Pathology Annotation Consensus & Inter-Rater Agreement (2D)

Before any digital-pathology AI model can be trained, someone has to decide what "tumor" looks like on a slide — and different pathologists don't always agree. This 2D canvas simulator draws several independent raters' tumor calls over the same grid of whole-slide-image patches as a draggable, rotatable isometric stack of layers above the true tumor mask, then majority-votes them into a consensus ground truth shown in a separate live vote-fraction heatmap. Live readouts compute Fleiss' kappa across the raters, the Dice overlap between the consensus mask and the real truth, and the fraction of patches every rater agreed on — showing directly why noisy or biased annotation, not model architecture, is often the ceiling on a pathology AI pipeline's real-world accuracy.