Human–machine interaction in computational cancer pathology

Abstract

The performance of the augmented pathologist that works in synergy with artificial intelligence (AI) is generally accepted as the most accurate in comparison to AI standing alone and the general pathologist standing alone. Human–machine interactions triggered by the synergic daily work give rise to trust-related concerns and potential biases that need to be addressed. The long-term use of AI requires actions to prevent deskilling of the pathology workforce, and to ensuring appropriate education of future generations. Establishment of clear guidelines for the verification and validation of AI tools is crucial for the maintenance of high-quality cancer pathology.