Less unnecessary surgery and adjuvant therapy for prostate cancer patients through digital pathology and deep learning

Most men die with, not because of prostate cancer. This high incidence-to-mortality ratio sounds like a positive trait, but comes with its own share of problems: high risk of overdiagnosis and overtreatment with significant patient morbidity. To combat overtreatment, several models have been developed to assign patients to risk categories with differing treatment regimes. Although these models show good correlation with patient outcome on the group level, their benefit for the individual patient remains limited.

Several groups have shown that quantifying the tumour and its micro-environment at the cellular level can result in biomarkers with strong prognostic potential, for example tumour/stroma ratio, the presence and composition of immune infiltrates or the amount of proliferating (Ki67-positive) cells. However, these findings have not translated to clinical practice due to the cumbersome and subjective manual extraction of these biomarkers from tissue slides.

Recent years have seen the more widespread introduction of whole-slide imaging systems, which for the first time allow computerized processing of tissue slides. Automated extraction of aforementioned quantitative biomarkers through image analysis can achieve the required accuracy and robustness to impact clinical practice. In tandem with these developments, computer vision has seen a machine learning revolution over the past decade due to the advent of deep learning.

Prostate cancer detection

In this project, we will combine deep learning and digitized whole-slide imaging of prostate cancer for reproducible extraction of quantitative biomarkers. Furthermore, due to the ability of deep learning systems to learn relevant features without human intervention, we expect to identify novel biomarkers which allow us to further improve the current risk models.

The aim of this project is to prevent unnecessary surgery and adjuvant therapy for individual patients by improving currently established risk models. Risk models will be enhanced through the addition of pre- and post-operative quantitative biomarkers obtained via image analysis and deep learning. We will focus both on the accurate and objective quantification of biomarkers already identified in literature and the discovery of novel biomarkers.

Funding

People

Geert Litjens

Geert Litjens

Professor

Wouter Bulten

Wouter Bulten

PhD Candidate

Hans Pinckaers

Hans Pinckaers

PhD Candidate

Bram van Ginneken

Bram van Ginneken

Professor, Scientific Co-Director

Diagnostic Image Analysis Group

Publications

  • W. Bulten, H. Pinckaers, H. van Boven, R. Vink, T. de Bel, B. van Ginneken, J. van der Laak, C. de Hulsbergen-van Kaa and G. Litjens, "Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study", Lancet Oncology, 2020;21(2):233-241.
  • W. Bulten, M. Balkenhol, J. Belinga, A. Brilhante, A. Çakır, L. Egevad, M. Eklund, X. Farré, K. Geronatsiou, V. Molinié, G. Pereira, P. Roy, G. Saile, P. Salles, E. Schaafsma, J. Tschui, A. Vos, B. Delahunt, H. Samaratunga, D. Grignon, A. Evans, D. Berney, C. Pan, G. Kristiansen, J. Kench, J. Oxley, K. Leite, J. McKenney, P. Humphrey, S. Fine, T. Tsuzuki, M. Varma, M. Zhou, E. Comperat, D. Bostwick, K. Iczkowski, C. Magi-Galluzzi, J. Srigley, H. Takahashi, T. van der Kwast, H. van Boven, R. Vink, J. van der Laak, C. der Hulsbergen-van Kaa and G. Litjens, "Artificial Intelligence Assistance Significantly Improves Gleason Grading of Prostate Biopsies by Pathologists", Modern Pathology, 2020.
  • W. Bulten, C. de Kaa, J. van der Laak and G. Litjens, "Automated segmentation of epithelial tissue in prostatectomy slides using deep learning", Medical Imaging, 2018;10581:105810S.
  • W. Bulten, P. Bándi, J. Hoven, R. van de Loo, J. Lotz, N. Weiss, J. van der Laak, B. van Ginneken, C. Hulsbergen-van de Kaa and G. Litjens, "Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard", Scientific Reports, 2019;9(1).
  • H. Pinckaers, W. Bulten and G. Litjens, "High resolution whole prostate biopsy classification using streaming stochastic gradient descent", Medical Imaging, 2019(1).
  • K. Dercksen, W. Bulten and G. Litjens, "Dealing with Label Scarcity in Computational Pathology: A Use Case in Prostate Cancer Classification", Medical Imaging with Deep Learning, 2019.
  • W. Bulten, H. Pinckaers, C. Hulsbergen-van de Kaa and G. Litjens, "Automated Gleason Grading of Prostate Biopsies Using Deep Learning", United States and Canadian Academy of Pathology (USCAP) 108th Annual Meeting, 2019.