Skip to main content
Springer Nature Link
Log in

Leveraging Point Annotations in Segmentation Learning with Boundary Loss

  • Conference paper
  • First Online:
Pattern Recognition (ICPR 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15313))

Included in the following conference series:

  • 193 Accesses

Abstract

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design, the boundary loss imposes a stronger penalty on the errors the farther away from the object boundary they occur. Hence it is inappropriate for cases of weak supervision where the ground truth label is much smaller than the actual object and a certain amount of false positives (w.r.t. the weak ground truth) is actually desirable. Using intensity-aware distances instead may alleviate this drawback, allowing for a certain amount of false positives with similar intensities without a significant increase to the training loss. This formulation is potentially more attractive than existing CRF-based regularizers, due to its simplicity and computational efficiency. We perform experiments on two multi-class datasets; ACDC (heart segmentation) and POEM (whole-body abdominal organ segmentation). Results are encouraging and show that this supervision strategy has great potential. On ACDC it outperforms the CRF-loss based approach, and on POEM data it performs on par with it. The code is made openly available.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Base code available at https://github.com/FilipMalmberg/DistanceTransforms.

References

  1. Asad, M., Dorent, R., Vercauteren, T.: FastGeodis: fast generalised geodesic distance transform. arXiv preprint arXiv:2208.00001 (2022)

  2. Bai, X., Sapiro, G.: Geodesic matting: a framework for fast interactive image and video segmentation and matting. Int. J. Comput. Vis. 82, 113–132 (2009). https://doi.org/10.1007/s11263-008-0191-z

    Article  Google Scholar 

  3. Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What’s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549–565. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_34

    Chapter  Google Scholar 

  4. 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 

  5. Chen, Z., et al.: Weakly supervised histopathology image segmentation with sparse point annotations. IEEE J. Biomed. Health Inform. 25(5), 1673–1685 (2020)

    Article  Google Scholar 

  6. Criminisi, A., Sharp, T., Blake, A.: GeoS: geodesic image segmentation. In: ECCV 2008, pp. 99–112 (2008)

    Google Scholar 

  7. Dai, J., He, K., Sun, J.: BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1635–1643 (2015). https://doi.org/10.1109/ICCV.2015.191

  8. Dubost, F., et al.: Weakly supervised object detection with 2D and 3D regression neural networks. Med. Image Anal. 65, 101767 (2020). https://doi.org/10.1016/j.media.2020.101767

    Article  Google Scholar 

  9. Fan, J., Zhang, Z., Song, C., Tan, T.: Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  10. Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3129–3136 (2010). https://doi.org/10.1109/CVPR.2010.5540073

  11. Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)

    Article  Google Scholar 

  12. Ji, Z., Shen, Y., Ma, C., Gao, M.: Scribble-based hierarchical weakly supervised learning for brain tumor segmentation. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, pp. 175–183 (2019)

    Google Scholar 

  13. Kervadec, H., Bouchtiba, J., Desrosiers, C., Granger, E., Dolz, J., Ayed, I.B.: Boundary loss for highly unbalanced segmentation. Med. Image Anal. 67, 101851 (2021)

    Article  Google Scholar 

  14. Kervadec, H., Dolz, J., Tang, M., Granger, E., Boykov, Y., Ben Ayed, I.: Constrained-CNN losses for weakly supervised segmentation. Med. Image Anal. 54, 88–99 (2019)

    Article  Google Scholar 

  15. Kervadec, H., Dolz, J., Wang, S., Granger, E., Ayed, I.B.: Bounding boxes for weakly supervised segmentation: global constraints get close to full supervision. In: Medical Imaging with Deep Learning, pp. 365–381. PMLR (2020)

    Google Scholar 

  16. Kim, B., Jeong, J., Han, D., Hwang, S.J.: The devil is in the points: weakly semi-supervised instance segmentation via point-guided mask representation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11360–11370 (2023)

    Google Scholar 

  17. Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems 24, pp. 109–117. Curran Associates, Inc. (2011)

    Google Scholar 

  18. Lin, D., Dai, J., Jia, J., He, K., Sun, J.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp. 3159–3167 (2016)

    Google Scholar 

  19. Lind, L.: Relationships between three different tests to evaluate endothelium-dependent vasodilation and cardiovascular risk in a middle-aged sample. J. Hypertens. 31, 1570–1574 (2013). https://doi.org/10.1097/HJH.0b013e3283619d50

    Article  Google Scholar 

  20. Liu, W., He, Q., He, X.: Weakly supervised nuclei segmentation via instance learning. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE (2022)

    Google Scholar 

  21. Ma, J., et al.: How distance transform maps boost segmentation CNNs: an empirical study. In: Medical Imaging with Deep Learning. Proceedings of Machine Learning Research, vol. 121, pp. 479–492. PMLR (2020). https://proceedings.mlr.press/v121/ma20b.html

  22. Mortazi, A., Khosravan, N., Torigian, D.A., Kurugol, S., Bagci, U.: Weakly supervised segmentation by a deep geodesic prior. In: Suk, H.I., Liu, M., Yan, P., Lian, C. (eds.) Machine Learning in Medical Imaging, pp. 238–246. Springer, Cham (2019)

    Chapter  Google Scholar 

  23. Ngoc, M.Õ.V., Boutry, N., Fabrizio, J., Géraud, T.: A minimum barrier distance for multivariate images with applications. Comput. Vis. Image Underst. 197–198, 102993 (2020). https://doi.org/10.1016/j.cviu.2020.102993

    Article  Google Scholar 

  24. Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation (2016). https://doi.org/10.48550/ARXIV.1606.02147

  25. Qu, H., et al.: Weakly supervised deep nuclei segmentation using points annotation in histopathology images. In: Medical Imaging with Deep Learning. Proceedings of Machine Learning Research, vol. 102, pp. 390–400. PMLR (2019). https://proceedings.mlr.press/v102/qu19a.html

  26. Rajchl, M., et al.: DeepCut: object segmentation from bounding box annotations using convolutional neural networks. IEEE Trans. Med. Imaging 36(2), 674–683 (2017). https://doi.org/10.1109/TMI.2016.2621185

    Article  Google Scholar 

  27. Strand, R., Ciesielski, K.C., Malmberg, F., Saha, P.K.: The minimum barrier distance. Comput. Vis. Image Underst. 117(4), 429–437 (2013). Special Issue on Discrete Geometry for Computer Imagery

    Google Scholar 

  28. Tang, M., Djelouah, A., Perazzi, F., Boykov, Y., Schroers, C.: Normalized cut loss for weakly-supervised CNN segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1818–1827 (2018). https://doi.org/10.1109/CVPR.2018.00195

  29. Tang, M., Perazzi, F., Djelouah, A., Ben Ayed, I., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised CNN segmentation. In: European Conference on Computer Vision (ECCV), Part XVI, pp. 524–540 (2018)

    Google Scholar 

  30. Toivanen, P.J.: New geodesic distance transforms for gray-scale images. Pattern Recogn. Lett. 17(5), 437–450 (1996). https://doi.org/10.1016/0167-8655(96)00010-4

    Article  Google Scholar 

  31. Wang, G., et al.: DeepIGeoS: a deep interactive geodesic framework for medical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1559–1572 (2019). https://doi.org/10.1109/TPAMI.2018.2840695

    Article  Google Scholar 

  32. Xu, J., Schwing, A.G., Urtasun, R.: Learning to segment under various forms of weak supervision. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3781–3790 (2015). https://doi.org/10.1109/CVPR.2015.7299002

  33. Yao, J., et al.: Position-based anchor optimization for point supervised dense nuclei detection. Neural Netw. 171, 159–170 (2024)

    Article  Google Scholar 

  34. Zheng, S., et al.: Conditional random fields as recurrent neural networks, pp. 1529–1537 (2015)

    Google Scholar 

  35. Zhou, Y., et al.: Prior-aware neural network for partially-supervised multi-organ segmentation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10671–10680 (2019). https://doi.org/10.1109/ICCV.2019.01077

Download references

Acknowledgements

EB was partially funded by the Centre for interdisciplinary mathematics (CIM), Uppsala University. HK and MdB were funded by the Dutch Research Council (NWO), VI.C.182.042.

Author information

Authors and Affiliations

  1. Department of Information Technology, Uppsala University, Uppsala, Sweden

    Eva Breznik, Filip Malmberg & Robin Strand

  2. Department of Biomedical Engineering and Health Systems, Royal Institute of Technology, Stockholm, Sweden

    Eva Breznik

  3. Antaros Medical, Mölndal, Sweden

    Joel Kullberg

  4. Department of Surgical Sciences, Uppsala University, Uppsala, Sweden

    Joel Kullberg, Håkan Ahlström & Robin Strand

  5. Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands

    Hoel Kervadec & Marleen de Bruijne

  6. Department of Computer Science, University of Copenhagen, Copenhagen, Denmark

    Marleen de Bruijne

Authors
  1. Eva Breznik
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hoel Kervadec
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Filip Malmberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joel Kullberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Håkan Ahlström
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Marleen de Bruijne
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Robin Strand
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Eva Breznik .

Editor information

Editors and Affiliations

  1. University of Salford, Salford, Lancashire, UK

    Apostolos Antonacopoulos

  2. IIT Bombay, Powai, Mumbai, Maharashtra, India

    Subhasis Chaudhuri

  3. Johns Hopkins University, Baltimore, MD, USA

    Rama Chellappa

  4. Chinese Academy of Sciences, Beijing, China

    Cheng-Lin Liu

  5. IIT Kharagpur, Kharagpur, West Bengal, India

    Saumik Bhattacharya

  6. Indian Statistical Institute, Kolkata, West Bengal, India

    Umapada Pal

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 4870 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Breznik, E. et al. (2025). Leveraging Point Annotations in Segmentation Learning with Boundary Loss. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15313. Springer, Cham. https://doi.org/10.1007/978-3-031-78201-5_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-78201-5_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-78200-8

  • Online ISBN: 978-3-031-78201-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships