Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Lessons from the first DBTex Challenge

Nature Machine Intelligence volume 3, pages 735–736 (2021)Cite this article

Subjects

A new international competition aims to speed up the development of AI models that can assist radiologists in detecting suspicious lesions from hundreds of millions of pixels in 3D mammograms. The top three winning teams compare notes.

Although screening based on 3D mammography is more accurate than on 2D mammography, its interpretation time, of about 70 slices per volume, is almost doubled1. Even when radiologists are aware of an existing lesion, for example, due to a physical examination showing a palpable mass, they need to identify the slices that encompass the suspicious lesion. It was recently shown that deep learning has the potential to achieve good performance in automatically detecting suspicious lesions in DBT, thus saving radiologists substantial time. Up to now, however, these deep learning approaches were never compared using a consistent evaluation mechanism due to the lack of public DBT datasets.

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

Buy

All prices are NET prices.

Fig. 1: Example outputs of breast lesion detection on DBT volumes from NYU.

References

  1. Aase, H. S. et al. Eur. Radiol. 29, 1175–1186 (2019).

    Article  Google Scholar 

  2. Buda, M. et al. Preprint at https://arxiv.org/abs/2011.07995 (2020).

  3. Clark, K. et al. J. Digit. Imaging 26, 1045–1057 (2013).

    Article  Google Scholar 

  4. Buda, M. et al. Data from the breast cancer screening — digital breast tomosynthesis (BCS-DBT). The Cancer Imaging Archive https://go.nature.com/2T3Y7bg (2020).

  5. Grand Challenge: Digital Breast Tomosynthesis Lesion Detection (SPIE, 2021); https://go.nature.com/3eklWDd

  6. Shoshan, Y. et al. In Medical Image Computing and Computer Assisted Intervention (eds de Bruijne, M. et al.) (Springer, 2021).

Download references

Author information

Author notes

  1. These authors contributed equally: Jungkyu Park, Yoel Shoshan, Robert Martí.

  2. These authors jointly supervised this work: Michal Rosen-Zvi, Krzysztof J. Geras.

Affiliations

  1. Department of Radiology, NYU Grossman School of Medicine, New York, NY, USA

    Jungkyu Park, Jakub Chłędowski, Jan Witowski, Alexandra Millet, Eric Kim, Alana Lewin, Kristine Pysarenko, Sardius Chen, Julia Goldberg, Shalin Patel, Anastasia Plaunova, Melanie Wegener, Stacey Wolfson, Jiyon Lee, Sana Hava, Sindhoora Murthy, Linda Du, Sushma Gaddam, Ujas Parikh, Laura Heacock, Linda Moy, Beatriu Reig & Krzysztof J. Geras

  2. Medical Image Analytics, IBM Research, Haifa, Israel

    Yoel Shoshan, Vadim Ratner, Daniel Khapun, Aviad Zlotnick, Ella Barkan, Flora Gilboa-Solomon & Michal Rosen-Zvi

  3. Institute of Computer Vision and Robotics, University of Girona, Girona, Spain

    Robert Martí & Pablo Gómez del Campo

  4. Jagiellonian University, Faculty of Mathematics and Information Technologies, Kraków, Poland

    Jakub Chłędowski

Authors
  1. Jungkyu Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoel Shoshan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Robert Martí
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pablo Gómez del Campo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Vadim Ratner
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Daniel Khapun
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Aviad Zlotnick
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Ella Barkan
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Flora Gilboa-Solomon
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Jakub Chłędowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Jan Witowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Alexandra Millet
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Eric Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Alana Lewin
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Kristine Pysarenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Sardius Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Julia Goldberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Shalin Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Anastasia Plaunova
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Melanie Wegener
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Stacey Wolfson
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Jiyon Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  23. Sana Hava
    View author publications

    You can also search for this author in PubMed Google Scholar

  24. Sindhoora Murthy
    View author publications

    You can also search for this author in PubMed Google Scholar

  25. Linda Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  26. Sushma Gaddam
    View author publications

    You can also search for this author in PubMed Google Scholar

  27. Ujas Parikh
    View author publications

    You can also search for this author in PubMed Google Scholar

  28. Laura Heacock
    View author publications

    You can also search for this author in PubMed Google Scholar

  29. Linda Moy
    View author publications

    You can also search for this author in PubMed Google Scholar

  30. Beatriu Reig
    View author publications

    You can also search for this author in PubMed Google Scholar

  31. Michal Rosen-Zvi
    View author publications

    You can also search for this author in PubMed Google Scholar

  32. Krzysztof J. Geras
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yoel Shoshan, Robert Martí or Krzysztof J. Geras.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Park, J., Shoshan, Y., Martí, R. et al. Lessons from the first DBTex Challenge. Nat Mach Intell 3, 735–736 (2021). https://doi.org/10.1038/s42256-021-00378-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-021-00378-z

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing