Decoding (digital) histopathology: The building blocks for computational researchers.

Abstract

Computational Pathology is a novel discipline at the intersection of pathology and computer science, driven by the recent advances in machine learning and image analysis. Nevertheless, combining the insights from both disciplines remains challenging, particularly due to differences in technical background and language between pathologists and engineers. It is acknowledged that literature translating fundamental pathology concepts for computer scientists remains limited, which further complicates the understanding of the field, especially for those entering the field. In this context, and aligned with the mission of the European Society of Digital and Integrative Pathology (ESDIP) to promote education and interdisciplinary collaboration in digital and computational pathology, this work aims to provide a comprehensive yet accessible guide to pathology for computational scientists and other researchers. Herein, we present an overview of the pathology laboratory workflow, digital pathology and whole-slide imaging, diagnostic fundamentals of neoplastic and nonneoplastic diseases, and current applications of AI in pathology. This guide is designed as a practical reference and educational resource to support computer scientists new to the field and to promote more effective collaboration between medical and computational communities.