Skip to main content

Robust T-Loss for Medical Image Segmentation

  • Conference paper
  • First Online:
Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 (MICCAI 2023)

Abstract

This paper presents a new robust loss function, the T-Loss, for medical image segmentation. The proposed loss is based on the negative log-likelihood of the Student-t distribution and can effectively handle outliers in the data by controlling its sensitivity with a single parameter. This parameter is updated during the backpropagation process, eliminating the need for additional computation or prior information about the level and spread of noisy labels. Our experiments show that the T-Loss outperforms traditional loss functions in terms of dice scores on two public medical datasets for skin lesion and lung segmentation. We also demonstrate the ability of T-Loss to handle different types of simulated label noise, resembling human error. Our results provide strong evidence that the T-Loss is a promising alternative for medical image segmentation where high levels of noise or outliers in the dataset are a typical phenomenon in practice. The project website can be found at https://robust-tloss.github.io.

M. Pouly and A. A. Navarini—Joint last authorship.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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/gaozhitong/SP_guided_Noisy_Label_Seg.

References

  1. Amruthalingam, L., et al.: Objective hand eczema severity assessment with automated lesion anatomical stratification. Exp. Dermatol. exd.14744 (2023). https://doi.org/10.1111/exd.14744

  2. Barron, J.T.: A general and adaptive robust loss function. In: CVPR, pp. 4331–4339 (2019)

    Google Scholar 

  3. Bishop, C.M.: Pattern recognition and machine learning. Inf. Sci. Stat. (2006)

    Google Scholar 

  4. Candemir, S., et al.: Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. TMI 33(2), 577–590 (2014). https://doi.org/10.1109/tmi.2013.2290491

    Article  Google Scholar 

  5. Codella, N.C.F., et al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: ISBI, pp. 168–172 (2018). https://doi.org/10.1109/ISBI.2018.8363547

  6. Dlova, N., et al.: Prevalence of skin diseases treated at public referral hospitals in KwaZulu-Natal, South Africa. Br. J. Dermatol. 178 (2017). https://doi.org/10.1111/bjd.15534

  7. Forbes, F., Wraith, D.: A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweight: application to robust clustering. Stat. Comput. 24(6), 971–984 (2013). https://doi.org/10.1007/s11222-013-9414-4

    Article  MathSciNet  MATH  Google Scholar 

  8. Ghosh, A., Kumar, H., Sastry, P.S.: Robust loss functions under label noise for deep neural networks. In: AAAI, pp. 1919–1925 (2017)

    Google Scholar 

  9. Girden, E.R.: ANOVA: Repeated Measures. No. no. 07–084 in Sage University Papers. Quantitative Applications in the Social Sciences (1992)

    Google Scholar 

  10. Groh, M., et al.: Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset. In: CVPRW, pp. 1820–1828 (2021). https://doi.org/10.1109/CVPRW53098.2021.00201

  11. Gurari, D., et al.: How to collect segmentations for biomedical images? A benchmark evaluating the performance of experts, crowdsourced non-experts, and algorithms. In: WACV, pp. 1169–1176 (2015). https://doi.org/10.1109/WACV.2015.160

  12. Isensee, F., Jaeger, P.F., Kohl, S.A.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). https://doi.org/10.1038/s41592-020-01008-z

    Article  Google Scholar 

  13. Jaeger, S., et al.: Automatic tuberculosis screening using chest radiographs. TMI 33(2), 233–245 (2014). https://doi.org/10.1109/tmi.2013.2284099

    Article  Google Scholar 

  14. Keselman, H.J., Rogan, J.C.: The Tukey multiple comparison test: 1953–1976. Psychol. Bull. 84(5), 1050–1056 (1977). https://doi.org/10.1037/0033-2909.84.5.1050

    Article  Google Scholar 

  15. Li, S., Gao, Z., He, X.: Superpixel-guided iterative learning from noisy labels for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 525–535. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_50

    Chapter  Google Scholar 

  16. Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017). https://doi.org/10.1016/j.media.2017.07.005

    Article  Google Scholar 

  17. Liu, S., Liu, K., Zhu, W., Shen, Y., Fernandez-Granda, C.: Adaptive early-learning correction for segmentation from noisy annotations. In: CVPR, pp. 2596–2606 (2022). https://doi.org/10.1109/CVPR52688.2022.00263

  18. Ma, X., Huang, H., Wang, Y., Romano, S., Erfani, S.M., Bailey, J.: Normalized loss functions for deep learning with noisy labels. In: ICML, vol. 119, pp. 6543–6553 (2020)

    Google Scholar 

  19. Murphy, K.P.: Machine Learning: A Probabilistic Perspective. Illustrated edition (2012)

    Google Scholar 

  20. Nettleton, D.F., Orriols-Puig, A., Fornells, A.: A study of the effect of different types of noise on the precision of supervised learning techniques. Artif. Intell. Rev. 33(4), 275–306 (2010). https://doi.org/10.1007/s10462-010-9156-z

    Article  Google Scholar 

  21. Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: CVPR, pp. 2233–2241 (2017). https://doi.org/10.1109/CVPR.2017.240

  22. Pechenizkiy, M., Tsymbal, A., Puuronen, S., Pechenizkiy, O.: Class noise and supervised learning in medical domains: the effect of feature extraction. In: CBMS, pp. 708–713 (2006). https://doi.org/10.1109/CBMS.2006.65

  23. Ribeiro, V., Avila, S., Valle, E.: Handling inter annotator agreement for automated skin lesion segmentation (2019)

    Google Scholar 

  24. Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19(1), 221–248 (2017). https://doi.org/10.1146/annurev-bioeng-071516-044442

    Article  Google Scholar 

  25. Stirenko, S., et al.: Chest X-ray analysis of tuberculosis by deep learning with segmentation and augmentation. In: ELNANO (2018). https://doi.org/10.1109/elnano.2018.8477564

  26. Sun, J., Kabán, A., Garibaldi, J.M.: Robust mixture clustering using Pearson type VII distribution. Pattern Recogn. Lett. 31(16), 2447–2454 (2010). https://doi.org/10.1016/j.patrec.2010.07.015

    Article  Google Scholar 

  27. Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: CVPR, pp. 2691–2699 (2015). https://doi.org/10.1109/CVPR.2015.7298885

  28. Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A., Belongie, S.: Learning from noisy large-scale datasets with minimal supervision. In: CVPR, pp. 6575–6583 (2017). https://doi.org/10.1109/CVPR.2017.696

  29. Wang, G., et al.: A noise-robust framework for automatic segmentation of COVID-19 pneumonia lesions from CT images. TMI 39(8), 2653–2663 (2020). https://doi.org/10.1109/TMI.2020.3000314

    Article  Google Scholar 

  30. Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., Bailey, J.: Symmetric cross entropy for robust learning with noisy labels. In: ICCV, pp. 322–330 (2019). https://doi.org/10.1109/ICCV.2019.00041

  31. Yan, K., Wang, X., Lu, L., Summers, R.M.: DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J. Med. Imaging 5(03), 1 (2018). https://doi.org/10.1117/1.JMI.5.3.036501

    Article  Google Scholar 

  32. Yang, S., et al.: Estimating instance-dependent Bayes-label transition matrix using a deep neural network. In: ICML, pp. 25302–25312 (2022)

    Google Scholar 

  33. Yao, Y., et al.: Dual T: reducing estimation error for transition matrix in label-noise learning. In: NeurIPS, vol. 33, pp. 7260–7271 (2020)

    Google Scholar 

  34. Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: NeurIPS, vol. 31 (2018)

    Google Scholar 

  35. Zhu, X., Wu, X.: Class noise vs. attribute noise: a quantitative study. Artif. Intell. Rev. 22(3), 177–210 (2004). https://doi.org/10.1007/s10462-004-0751-8

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Alvaro Gonzalez-Jimenez .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 349 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Gonzalez-Jimenez, A., Lionetti, S., Gottfrois, P., Gröger, F., Pouly, M., Navarini, A.A. (2023). Robust T-Loss for Medical Image Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14222. Springer, Cham. https://doi.org/10.1007/978-3-031-43898-1_68

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-43898-1_68

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-43897-4

  • Online ISBN: 978-3-031-43898-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics