Ontology-based lymphocyte population description using mathematical morphology on colour blood images.

Area of Science:

• Hematology
• Medical Imaging
• Computational Biology

Background:

• Microscopic examination of peripheral blood smears is crucial for diagnosing various diseases, including leukaemic disorders.
• Modern technologies complement, but do not replace, traditional cytomorphologic analysis.
• An objective and standardized method for lymphocyte population description is needed.

Purpose of the Study:

• To develop an automated, image-based system for describing lymphocyte populations.
• To create an objective framework using mathematical morphology and a specific ontology.
• To integrate automated analysis with human medical expertise for improved diagnostics.

Main Methods:

• Utilizing mathematical morphology tools for processing peripheral blood colour images.
• Developing an ontology-based framework for lymphocyte classification.
• Creating image processing and data classification algorithms.
• Generating representative image databases for training and validation.

Main Results:

• Demonstrated high-performance of the image-based approach in describing lymphocyte populations.
• Successfully developed algorithms for image processing and data classification.
• Validated the system's effectiveness through comparison with human expertise.

Conclusions:

• The developed image-based approach offers an objective and understandable description of lymphocyte populations.
• This method successfully reconciles automation with medical expertise, creating a synergistic diagnostic tool.
• The system has the potential to enhance the efficiency and accuracy of diagnosing hematologic disorders.