General Pathologists Achieve Near-Specialist Diagnostic Performance Using Deep Learning–Based Virtual Staining for Donor Kidney Assessment: A Retrospective-Prospective Diagnostic Concordance Study

Key Points

• Deep learning-based virtual staining achieves near-specialist diagnostic performance for donor kidneys.
• In diagnostic assessments, general pathologists achieved a concordance rate of 90% with specialist pathologists.
• The retrospective-prospective diagnostic concordance study involved cross-analysis of kidney samples under virtual staining conditions.
• This advance supports the integration of deep learning techniques in pathology, improving diagnostic accuracy for organ transplants.