The interpretation of immunohistochemical markers in melanocytic lesions possesses difficulties due to expression in non-melanocytic cells and the time-consuming, non-reproducible nature of manual assessment. A digital tool that accurately quantifies Ki67 and PRAME may valuably aid pathologists in the diagnostic classification of melanocytic lesions. The aim of this study was to assess the diagnostic performance of digitally quantified Ki67 and PRAME in challenging melanocytic lesions utilizing double nuclear staining methods for accurate identification of melanocytic cells. We explored the difference in Ki67 and PRAME expression by WHO-lesion-groups and Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis version 2.0 (MPATH-Dx V2.0). Tissue slides from a cohort of 156 melanocytic lesions were stained with the Ki67/SOX10 double nuclear stain and the PRAME/SOX10 virtual double nuclear stain. Melanocytic cell specific Ki67/SOX10- and PRAME/SOX10-indexes were quantified by AI-driven digital image analysis (DIA) and compared to non-specific Ki67- and PRAME-indexes. The results showed that ROC AUC of the Ki67/SOX10-index was increased compared to the non-specific Ki67-index (p < 0.001), as opposed to the AUC of the PRAME/SOX10-index compared to non-specific PRAME-index (p = 0.090). The medians of digitally quantified Ki67- and PRAME-indexes differed significantly for the overall WHO-groups and MPATH-Dx V2.0 classes (p < 0.001). In conclusion, we found that double nuclear staining improved the diagnostic performance of Ki67, but not PRAME. The combination of digitally quantified Ki67- and PRAME-indexes may potentially serve as a tool for diagnostic classification of challenging melanocytic lesions. The proposed diagnostic tool presents the results visually, graphically, and quantitatively to optimally aid the pathologist.

Melanocytic lesions

Ki67

PRAME

MPATH-Dx classification

Digital pathology

Artificial intelligence

Multiplex immunohistochemistry

© 2025 The Authors. Published by Elsevier GmbH.