Fig. 2

Biomarker development and evaluation data: visualization of the data split per type (TNBC, Luminal B), center (NKI, RUMC+SCDC, IMPRESS) and data subset (development, evaluation), starting from the exclusion of cases due to quality (in gray) and for training of the segmentation model (in blue, part of \({\text{dev}}_{\rm seg}^{\rm train}\)) to the definition of the development (in green, \({\text{dev}}_{\rm bm}\)) and evaluation (in yellow, \({\text{val}}_{\rm int}\)) datasets. Shown is also the additional IMPRESS [24] evaluation data (in orange, \({\text{val}}_{\rm ext}\)). Not included is the additional data for segmentation model training