From detection of individual metastases to classification of lymph node status at the patient level: the CAMELYON17 challenge

Peter Bandi*, Oscar Geessink, Quirine Manson, Marcory van Dijk, Maschenka Balkenhol, Meyke Hermsen, Babak Ehteshami Bejnordi, Byungjae Lee, Kyunghyun Paeng, Aoxiao Zhong, Quanzheng Li, Farhad Ghazvinian Zanjani, Svitlana Zinger, Keisuke Fukuta, Daisuke Komura, Vlado Ovtcharov, Shenghua Cheng, Shaoqun Zeng, Jeppe Thagaard, Anders Bjorholm DahlHuangjing Lin, Hao Chen, Ludwig Jacobsson, Martin Hedlund, Melih Cetin, Eren Halici, Hunter Jackson, Richard Chen, Fabian Both, Jorg Franke, Heidi Kusters-Vandevelde, Willem Vreuls, Peter Bult, Bram van Ginneken, Jeroen van der Laak, Geert Litjens

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

196 Downloads (Pure)

Abstract

Automated detection of cancer metastases in lymph nodes has the potential to improve assessment of prognosis for patients. To enable fair comparison between the algorithms for this purpose, we set up the CAMELYON17 challenge in conjunction with the IEEE International Symposium on Biomedical Imaging 2017 conference in Melbourne. Over 300 participants registered on the challenge website, of which 23 teams submitted a total of 37 algorithms before the initial deadline. Participants were provided with 899 whole-slide images for developing their algorithms. The developed algorithms were evaluated based on the test set encompassing 100 patients and 500 whole-slide images. The evaluation metric used was a quadratic weighted Cohen’s kappa. We discuss the algorithmic details of the ten best pre-conference and two post-conference submissions. All these participants used convolutional neural networks in combination with pre-and postprocessing steps. Algorithms differed mostly in neural network architecture, training strategy and pre-and postprocessing methodology. Overall, the kappa metric ranged from 0.89 to -0.13 across all submissions. The best results were obtained with pre-trained architectures such as ResNet. Confusion matrix analysis revealed that all participants struggled with reliably identifying isolated tumor cells, the smallest type of metastasis, with detection rates below 40%. Qualitative inspection of the results of the top participants showed categories of false positives, such as nerves or contamination, which could be targets for further optimization. Last, we show that simple combinations of the top algorithms result in higher kappa metric values than any algorithm individually, with 0.93 for the best combination.
Original languageEnglish
JournalI E E E Transactions on Medical Imaging
Volume38
Issue number2
Pages (from-to)550-560
Number of pages11
ISSN0278-0062
DOIs
Publication statusPublished - 2018

Keywords

  • Breast cancer
  • Sentinel lymph node
  • Lymph node metastases
  • Whole-slide images
  • Grand challenge

Cite this

Bandi, P., Geessink, O., Manson, Q., van Dijk, M., Balkenhol, M., Hermsen, M., Bejnordi, B. E., Lee, B., Paeng, K., Zhong, A., Li, Q., Zanjani, F. G., Zinger, S., Fukuta, K., Komura, D., Ovtcharov, V., Cheng, S., Zeng, S., Thagaard, J., ... Litjens, G. (2018). From detection of individual metastases to classification of lymph node status at the patient level: the CAMELYON17 challenge. I E E E Transactions on Medical Imaging, 38(2), 550-560. https://doi.org/10.1109/TMI.2018.2867350