Skip to main content

Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin and Eosin-Stained Histological Images

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13540))

Abstract

Recently, pruning deep neural networks (DNNs) has received a lot of attention for improving accuracy and generalization power, reducing network size, and increasing inference speed on specialized hardwares. Although pruning was mainly tested on computer vision tasks, its application in the context of medical image analysis has hardly been explored. This work investigates the impact of well-known pruning techniques, namely layer-wise and network-wide magnitude pruning, on the nuclei instance segmentation performance in histological images. Our utilised instance segmentation model consists of two main branches: (1) a semantic segmentation branch, and (2) a deep regression branch. We investigate the impact of weight pruning on the performance of both branches separately, and on the final nuclei instance segmentation result. Evaluated on two publicly available datasets, our results show that layer-wise pruning delivers slightly better performance than network-wide pruning for small compression ratios (CRs) while for large CRs, network-wide pruning yields superior performance. For semantic segmentation, deep regression and final instance segmentation, 93.75%, 95%, and 80% of the model weights can be pruned by layer-wise pruning with less than 2% reduction in the performance of respective models.

Keywords

A. Mahbod—The first two authors contributed equally to this work.

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

Buying options

Chapter
EUR   29.95
Price includes VAT (France)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR   42.79
Price includes VAT (France)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR   52.74
Price includes VAT (France)
  • 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

Learn about institutional subscriptions

References

  1. Anwar, S.M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., Khan, M.K.: Medical image analysis using convolutional neural networks: a review. J. Med. Syst. 42(11), 1–13 (2018). https://doi.org/10.1007/s10916-018-1088-1

    Article  Google Scholar 

  2. Bancher, B., Mahbod, A., Ellinger, I., Ecker, R., Dorffner, G.: Improving mask r-cnn for nuclei instance segmentation in hematoxylin & eosin-stained histological images. In: MICCAI Workshop on Computational Pathology, pp. 20–35. PMLR (2021)

    Google Scholar 

  3. Entezari, R., Saukh, O.: Class-dependent compression of deep neural networks. In: Proceedings of the International Workshop on Machine Learning on Edge in Sensor Systems (2020)

    Google Scholar 

  4. Entezari, R., Saukh, O.: Class-dependent pruning of deep neural networks. In: IEEE Second Workshop on Machine Learning on Edge in Sensor Systems, pp. 13–18 (2020). https://doi.org/10.1109/SenSysML50931.2020.00010

  5. Graham, S., et al.: Hover-Net: simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med. Image Anal. 58, 101563 (2019). https://doi.org/10.1016/j.media.2019.101563

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

    Google Scholar 

  7. Hoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., Peste, A.: Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks. J. Mach. Learn. Res. 22(241), 1–124 (2021)

    MathSciNet  Google Scholar 

  8. Hooker, S., Courville, A., Clark, G., Dauphin, Y., Frome, A.: What do compressed deep neural networks forget? arXiv preprint arXiv:1911.05248 (2019)

  9. Jeong, T., Bollavaram, M., Delaye, E., Sirasao, A.: Neural network pruning for biomedical image segmentation. In: Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 11598, pp. 415–425. SPIE (2021). https://doi.org/10.1117/12.2579256

  10. Jørgensen, A.S., et al.: Using cell nuclei features to detect colon cancer tissue in hematoxylin and eosin stained slides. Cytometry Part A, 91(8), 785–793 (2017). https://doi.org/10.1002/cyto.a.23175, https://onlinelibrary.wiley.com/doi/abs/10.1002/cyto.a.23175

  11. Khan, S., Rahmani, H., Shah, S.A.A., Bennamoun, M.: A guide to convolutional neural networks for computer vision. Synth. Lect. Comput. Vis. 8(1), 1–207 (2018). https://doi.org/10.2200/S00822ED1V01Y201712COV015

    Article  Google Scholar 

  12. Kumar, N., et al.: A multi-organ nucleus segmentation challenge. IEEE Trans. Med. Imaging 39(5), 1380–1391 (2020). https://doi.org/10.1109/TMI.2019.2947628

    Article  Google Scholar 

  13. Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)

  14. Mahbod, A., Schaefer, G., Bancher, B., Löw, C., Dorffner, G., Ecker, R., Ellinger, I.: CryoNuSeg: a dataset for nuclei instance segmentation of cryosectioned H & E-stained histological images. Comput. Biol. Med. 132, 104349 (2021). https://doi.org/10.1016/j.compbiomed.2021.104349

    Article  Google Scholar 

  15. Mahbod, A., Schaefer, G., Ellinger, I., Ecker, R., Smedby, Ö., Wang, C.: A two-stage U-Net algorithm for segmentation of nuclei in H & E-stained tissues. In: Reyes-Aldasoro, C.C., Janowczyk, A., Veta, M., Bankhead, P., Sirinukunwattana, K. (eds.) ECDP 2019. LNCS, vol. 11435, pp. 75–82. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-23937-4_9

    Chapter  Google Scholar 

  16. Muckatira, S.: Properties of winning tickets on skin lesion classification. arXiv preprint arXiv:2008.12141 (2020)

  17. Naylor, P., Laé, M., Reyal, F., Walter, T.: Segmentation of nuclei in histopathology images by deep regression of the distance map. IEEE Trans. Med. Imaging 38(2), 448–459 (2019). https://doi.org/10.1109/TMI.2018.2865709

    Article  Google Scholar 

  18. Renda, A., Frankle, J., Carbin, M.: Comparing rewinding and fine-tuning in neural network pruning. arXiv preprint arXiv:2003.02389 (2020)

  19. Skinner, B.M., Johnson, E.E.P.: Nuclear morphologies: their diversity and functional relevance. Chromosoma 126(2), 195–212 (2016). https://doi.org/10.1007/s00412-016-0614-5

    Article  Google Scholar 

  20. Zhou, A., et al.: Learning n: M fine-grained structured sparse neural networks from scratch. arXiv preprint arXiv:2102.04010 (2021)

Download references

Acknowledgements

This project was supported by the Austrian Research Promotion Agency (FFG), No. 872636. This study was conducted retrospectively using human subject data made available through open access. Ethical approval was not required as confirmed by the license attached with the open access data.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Amirreza Mahbod .

Editor information

Editors and Affiliations

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

Mahbod, A., Entezari, R., Ellinger, I., Saukh, O. (2022). Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin and Eosin-Stained Histological Images. In: Wu, S., Shabestari, B., Xing, L. (eds) Applications of Medical Artificial Intelligence. AMAI 2022. Lecture Notes in Computer Science, vol 13540. Springer, Cham. https://doi.org/10.1007/978-3-031-17721-7_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-17721-7_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-17720-0

  • Online ISBN: 978-3-031-17721-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics