Skip to main content

Multichannel convolutional neural network-based fuzzy active contour model for medical image segmentation

Abstract

Anatomical maps depicted by medical images reflect the health of the human body. Understanding the detailed division of the regions in the anatomical maps is helpful for diagnosis and further treatment. For example, the lung window contains the lung parenchyma, mediastinum, and diseased tumor. Accurate tumor segmentation can be more comprehensive and accurate to determine the disease condition to select the appropriate radiotherapy means to improve the success rate of treatment. However, the traditional manual segmentation task is large, and the segmentation results vary with the experience level of the observer. Therefore, the development of automatic and reliable segmentation methods is a feasible and important task in clinical practice. Therefore, this paper proposes a multichannel convolutional neural network (CNN)-based fuzzy active contour model for medical image segmentation. Medical images are gridded and labeled using the superpixel SLIC method. The gridded images are used as data sets to train the multichannel CNN network to segment superpixels of organ boundaries, and the seed points of these superpixels are connected to form rough segmentation boundaries. The rough segmentation boundary is used as the initial contour, and the organ boundary in the medical image is obtained by fuzzy active contour segmentation. Finally, we conduct comparison experiments with the state-of-the-art segmentation methods, the results of the subjective evaluation and objective evaluation show that the proposed method has a better segmentation effect and robustness.

This is a preview of subscription content, access via your institution.

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

References

  1. Bai XD, Cao ZG, Wang Y et al (2014) Image segmentation using modified SLIC and Nyström based spectral clustering. Optik 125(16):4302–4307

    Article  Google Scholar 

  2. Bi L, Feng D, Kim J (2018) Dual-path adversarial learning for fully convolutional network (FCN)-based medical image segmentation. Vis Comput 34(6–8):1–10

    Google Scholar 

  3. Brion E, Jean L, Javaid U et al (2019) Using planning CTs to enhance CNN-based bladder segmentation on cone beam CT. In: Image-guided procedures, robotic interventions, and modeling, vol 10951. https://doi.org/10.1117/12.2512791

  4. Chen X, Udupa JK, Bagci U, Zhuge Y, Yao J (2012) Medical image segmentation by combining graph cuts and oriented active appearance models. IEEE Trans Image Process 21(4):2035–2046. https://doi.org/10.1109/TIP.2012.2186306

    MathSciNet  Article  MATH  Google Scholar 

  5. Chu J, Min H, Liu L et al (2015) A novel computer aided breast mass detection scheme based on morphological enhancement and SLIC superpixel segmentation. Med Phys 42(7):3859–3869

    Article  Google Scholar 

  6. Drozdzal M, Chartrand G, Vorontsov E et al (2017) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13

    Article  Google Scholar 

  7. Efimenko M, Ignatev A, Koshechkin K (2020) Review of medical image recognition technologies to detect melanomas using neural networks. BMC Bioinform 21(Suppl 11):270

    Article  Google Scholar 

  8. Faisal R, Syed IAS, Naveed Riaz M et al (2020) A region-based deep level set formulation for vertebral bone segmentation of osteoporotic fractures. J Dig Imaging 33(1):191–203

    Article  Google Scholar 

  9. Gu X, Angelov P (2019) Self-boosting first-order autonomous learning neuro-fuzzy systems. Appl Soft Comput 77:118–134. https://doi.org/10.1016/j.asoc.2019.01.005

    Article  Google Scholar 

  10. Hedrea E, Precup R, Roman R et al (2021) Tensor product-based model transformation approach to tower crane systems modeling. Asian J Control. https://doi.org/10.1002/asjc.2494

    Article  Google Scholar 

  11. Jenkinson M, Smith S (2001) A global optimisation method for robust affine registration of brain images. Med Image Anal 5(2):143–156. https://doi.org/10.1016/S1361-8415(01)00036-6

    Article  Google Scholar 

  12. Kang J, Ding J, Wan Y et al (2020) Liver image segmentation algorithm based on watershed correction and U-Net. Comput Eng (in Chinese) 46(1):255–261

    Google Scholar 

  13. Kayalibay B, Jensen G, van der Smagt P (2017) CNN-based segmentation of medical imaging data. arXiv:1701.03056

  14. Pozna C, Precup RE (2014) Applications of signatures to expert systems modelling. Acta Polytech Hung 11(2):21–39

    Google Scholar 

  15. Rcr A, Rep A, Bd A et al (2019) Combined model-free adaptive control with fuzzy component by virtual reference feedback tuning for tower crane systems. Proc Comput Sci 162:267–274. https://doi.org/10.1016/j.procs.2019.11.284

    Article  Google Scholar 

  16. Roth HR, Oda H, Zhou X et al (2018) An application of cascaded 3D fully convolutional networks for medical image segmentation. Comput Med Imaging Graph 66:90–99

    Article  Google Scholar 

  17. Sun W-Y, Dong E-Q, Cao Z-L, Zhang Q (2017) A robust local segmentation method based on fuzzy-energy based active contour. Acta Autom Sin 43(4):611–621. https://doi.org/10.16383/j.aas.2017.c160260

    Article  Google Scholar 

  18. Teng L, Li H, Yin S et al (2020) An active contour model based on hybrid energy and fisher criterion for image segmentation. Int J Image Data Fusion 11(1):97–112

    Article  Google Scholar 

  19. Toennies K, Rak M, Engel K (2014) Deformable part models for object detection in medical images. Biomed Eng Online 13(Suppl 1):S1

    Article  Google Scholar 

  20. Tseng KK, Zhang R, Chen CM et al (2020) DNetUnet: a semi-supervised CNN of medical image segmentation for super-computing AI service. J Supercomput. https://doi.org/10.1007/s11227-020-03407-7

    Article  Google Scholar 

  21. Tustison NJ, Yang Y, Salerno M (2015) Advanced normalization tools for cardiac motion correction. In: Camara O, Mansi T, Pop M, Rhode K, Sermesant M, Young A (eds) Statistical atlases and computational models of the heart—imaging and modelling challenges. STACOM 2014. Lecture notes in computer science, vol 8896. Springer, Cham. https://doi.org/10.1007/978-3-319-14678-2_1

  22. Wang X, Yin S, Sun Ke et al (2020) GKFC-CNN: modified Gaussian kernel fuzzy C-means and convolutional neural network for apple segmentation and recognition. J Appl Sci Eng 23(3):555–561

    Google Scholar 

  23. Xue P, Dong E, Ji H (2020) Lung 4D CT image registration based on high-order markov random field. IEEE Trans Med Imaging 39(4):910–921. https://doi.org/10.1109/TMI.2019.2937458

    Article  Google Scholar 

  24. Yin S, Li H, Liu D, Karim S (2020a) Active contour modal based on density-oriented BIRCH clustering method for medical image segmentation. Multimed Tools Appl 79:31049–31068

    Article  Google Scholar 

  25. Yin S, Li H, Teng L et al (2020b) An optimised multi-scale fusion method for airport detection in large-scale optical remote sensing images. Int J Image Data Fusion 11(2):201–214

    Article  Google Scholar 

  26. Yongpeng TAO, Yu JING, Cong XU (2020) CT image segmentation method combining superpixel and CNN. Comput Eng Appl (in Chinese) 56(5):200–205

    Google Scholar 

  27. Yu Q, Gao Y, Zheng Y et al (2020) Crossover-Net: leveraging vertical-horizontal crossover relation for robust medical image segmentation. Pattern Recognit 113(10):107756

    Google Scholar 

  28. Zall R, Kangavari MR (2019) On the construction of multi-relational classifier based on canonical correlation analysis. Int J Artif Intell 17(2):23–43

    Google Scholar 

  29. Zhang L et al (2020) Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans Med Imaging 39(7):2531–2540. https://doi.org/10.1109/TMI.2020.2973595

    Article  Google Scholar 

  30. Zhang Z, Wu C, Coleman S et al (2020) DENSE-INception U-net for medical image segmentation. Comput Methods Progr Biomed 192:105395

    Article  Google Scholar 

  31. Zhou T, Ruan S, Canu S (2020) A review: deep learning for medical image segmentation using multi-modality fusion. arXiv:2004.10664

Download references

Acknowledgements

This work is supported by Basic Research Projects Under Basic Scientific Research Operating Expenses (No. 2019-KYYWF-1387). Also, The authors are grateful to Education Department of Liaoning Province for funding this work through Liaoning Province Future School Innovation Plan (Project Number 2020CFS073).

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Shoulin Yin or Lin Teng.

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

Verify currency and authenticity via CrossMark

Cite this article

Shi, Q., Yin, S., Wang, K. et al. Multichannel convolutional neural network-based fuzzy active contour model for medical image segmentation. Evolving Systems (2021). https://doi.org/10.1007/s12530-021-09392-3

Download citation

Keywords

  • Medical image segmentation
  • Multichannel CNN
  • SLIC
  • Fuzzy active contour