Skip to main content

Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model

  • Conference paper
  • First Online:
Deep Generative Models (MICCAI 2023)

Abstract

Mitotic figure detection in histology images is a hard-to-define, yet clinically significant task, where labels are generated with pathologist interpretations and where there is no “gold-standard” independent ground-truth. However, it is well-established that these interpretation based labels are often unreliable, in part, due to differences in expertise levels and human subjectivity. In this paper, our goal is to shed light on the inherent uncertainty of mitosis labels and characterize the mitotic figure classification task in a human interpretable manner. We train a probabilistic diffusion model to synthesize patches of cell nuclei for a given mitosis label condition. Using this model, we can then generate a sequence of synthetic images that correspond to the same nucleus transitioning into the mitotic state. This allows us to identify different image features associated with mitosis, such as cytoplasm granularity, nuclear density, nuclear irregularity and high contrast between the nucleus and the cell body. Our approach offers a new tool for pathologists to interpret and communicate the features driving the decision to recognize a mitotic figure.

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

Access this chapter

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.

    https://github.com/lucidrains/denoising-diffusion-pytorch.

  2. 2.

    https://github.com/cagladbahadir/dpm-for-mitotic-figures.

References

  1. Albarqouni, S., Baur, C., Achilles, F., Belagiannis, V., Demirci, S., Navab, N.: Aggnet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE Trans. Med. Imaging 35(5), 1313–1321 (2016)

    Article  Google Scholar 

  2. Albayrak, A., Bilgin, G.: Mitosis detection using convolutional neural network based features. In: 2016 IEEE 17th International symposium on computational intelligence and informatics (CINTI), pp. 000335–000340. IEEE (2016)

    Google Scholar 

  3. Aubreville, M., et al.: Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region. Sci. Rep. 10(1), 1–11 (2020)

    Article  Google Scholar 

  4. Aubreville, M., et al.: Mitosis domain generalization in histopathology images-the midog challenge. Med. Image Anal. 84, 102699 (2023)

    Article  Google Scholar 

  5. Beevi, K.S., Nair, M.S., Bindu, G.: Automatic mitosis detection in breast histopathology images using convolutional neural network based deep transfer learning. Biocybern. Biomed. Eng. 39(1), 214–223 (2019)

    Article  Google Scholar 

  6. Bertram, C.A., Aubreville, M., Marzahl, C., Maier, A., Klopfleisch, R.: A large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor. Sci. Data 6(1), 1–9 (2019)

    Article  Google Scholar 

  7. Bertram, C.A., et al.: Are pathologist-defined labels reproducible? Comparison of the TUPAC16 mitotic figure dataset with an alternative set of labels. In: Cardoso, J., et al. (eds.) IMIMIC/MIL3ID/LABELS -2020. LNCS, vol. 12446, pp. 204–213. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61166-8_22

    Chapter  Google Scholar 

  8. Fick, R.H.J., Moshayedi, A., Roy, G., Dedieu, J., Petit, S., Hadj, S.B.: Domain-specific cycle-GAN augmentation improves domain generalizability for mitosis detection. In: Aubreville, M., Zimmerer, D., Heinrich, M. (eds.) MICCAI 2021. LNCS, vol. 13166, pp. 40–47. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97281-3_5

    Chapter  Google Scholar 

  9. Ganz, J., et al.: Automatic and explainable grading of meningiomas from histopathology images. In: MICCAI Workshop on Computational Pathology, pp. 69–80. PMLR (2021)

    Google Scholar 

  10. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840–6851 (2020)

    Google Scholar 

  11. Malon, C., et al.: Mitotic figure recognition: agreement among pathologists and computerized detector. Anal. Cell. Pathol. 35(2), 97–100 (2012)

    Article  Google Scholar 

  12. Moghadam, P.A., et al.: A morphology focused diffusion probabilistic model for synthesis of histopathology images. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2000–2009 (2023)

    Google Scholar 

  13. Roetzer-Pejrimovsky, T., et al.: the digital brain Tumour atlas, an open histopathology resource. Sci. Data 9(1), 55 (2022)

    Article  Google Scholar 

  14. Saha, M., Chakraborty, C., Racoceanu, D.: Efficient deep learning model for mitosis detection using breast histopathology images. Comput. Med. Imaging Graph. 64, 29–40 (2018)

    Article  Google Scholar 

  15. Sanchez, P., Kascenas, A., Liu, X., O’Neil, A.Q., Tsaftaris, S.A.: What is healthy? Generative counterfactual diffusion for lesion localization. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds.) DGM4MICCAI 2022. LNCS, vol. 13609, pp. 34–44. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-18576-2_4

    Chapter  Google Scholar 

  16. Sebai, M., Wang, T., Al-Fadhli, S.A.: Partmitosis: a partially supervised deep learning framework for mitosis detection in breast cancer histopathology images. IEEE Access 8, 45133–45147 (2020)

    Article  Google Scholar 

  17. Sigirci, I.O., Albayrak, A., Bilgin, G.: Detection of mitotic cells in breast cancer histopathological images using deep versus handcrafted features. Multimedia Tools Appl. 81(10), 13179–13202 (2022)

    Article  Google Scholar 

  18. Sohail, A., Khan, A., Wahab, N., Zameer, A., Khan, S.: A multi-phase deep CNN based mitosis detection framework for breast cancer histopathological images. Sci. Rep. 11(1), 1–18 (2021)

    Article  Google Scholar 

  19. Thomas, R.P., et al.: The digital brain Tumour atlas, an open histopathology resource [data set]. https://doi.org/10.25493/WQ48-ZGX

  20. Veta, M., van Diest, P.J., Pluim, J.P.: Detecting mitotic figures in breast cancer histopathology images. In: Medical Imaging 2013: Digital Pathology, vol. 8676, pp. 70–76. SPIE (2013)

    Google Scholar 

  21. Wei, B.R., et al.: Agreement in histological assessment of mitotic activity between microscopy and digital whole slide images informs conversion for clinical diagnosis. Acad. Pathol. 6, 2374289519859841 (2019)

    Article  Google Scholar 

  22. Wilm, F., Marzahl, C., Breininger, K., Aubreville, M.: Domain adversarial RetinaNet as a reference algorithm for the MItosis DOmain generalization challenge. In: Aubreville, M., Zimmerer, D., Heinrich, M. (eds.) MICCAI 2021. LNCS, vol. 13166, pp. 5–13. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97281-3_1

    Chapter  Google Scholar 

  23. Wu, B., et al.: FF-CNN: an efficient deep neural network for mitosis detection in breast cancer histological images. In: Valdés Hernández, M., González-Castro, V. (eds.) MIUA 2017. CCIS, vol. 723, pp. 249–260. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60964-5_22

    Chapter  Google Scholar 

  24. Zehra, T., et al.: A novel deep learning-based mitosis recognition approach and dataset for uterine leiomyosarcoma histopathology. Cancers 14(15), 3785 (2022)

    Article  Google Scholar 

Download references

Acknowledgements

Funding for this project was partially provided by The New York-Presbyterian Hospital William Rhodes Center for Glioblastoma-Collaborative Research Initiative, a Weill Cornell Medicine Neurosurgery-Cornell Biomedical Engineering seed grant, The Burroughs Wellcome Weill Cornell Physician Scientist Program Award, NIH grant R01AG053949, and the NSF CAREER 1748377 grant. Project support for this study was provided by the Center for Translational Pathology of the Department of Pathology and Laboratory Medicine at Weill Cornell Medicine.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Cagla Deniz Bahadir .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 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

Bahadir, C.D., Liechty, B., Pisapia, D.J., Sabuncu, M.R. (2024). Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds) Deep Generative Models. MICCAI 2023. Lecture Notes in Computer Science, vol 14533. Springer, Cham. https://doi.org/10.1007/978-3-031-53767-7_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-53767-7_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-53766-0

  • Online ISBN: 978-3-031-53767-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics