Artificial Intelligence and Data Science Methods for Automatic Detection of White Blood Cells in Images

Area of Science:

• Biomedical diagnostics
• Medical imaging analysis
• Computational pathology

Background:

• Healthcare operations increasingly rely on data science (DS) and artificial intelligence (AI).
• Accurate white blood cell (WBC) counting and classification are crucial for diagnosing blood disorders like leukemia.
• Manual methods for WBC analysis are time-consuming and prone to errors.

Purpose of the Study:

• To evaluate the effectiveness of AI and DS in automating WBC detection and classification for disease diagnosis.
• To analyze the current research landscape on AI and DS applications in WBC image analysis using science mapping.

Main Methods:

• Bibliographic data from SCOPUS were analyzed using a literature survey and science mapping methodology.
• Evaluation of various AI algorithms (machine learning, deep learning) and DS methods for WBC image classification.

Main Results:

• AI and DS methods, including machine learning and deep learning, demonstrate significant potential for automatic WBC detection and classification.
• These algorithms effectively analyze microscopic blood cell images, improving diagnostic speed and accuracy.
• Automated identification and classification of WBCs streamline the diagnostic process, aiding hematologists.

Conclusions:

• AI and DS algorithms are potent tools for enhancing the accuracy and efficiency of biomedical diagnostics, particularly in hematology.
• The automation of WBC analysis accelerates patient diagnosis and allows for earlier detection of abnormalities.
• Future research will explore the integration of generative AI in blood cell diagnostics.