Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Unsupervised Bias Discovery in Medical Image Segmentation

  • Conference paper
  • First Online:

Abstract

It has recently been shown that deep learning models for anatomical segmentation in medical images can exhibit biases against certain sub-populations defined in terms of protected attributes like sex or ethnicity. In this context, auditing fairness of deep segmentation models becomes crucial. However, such audit process generally requires access to ground-truth segmentation masks for the target population, which may not always be available, especially when going from development to deployment. Here we propose a new method to anticipate model biases in biomedical image segmentation in the absence of ground-truth annotations. Our unsupervised bias discovery method leverages the reverse classification accuracy framework to estimate segmentation quality. Through numerical experiments in synthetic and realistic scenarios we show how our method is able to successfully anticipate fairness issues in the absence of ground-truth labels, constituting a novel and valuable tool in this field.

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

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /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
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 12583
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 15729
Price includes VAT (Japan)
  • 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

Similar content being viewed by others

Notes

  1. 1.

    Code for the full RCA pipeline based on deep registration networks is publicly available athttps://github.com/ngaggion/UBD_SourceCode.

  2. 2.

    For JSRT, Montgomery and Shenzhen we used the original annotations. For PadChest, we used the annotations released in the Chest X-ray Landmark Database [7] publicly available athttps://github.com/ngaggion/Chest-xray-landmark-dataset.

References

  1. Bustos, A., Pertusa, A., Salinas, J.M., de la Iglesia-Vayá, M.: PadChest: a large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal.66, 101797 (2020)

    Article  Google Scholar 

  2. Candemir, S., et al.: Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans. Med. Imaging33(2), 577–590 (2014).https://doi.org/10.1109/TMI.2013.2290491

    Article  Google Scholar 

  3. Cubero, L., Serrano, J., Castelli, J., De Crevoisier, R., Acosta, O., Pascau, J.: Exploring uncertainty for clinical acceptability in head and neck deep learning-based oar segmentation. In: IEEE ISBI 2023. IEEE (2023)

    Google Scholar 

  4. Czolbe, S., Arnavaz, K., Krause, O., Feragen, A.: Is segmentation uncertainty useful? In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds.) IPMI 2021. LNCS, vol. 12729, pp. 715–726. Springer, Cham (2021).https://doi.org/10.1007/978-3-030-78191-0_55

    Chapter  Google Scholar 

  5. Fournel, J., et al.: Medical image segmentation automatic quality control: a multi-dimensional approach. Med. Image Anal.74, 102213 (2021)

    Article  Google Scholar 

  6. Fu, Y., Lei, Y., Wang, T., Curran, W.J., Liu, T., Yang, X.: A review of deep learning based methods for medical image multi-organ segmentation. Physica Med.85, 107–122 (2021)

    Article  Google Scholar 

  7. Gaggion, N., Mansilla, L., Mosquera, C., Milone, D.H., Ferrante, E.: Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis. IEEE Trans. Med. Imaging (2022).https://doi.org/10.1109/tmi.2022.3224660.https://doi.org/10.1109

  8. Gaggion, N., Vakalopoulou, M., Milone, D.H., Ferrante, E.: Multi-center anatomical segmentation with heterogeneous labels via landmark-based models. In: 20th IEEE International Symposium on Biomedical Imaging (ISBI). IEEE (2023)

    Google Scholar 

  9. Jaeger, S., et al.: Automatic tuberculosis screening using chest radiographs. IEEE Trans. Med. Imaging33(2), 233–245 (2014).https://doi.org/10.1109/TMI.2013.2284099

    Article  Google Scholar 

  10. Krishnakumar, A., Prabhu, V., Sudhakar, S., Hoffman, J.: UDIS: unsupervised discovery of bias in deep visual recognition models. In: British Machine Vision Conference (BMVC), vol. 1, p. 3 (2021)

    Google Scholar 

  11. Lahoti, P., et al.: Fairness without demographics through adversarially reweighted learning. Adv. Neural. Inf. Process. Syst.33, 728–740 (2020)

    Google Scholar 

  12. Larrazabal, A.J., Nieto, N., Peterson, V., Milone, D.H., Ferrante, E.: Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc. Natl. Acad. Sci.117(23), 12592–12594 (2020)

    Article  Google Scholar 

  13. Liu, X., Glocker, B., McCradden, M.M., Ghassemi, M., Denniston, A.K., Oakden-Rayner, L.: The medical algorithmic audit. Lancet Digit. Health4(5), e384–e397 (2022)

    Article  Google Scholar 

  14. Mansilla, L., Ferrante, E.: Segmentación multi-atlas de imágenes médicas con selección de atlas inteligente y control de calidad automático. In: XXIV Congreso Argentino de Ciencias de la Computación (La Plata, 2018) (2018)

    Google Scholar 

  15. Mansilla, L., Milone, D.H., Ferrante, E.: Learning deformable registration of medical images with anatomical constraints. Neural Netw.124, 269–279 (2020)

    Article  Google Scholar 

  16. Puyol-Antón, E., et al.: Fairness in cardiac MR image analysis: an investigation of bias due to data imbalance in deep learning based segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021, Part III. LNCS, vol. 12903, pp. 413–423. Springer, Cham (2021).https://doi.org/10.1007/978-3-030-87199-4_39

    Chapter  Google Scholar 

  17. Ricci Lara, M.A., Echeveste, R., Ferrante, E.: Addressing fairness in artificial intelligence for medical imaging. Nat. Commun.13(1), 1–6 (2022)

    Article  Google Scholar 

  18. 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, Part III. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  19. Schrouff, J., Chen, C., et al.: Diagnosing failures of fairness transfer across distribution shift in real-world medical settings. Adv. Neural. Inf. Process. Syst.35, 19304–19318 (2022)

    Google Scholar 

  20. Shiraishi, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am. J. Roentgenol.174(1), 71–74 (2000)

    Article  Google Scholar 

  21. Valindria, V.V., et al.: Reverse classification accuracy: predicting segmentation performance in the absence of ground truth. IEEE Trans. Med. Imaging36(8), 1597–1606 (2017)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by Argentina’s National Scientific and Technical Research Council (CONICET), which covered the salaries of E.F., R.E. and D.M., and the fellowships of N.G. and L.M. The authors gratefully acknowledge NVIDIA Corporation with the donation of the GPUs used for this research, and the support of Universidad Nacional del Litoral (Grants CAID-PIC-50220140100084LI, 50620190100145LI), ANPCyT (PICT-PRH-2019-00009) and the Google Award for Inclusion Research (AIR) Program.

Author information

Authors and Affiliations

  1. Research Institute for Signals, Systems and Computational Intelligence, sinc(i) (CONICET, Universidad Nacional del Litoral), Santa Fe, Argentina

    Nicolás Gaggion, Rodrigo Echeveste, Lucas Mansilla, Diego H. Milone & Enzo Ferrante

Authors
  1. Nicolás Gaggion

    You can also search for this author inPubMed Google Scholar

  2. Rodrigo Echeveste

    You can also search for this author inPubMed Google Scholar

  3. Lucas Mansilla

    You can also search for this author inPubMed Google Scholar

  4. Diego H. Milone

    You can also search for this author inPubMed Google Scholar

  5. Enzo Ferrante

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toNicolás Gaggion.

Editor information

Editors and Affiliations

  1. Fraunhofer-Institute for Computer Graphics Research (IGD), Darmstadt, Germany

    Stefan Wesarg

  2. King's College London, London, UK

    Esther Puyol Antón

  3. Université de Rennes, Rennes, France

    John S. H. Baxter

  4. Singapore, Singapore

    Marius Erdt

  5. Aachen University of Applied Sciences, Aachen, Germany

    Klaus Drechsler

  6. Fraunhofer-Institute for Computer Graphics Research (IGD), Darmstadt, Germany

    Cristina Oyarzun Laura

  7. Technion – Israel Institute of Technology, Haifa, Israel

    Moti Freiman

  8. Tongji University, Shanghai, China

    Yufei Chen

  9. Imperial College London, London, UK

    Islem Rekik

  10. Western University, London, ON, Canada

    Roy Eagleson

  11. Technical University of Denmark, Kgs Lyngby, Denmark

    Aasa Feragen

  12. King's College London, London, UK

    Andrew P. King

  13. University of Copenhagen, Copenhagen, Denmark

    Veronika Cheplygina

  14. University of Copenhagen, Copenhagen, Denmark

    Melani Ganz-Benjaminsen

  15. Universidad Nacional del Litoral, Santa Fe, Argentina

    Enzo Ferrante

  16. Imperial College London, London, UK

    Ben Glocker

  17. Vanderbilt University, Nashville, TN, USA

    Daniel Moyer

  18. Technical University of Denmark, Kgs. Lyngby, Denmark

    Eikel Petersen

Rights 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

Gaggion, N., Echeveste, R., Mansilla, L., Milone, D.H., Ferrante, E. (2023). Unsupervised Bias Discovery in Medical Image Segmentation. In: Wesarg, S.,et al. Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging. CLIP EPIMI FAIMI 2023 2023 2023. Lecture Notes in Computer Science, vol 14242. Springer, Cham. https://doi.org/10.1007/978-3-031-45249-9_26

Download citation

Publish with us

Societies and partnerships

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /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
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 12583
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 15729
Price includes VAT (Japan)
  • 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

[8]ページ先頭
©2009-2025 Movatter.jp