Automated curation of large-scale cancer histopathology image datasets using deep learning

Research output: Contribution to journalResearch articleContributedpeer-review


  • Lars Hilgers - , RWTH Aachen University, Else Kröner-Fresenius Center for Digital Health (EKFZ) (Author)
  • Narmin Ghaffari Laleh - , Else Kröner Fresenius Center for Digital Health, RWTH Aachen University (Author)
  • Nicholas P. West - , University of Leeds (Author)
  • Alice Westwood - , University of Leeds (Author)
  • Katherine J. Hewitt - , Else Kröner Fresenius Center for Digital Health, RWTH Aachen University (Author)
  • Philip Quirke - , University of Leeds (Author)
  • Heike I. Grabsch - , University of Leeds, Maastricht University (Author)
  • Zunamys I. Carrero - , Else Kröner Fresenius Center for Digital Health (Author)
  • Emylou Matthaei - , Else Kröner-Fresenius Center for Digital Health (EKFZ) (Author)
  • Chiara M.L. Loeffler - , Else Kröner Fresenius Center for Digital Health (Author)
  • Titus J. Brinker - , German Cancer Research Center (DKFZ) (Author)
  • Tanwei Yuan - , German Cancer Research Center (DKFZ) (Author)
  • Hermann Brenner - , German Cancer Research Center (DKFZ) (Author)
  • Alexander Brobeil - , Heidelberg University  (Author)
  • Michael Hoffmeister - , German Cancer Research Center (DKFZ) (Author)
  • Jakob Nikolas Kather - , Else Kröner Fresenius Center for Digital Health, University of Leeds, Heidelberg University  (Author)


Background: Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient. Methods: We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide. Results: In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994–0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979–0.985] and 0.875 [95% CI: 0.864–0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort. Conclusion: Our findings show that using the low-resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations.


Original languageEnglish
Pages (from-to)1139-1153
Number of pages15
Issue number7
Publication statusPublished - Jun 2024

External IDs

PubMed 38409878
ORCID /0000-0001-8501-1566/work/159607726


Sustainable Development Goals


  • colorectal cancer, deep learning, digital pathology, quality control, Neural Networks, Computer, Colorectal Neoplasms/pathology, Humans, Image Processing, Computer-Assisted/methods, Image Interpretation, Computer-Assisted/methods, Deep Learning