Article  PubMed  PubMed Central  Google Scholar 

  5. Alves RS, Tavares JMR (2015) Computer image registration techniques applied to nuclear medicine images. In: Computational and experimental biomedical sciences: methods and applications. Springer, pp 173–191

  6. Cai X, Cui Z, Zeng J, Tan Y (2009) Individual parameter selection strategy for particle swarm optimization. In: Particle swarm optimization. Intechopen, pp 89–112

  7. Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277

    Article  CAS  PubMed  Google Scholar 

  8. Cheng R, Roth HR, Lay NS, Lu L, Turkbey B, Gandler W, McCreedy ES, Pohida TJ, Pinto PA, Choyke PL et al (2017) Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks. J Med Imaging 4(4):041,302

    Article  Google Scholar 

  9. Chollet F et al (2015) Keras. https://github.com/fchollet/keras

  10. Damião R, Figueiredo RT, Dornas MC, Lima DS, Koschorke MA (2015) Câncer de próstata Revista Hospital universitário Pedro Ernesto, pp 14

  11. De Visschere P (2018) Improving the diagnosis of clinically significant prostate cancer with magnetic resonance imaging. Journal of the Belgian Society of Radiology 102(1)

  12. Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory In: , 1995. MHS’95., Proceedings of the Sixth International Symposium on Micro Machine and Human Science. IEEE, pp 39–43

  13. Eberhart RC, Shi Y (2000) Comparing inertia weights and constriction factors in particle swarm optimization. In: 2000. Proceedings of the 2000 Congress on Evolutionary Computation, vol 1. IEEE, pp 84–88

  14. Ferreira A, Gentil F, Tavares JMR (2014) Segmentation algorithms for ear image data towards biomechanical studies. Comput Methods Biomech Biomed Eng 17(8):888–904

    Article  Google Scholar 

  15. Ghose S, Oliver A, Martí R, Lladó X, Vilanova JC, Freixenet J, Mitra J, Sidibé D, Meriaudeau F (2012) A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images. Comput Methods Programs Biomed 108(1):262–287

    Article  PubMed  Google Scholar 

  16. Gonċalves PC, Tavares JMR, Jorge RN (2008) Segmentation and simulation of objects represented in images using physical principles. Comput Model Eng Sci 32(1):45–55

    Google Scholar 

  17. Gonzalez RC, Wintz P (1977) Digital image processing(book). Reading, Mass., Addison-Wesley Publishing Co., Inc. Applied Mathematics and Computation (13), pp 451

  18. Guo Y, Gao Y, Shen D (2017) Deformable mr prostate segmentation via deep feature learning and sparse patch matching. In: Deep learning for medical image analysis. Elsevier, pp 197–222

  19. Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31

    Article  PubMed  Google Scholar 

  20. Jia H, Xia Y, Cai W, Fulham M, Feng D (2017) Prostate segmentation in mr images using ensemble deep convolutional neural networks. In: 2017 IEEE 14th international symposium on Biomedical imaging (ISBI 2017). IEEE, pp 762–765

  21. Jia H, Xia Y, Song Y, Cai W, Fulham M, Feng D (2018) Atlas registration and ensemble deep convolutional neural network-based prostate segmentation using magnetic resonance imaging. Neurocomputing 275:1358–1369

    Article  Google Scholar 

  22. Kennedy J (2011) Particle swarm optimization. In: Encyclopedia of machine learning. Springer, pp 760–766

  23. Korsager AS, Fortunati V, Lijn F, Carl J, Niessen W, ØStergaard LR, Walsum T (2015) The use of atlas registration and graph cuts for prostate segmentation in magnetic resonance images. Med Phys 42 (4):1614–1624

    Article  PubMed  Google Scholar 

  24. Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  25. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  CAS  PubMed  Google Scholar 

  26. LeCun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, pp 253–256

  27. Li A, Li C, Wang X, Eberl S, Feng D, Fulham M (2013) Automated segmentation of prostate mr images using prior knowledge enhanced random walker. In: International conference on digital image computing: Techniques and applications (DICTA). IEEE, pp 1–7

  28. Litjens G, Futterer J, Huisman H (2015) Data from prostate-3t: the cancer imaging archive. https://doi.org/10.7937/K9/TCIA.2015.QJTV5IL5. Accessed: 2018-01-15

  29. Litjens G, Toth R, van de Ven W, Hoeks C, Kerkstra S, van Ginneken B, Vincent G, Guillard G, Birbeck N, Zhang J et al (2014) Evaluation of prostate segmentation algorithms for mri: the promise12 challenge. Med Image Anal 18(2):359–373

    Article  PubMed  Google Scholar 

  30. Liu YJ, Yu M, Li BJ, He Y (2017) Intrinsic manifold slic: a simple and efficient method for computing content-sensitive superpixels. IEEE transactions on pattern analysis and machine intelligence

  31. Ma Z, Tavares JMR, Jorge RN (2009) A review on the current segmentation algorithms for medical images. In: Proceedings of the 1st International Conference on Imaging Theory and Applications (IMAGAPP), pp 135–140

  32. Ma Z, Tavares JMR, Jorge RN, Mascarenhas T (2010) A review of algorithms for medical image segmentation and their applications to the female pelvic cavity. Comput Methods Biomech Biomed Eng 13(2):235–246

    Article  Google Scholar 

  33. Mohler JL, Armstrong AJ, Bahnson RR, D’Amico AV, Davis BJ, Eastham JA, Enke CA, Farrington TA, Higano CS, Horwitz EM et al (2016) Prostate cancer, version 1.2016. J Natl Compr Cancer Netw 14(1):19–30

    Article  Google Scholar 

  34. Oliveira FP, Tavares JMR (2014) Medical image registration: a review. Comput Methods Biomech Biomed Eng 17(2):73–93

    Article  Google Scholar 

  35. Rubinstein RY, Kroese DP (2013) The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simulation and machine learning. Springer Science & Business Media

  36. Siegel R, Miller K, Jemal A (2018) Cancer statistics, 2018. CA: Cancer J Clin 68:7–30

    Google Scholar 

  37. Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA: a Cancer J Clin 69(1):7–34

    Google Scholar 

  38. da Silva GL, da Silva Neto OP, Silva AC, de Paiva AC, Gattass M (2017) Lung nodules diagnosis based on evolutionary convolutional neural network. Multimed Tools Appl 76(18):19,039–19,055

    Article  Google Scholar 

  39. da Silva GLF, Valente TLA, Silva AC, de Paiva AC, Gattass M (2018) Convolutional neural network-based pso for lung nodule false positive reduction on ct images. Comput Methods Prog Biomed 162:109–118

    Article  Google Scholar 

  40. Sołtysiński T (2008) Bayesian constrained spectral method for segmentation of noisy medical images. theory and applications. In: Advanced computational intelligence paradigms in healthcare-3. Springer, pp 181–206

  41. Sołtysiński T (2008) Novel quantitative method for spleen’s morphometry in splenomegally. In: International conference on artificial intelligence and soft computing. Springer, pp 981–991

  42. Sołtysiński T, Kałużynski K, Pałko T (2006) Cardiac ventricle contour reconstruction in ultrasonographic images using bayesian constrained spectral method. In: International conference on artificial intelligence and soft computing. Springer, pp 988–997

  43. Stojanov D, Koceski S (2014) Topological mri prostate segmentation method. In: Federated conference on computer science and information systems (fedCSIS). IEEE, pp 219–225

  44. Taha AA, Hanbury A (2015) Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC Med Imaging 15(1):29

    Article  PubMed  PubMed Central  Google Scholar 

  45. Tavares JMR (2014) Analysis of biomedical images based on automated methods of image registration. In: International symposium on visual computing. Springer, pp 21–30

  46. for Therapy Guided Image, N.C.: Prostate mr image database (2008). http://prostatemrimagedatabase.com/. Accessed: 2017-08-19

  47. Tian Z, Liu L, Fei B (2015) A fully automatic multi-atlas based segmentation method for prostate mr images. In: Medical imaging 2015: Image processing, vol 9413. International society for optics and photonics, pp 941340

  48. Tian Z, Liu L, Zhang Z, Fei B (2016) Superpixel-based segmentation for 3d prostate mr images. IEEE Trans Med Imaging 35(3):791–801

    Article  PubMed  Google Scholar 

  49. Tian Z, Liu L, Zhang Z, Xue J, Fei B (2017) A supervoxel-based segmentation method for prostate mr images. Med Phys 44(2):558–569

    Article  CAS  PubMed  Google Scholar 

  50. Ullrich T, Quentin M, Oelers C, Dietzel F, Sawicki L, Arsov C, Rabenalt R, Albers P, Antoch G, Blondin D et al (2017) Magnetic resonance imaging of the prostate at 1.5 versus 3.0 t: a prospective comparison study of image quality. Eur J Radiol 90:192–197

    Article  CAS  PubMed  Google Scholar 

  51. Xu J, Luo X, Wang G, Gilmore H, Madabhushi A (2016) A deep convolutional neural network for segmenting and classifying epithelial and stromal regions in histopathological images. Neurocomputing 191:214–223

    Article  PubMed  PubMed Central  Google Scholar 

  52. Yan K, Li C, Wang X, Li A, Yuan Y, Feng D, Khadra M, Kim J (2016) Automatic prostate segmentation on mr images with deep network and graph model. In: IEEE 38Th annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 635–638

  53. Yang X, Zhan S, Xie D (2016) Landmark based prostate mri segmentation via improved level set method. In: IEEE 13Th international conference on signal processing (ICSP). IEEE, pp 29–34

  54. Yang X, Zhan S, Xie D, Zhao H, Kurihara T (2017) Hierarchical prostate mri segmentation via level set clustering with shape prior. Neurocomputing 257:154–163

    Article  Google Scholar 

  55. Ye X, Oyoyo U, Lu A, Dixon J, Rojas H, Randolph S, Kelly T (2016) Comparison of 3.0 t pac versus 1.5 t erc mri in detecting local prostate carcinoma. bioRxiv, pp 058123

  56. Yoo TS, Ackerman MJ, Lorensen WE, Schroeder W, Chalana V, Aylward S, Metaxas D, Whitaker R (2002) Engineering and algorithm design for an image processing api: a technical report on itk-the insight toolkit. Studies in health technology and informatics, pp 586–592

  57. Yu L, Yang X, Chen H, Qin J, Heng PA (2017) Volumetric convnets with mixed residual connections for automated prostate segmentation from 3d mr images. In: AAAI, pp 66–72

Download references

Funding

The authors acknowledge CAPES and CNPq for their financial support.

Author information

Authors and Affiliations

  1. Applied Computing Group - NCA, Federal University of Maranhão - UFMA, Av. dos Portugueses, SN, Bacanga, São Luís, MA, 65085-580, Brazil

    Giovanni L. F. da Silva, Petterson S. Diniz, Jonnison L. Ferreira, João V. F. França, Aristófanes C. Silva, Anselmo C. de Paiva & Elton A. A. de Cavalcanti

Authors
  1. Giovanni L. F. da Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Petterson S. Diniz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jonnison L. Ferreira
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. João V. F. França
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Aristófanes C. Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Anselmo C. de Paiva
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Elton A. A. de Cavalcanti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giovanni L. F. da Silva.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

da Silva, G.L.F., Diniz, P.S., Ferreira, J.L. et al. Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans. Med Biol Eng Comput 58, 1947–1964 (2020). https://doi.org/10.1007/s11517-020-02199-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-020-02199-5

Keywords

Search

Navigation