Hematopathology Practice in the Digital Era: What has Changed?

Area of Science:

• Hematopathology
• Digital Pathology
• Artificial Intelligence

Background:

• Hematopathology workflows involve complex data for diagnosis and patient management, starting with blood cell counts and morphologic evaluation of peripheral blood (PB) and bone marrow (BM).
• Digital pathology offers potential for revolutionizing PB and BM assessment via AI-assisted and automated evaluation.

Purpose of the Study:

• To review the current state of digitalization in hematopathology.
• To discuss recent research utilizing machine learning for automated specimen analysis.
• To outline the advantages and barriers to AI implementation and propose future AI-driven workflows.

Main Methods:

• Review of current literature on digital pathology and AI in hematopathology.
• Analysis of machine learning models for automated analysis of blood and bone marrow specimens.
• Discussion of implementation challenges and prospective workflow development.

Main Results:

• Digital pathology and AI show promise for improving hematopathology diagnostics.
• Significant hurdles including regulatory oversight, data standardization, and workforce training impede widespread adoption.
• AI-driven workflows could enhance efficiency and comprehensiveness in clinical workup.

Conclusions:

• Digitalization and AI hold transformative potential for hematopathology practice.
• Overcoming implementation barriers is crucial for realizing the benefits of AI in clinical settings.
• Future workflows integrating AI can lead to more efficient and accurate patient management.