Webinar ISLH di giugno 2026

Overview:

Accurate blast cell identification is essential for the diagnosis, classification, and monitoring of hematologic malignancies. While microscopic examination of peripheral blood and bone marrow smears remains the diagnostic gold standard, it is labor-intensive and subject to inter-observer variability.

Recent advances in automated digital morphology and artificial intelligence, particularly deep learning models, have improved blast detection by enabling rapid and standardized pre-classification of cells.

These systems enhance workflow efficiency, reduce observer variability, and support large-scale diagnostic screening.

Although challenges remain, including morphological overlap among cell populations, AI-assisted morphology is emerging as a valuable complement to expert hematologic evaluation.

Learning Objectives:

• Describe the role of automated digital morphology and deep learning algorithms in the detection and pre-classification of blast cells in peripheral blood and bone marrow smears.

• Evaluate the benefits of AI-assisted blast detection, including improved efficiency, standardization, reproducibility, and support for high-throughput diagnostic workflows.

• Recognize the current limitations of automated blast classification, including morphological overlap, lineage assignment challenges, and the need for integration with complementary diagnostic methods.