|
Artificial Intelligence Revolution in Leukocyte Classification: From Deep Learning to Intelligent Hematology Analyzers
|
Behnaz Tavasoli1   , Zahra Eskandari2 , Mahdis Abdar Esfahani3 |
1- Technical Supervisor and Research and Development (R&D) Manager. Rooz Azmoon Technology Company
2- Department of Hematology, Faculty of Allied Medicine, Bushehr University of Medical Sciences, Bushehr, Iran
3- Student Research Committee, Department of Hematology and Blood Banking, School of Allied Medical Sciences, Bushehr University of Medical Sciences, Bushehr, Iran |
|
|
Abstract: (24 Views) |
Recognition and differentiation of white blood cells (WBCs) are among the most important tasks in clinical laboratories. Qualitative and quantitative changes in WBCs may be associated with a wide spectrum of disorders, ranging from infectious diseases to hematologic malignancies. However, the traditional method based on light microscopy has high diagnostic value, it has several limitations, including being time-consuming, operator-dependent, and having limited repeatability, which make it a challenging approach for routine laboratory practice.
In recent years, remarkable progress in artificial intelligence (AI) and machine learning has opened a new window for diagnostic applications in laboratory hematology. The integration of AI and machine learning from classical algorithms in image segmenting and feature extraction algorithms to advanced deep learning models such as U-Net، Mask R-CNN in classification of WBCs, has significantly improved diagnostic precision and revolutionized laboratory hematology.
The development of next-generation smart hematology analyzers powered by AI demonstrates that AI is no longer confined to research settings but has become a powerful tool in modern laboratory diagnostics. Although the need for larger and more diverse datasets remains a significant challenge, AI has become an invaluable tool in modern hematology laboratories by improving diagnostic accuracy, reducing human intervention, and enhancing workflow efficiency. This new technology not only reduces time and cost of analysis but also facilitates the more accurate diagnosis of hematological diseases through its high precision and excellent reproducibility.
|
|
| Keywords: Artificial intelligence, Machine learning, Deep learning, Peripheral blood smear, Flow cytometry, Smart hematology analyzer, Hematology, White blood cells (WBCs) |
|
|
Full-Text [PDF 1402 kb]
(19 Downloads)
|
Type of Study: Review |
Subject:
خون شناسی (هماتولوژی)
Received: 2026/09/28 | Accepted: 2026/09/29 | Published: 2026/09/29
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
