Skip to main content

Triple-View Feature Learning for Medical Image Segmentation

  • Conference paper
  • First Online:
Resource-Efficient Medical Image Analysis (REMIA 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13543))

Included in the following conference series:

Abstract

Deep learning models, e.g. supervised Encoder-Decoder style networks, exhibit promising performance in medical image segmentation, but come with a high labelling cost. We propose TriSegNet, a semi-supervised semantic segmentation framework. It uses triple-view feature learning on a limited amount of labelled data and a large amount of unlabeled data. The triple-view architecture consists of three pixel-level classifiers and a low-level shared-weight learning module. The model is first initialized with labelled data. Label processing, including data perturbation, confidence label voting and unconfident label detection for annotation, enables the model to train on labelled and unlabeled data simultaneously. The confidence of each model gets improved through the other two views of the feature learning. This process is repeated until each model reaches the same confidence level as its counterparts. This strategy enables triple-view learning of generic medical image datasets. Bespoke overlap-based and boundary-based loss functions are tailored to the different stages of the training. The segmentation results are evaluated on four publicly available benchmark datasets including Ultrasound, CT, MRI, and Histology images. Repeated experiments demonstrate the effectiveness of the proposed network compared against other semi-supervised algorithms, across a large set of evaluation measures.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 44.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 59.99
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

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/HiLab-git/SSL4MIS.

  2. 2.

    https://github.com/ziyangwang007/CV-SSL-MIS.

  3. 3.

    https://github.com/qubvel/segmentation_models/tree/master/segmentation_models.

References

  1. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). www.tensorflow.org/

  2. Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514–2525 (2018)

    Article  Google Scholar 

  3. Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pp. 92–100 (1998)

    Google Scholar 

  4. Chaurasia, A., Culurciello, E.: Linknet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing, pp. 1–4. IEEE (2017)

    Google Scholar 

  5. Chen, D.D., et al.: Tri-net for semi-supervised deep learning. In: International Joint Conferences on Artificial Intelligence (2018)

    Google Scholar 

  6. Chen, L.-C., et al.: Naive-student: leveraging semi-supervised learning in video sequences for urban scene segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 695–714. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_40

    Chapter  Google Scholar 

  7. Chen, X., et al.: Semi-supervised semantic segmentation with cross pseudo supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2613–2622 (2021)

    Google Scholar 

  8. Chen, X., et al.: Learning active contour models for medical image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11632–11640 (2019)

    Google Scholar 

  9. Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647–655. PMLR (2014)

    Google Scholar 

  10. Gamper, J., Alemi Koohbanani, N., Benet, K., Khuram, A., Rajpoot, N.: PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification. In: Reyes-Aldasoro, C.C., Janowczyk, A., Veta, M., Bankhead, P., Sirinukunwattana, K. (eds.) ECDP 2019. LNCS, vol. 11435, pp. 11–19. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-23937-4_2

    Chapter  Google Scholar 

  11. Huang, J., et al.: O2u-net: a simple noisy label detection approach for deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3326–3334 (2019)

    Google Scholar 

  12. Kaggle: Ultrasound nerve segmentation. www.kaggle.com/c/ultrasound-nerve-segmentation

  13. Ke, Z., Qiu, D., Li, K., Yan, Q., Lau, R.W.H.: Guided collaborative training for pixel-wise semi-supervised learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 429–445. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_26

    Chapter  Google Scholar 

  14. Kim, S.W., et al.: Parallel feature pyramid network for object detection. In: Proceedings of the European Conference on Computer Vision, pp. 234–250 (2018)

    Google Scholar 

  15. Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)

  16. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  17. Luo, X., et al.: Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 318–329. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_30

    Chapter  Google Scholar 

  18. Qiao, S., et al.: Deep co-training for semi-supervised image recognition. In: Proceedings of the European Conference on Computer Vision, pp. 135–152 (2018)

    Google Scholar 

  19. 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 

  20. Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1195–1204 (2017)

    Google Scholar 

  21. Verma, V., et al.: Interpolation consistency training for semi-supervised learning. In: International Joint Conference on Artificial Intelligence, pp. 3635–3641 (2019)

    Google Scholar 

  22. Vu, T.H., et al.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2517–2526 (2019)

    Google Scholar 

  23. Wang, Z., Zhang, Z., Voiculescu, I.: RAR-U-Net: a residual encoder to attention decoder by residual connections framework for spine segmentation under noisy labels. In: Proceedings of the IEEE International Conference on Image Processing. IEEE (2021)

    Google Scholar 

  24. Wang, Z., et al.: Computationally-efficient vision transformer for medical image semantic segmentation via dual pseudo-label supervision. In: IEEE International Conference on Image Processing (ICIP) (2022)

    Google Scholar 

  25. Wang, Z., et al.: An uncertainty-aware transformer for MRI cardiac semantic segmentation via mean teachers. In: Yang, G., Aviles-Rivero, A., Roberts, M., Schönlieb, C.B., et al. (eds.) Medical Image Understanding and Analysis. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-12053-4_37

    Chapter  Google Scholar 

  26. Xia, Y., et al.: 3D semi-supervised learning with uncertainty-aware multi-view co-training. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3646–3655 (2020)

    Google Scholar 

  27. Yao, J., Burns, J.E., Munoz, H., Summers, R.M.: Detection of vertebral body fractures based on cortical shell unwrapping. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7512, pp. 509–516. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33454-2_63

    Chapter  Google Scholar 

  28. Yeghiazaryan, V., Voiculescu, I.D.: Family of boundary overlap metrics for the evaluation of medical image segmentation. SPIE J. Med. Imaging 5(1), 015006 (2018)

    Google Scholar 

  29. You, X., et al.: Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern Recogn. 44(10–11), 2314–2324 (2011)

    Article  Google Scholar 

  30. Yu, L., Wang, S., Li, X., Fu, C.-W., Heng, P.-A.: Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 605–613. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_67

    Chapter  Google Scholar 

  31. Zhang, Y., Yang, L., Chen, J., Fredericksen, M., Hughes, D.P., Chen, D.Z.: Deep adversarial networks for biomedical image segmentation utilizing unannotated images. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 408–416. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_47

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ziyang Wang .

Editor information

Editors and Affiliations

Appendices

A Algorithm of TriSegNet

The training of TriSegNet consists of four stages which is briefly illustrated in Algorithm 1. The code of TriSegNet will be publicly availableFootnote 2.

figure a

B The CNN Architecture of Multi-view Learning

To properly encourage the differences of the three views of feature learning on dense prediction, not only the data feed and initialization of parameters, but three different advanced CNN are proposed in TriSegNet. We utilize three different techniques for CNN i.e. skip connection, efficiently passing feature information through residual learning, and multi-scale feature learning. The parameters of three classifiers are briefly illustrated in Table 4 and the source code has been released onlineFootnote 3.

Table 3. The computation cost information of three classifier

C Evaluation Methods, Qualitative, and Quantitative Results

Table 2 reports the TriSegNet performance direct comparison with other algorithms with several strict and novel quantitative evaluation metrics to which the boundaries of the machine segmentation(MS) match those of the ground truth(GT), using the Directed Boundary Dice relative to GT (DBD\(_G\)), Directed Boundary Dice relative to MS (DBD\(_M\)) and Symmetric Boundary Dice (SBD).

In a von Neumann neighbourhood \(N_x\) of each pixel x on the boundary \(\partial G\) of the ground truth,

$$\begin{aligned} DBD_G=DBD(G, M)=\displaystyle \frac{\sum \limits _{x \in \partial G} \text {Dice}(N_x)}{\left| \partial G \right| } \end{aligned}$$
(4)
$$\begin{aligned} DBD_M=DBD(M, G)=\displaystyle \frac{\sum \limits _{x \in \partial M} \text {Dice}(N_Y)}{\left| \partial M \right| } \end{aligned}$$
(5)
$$\begin{aligned} SBD = \displaystyle \frac{\sum \limits _{x \in \partial G} DSC(N_x) + \sum \limits _{y \in \partial M} DSC(N_y)}{\left| \partial G \right| + \left| \partial M \right| } \end{aligned}$$
(6)

where Dice is \(Dice(N_x) = \frac{2 | G(N_x) \cap M(N_y)|}{| G(N_x)| + | M(N_y)|} \). The symmetric average is being brought down by DBD\(_G\) when the latter features isolated areas of false negative labels. These measures penalise mislabelled areas in the machine segmentation.

Some of example qualitative results on MRI Cardiac test set are briefly sketched in Fig. 4. Eight images are selected from MRI test set where the first row illustrates raw images. The rest of them illustrate the MS by each semi-supervised algorithm against GT where yellow, green, red, and black represent true positive, false negative, false positive and true negative at pixel level. The proposed method shows fewer false positive and false negative pixels, and significantly low HD as well, because the TriSegNet is beneficial with different views of high-level pixel-level classifier and proposed mixed boundary- and overlap-based loss function.

Fig. 4.
figure 4

Sample qualitative results on MRI cardiac test set

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, Z., Voiculescu, I. (2022). Triple-View Feature Learning for Medical Image Segmentation. In: Xu, X., Li, X., Mahapatra, D., Cheng, L., Petitjean, C., Fu, H. (eds) Resource-Efficient Medical Image Analysis. REMIA 2022. Lecture Notes in Computer Science, vol 13543. Springer, Cham. https://doi.org/10.1007/978-3-031-16876-5_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-16876-5_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-16875-8

  • Online ISBN: 978-3-031-16876-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics