Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge.

•Tumor proliferation is an important breast cancer prognostic biomarker.•Previous efforts for automatic assessment were limited to mitosis detection in predefined regions.•In a real-world setting, automatic methods must produce a score for whole-slide images.•To bridge this gap, we have organized the TUPAC16 medical image analysis challenge.•Eleven methods for assessment of two proliferation scores (mitosis-based and PAM50 molecular) were compared and evaluated.