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

Area of Science:

• Computational pathology as an emerging interdisciplinary field.
• Integration of pathology and computer science, leveraging machine learning and image analysis.
• Bridging the knowledge gap between pathologists and computer scientists.

Background:

• Challenges in interdisciplinary collaboration due to differing technical backgrounds and terminology.
• Limited availability of pathology literature tailored for computer scientists.
• Need for accessible educational resources to facilitate entry into computational pathology.

Purpose of the Study:

• To provide a comprehensive and accessible guide to pathology for computational scientists.
• To promote interdisciplinary education and collaboration in digital and computational pathology.
• To serve as a practical reference for researchers new to the field.

Main Methods:

• Overview of the pathology laboratory workflow.
• Explanation of digital pathology and whole-slide imaging.
• Introduction to diagnostic fundamentals of neoplastic and nonneoplastic diseases.
• Review of current artificial intelligence (AI) applications in pathology.

Main Results:

• A structured guide covering essential pathology concepts for computational scientists.
• Detailed explanation of digital pathology techniques and AI integration.
• Foundation for understanding diagnostic principles in pathology.

Conclusions:

• The guide aims to enhance understanding and collaboration between medical and computational communities.
• It serves as a crucial educational resource for computational scientists entering the field.
• Facilitates effective interdisciplinary research and development in computational pathology.