Development of 3D Intelligent Quantitative Phase Microscope for Sickle Cells Screening.

Area of Science:

• Biomedical Engineering
• Medical Diagnostics
• Artificial Intelligence in Healthcare

Background:

• Sickle cell disease (SCD) is a genetic blood disorder characterized by abnormal red blood cell shape.
• Current screening methods are time-consuming and require significant manual labor, leading to potential delays and misdiagnoses.
• Accurate and early detection of SCD is critical for effective patient management.

Purpose of the Study:

• To develop and evaluate an automated intelligent microscope system for rapid and reliable sickle cell disease screening.
• To reduce manual intervention and improve the efficiency of red blood cell analysis for SCD detection.
• To explore the potential of artificial intelligence in haematological diagnostics.

Main Methods:

• An intelligent microscope system employing an interferometric method to capture high-resolution 3D phase images of red blood cells.
• Deep learning-based UNET model for semantic segmentation to differentiate between sickle and healthy red blood cells.
• Classification of red blood cells using various machine learning models, including Gradient Boosting.

Main Results:

• The developed system successfully automates the screening process for sickle cell disease.
• The Gradient Boosting model achieved a high accuracy of 94.9% in classifying red blood cells.
• The system demonstrates scalability and user-friendliness, suitable for resource-limited environments.

Conclusions:

• The intelligent microscope system provides a faster and more reliable diagnostic tool for sickle cell disease.
• This AI-driven approach significantly enhances the detection capabilities for SCD.
• The system lays the groundwork for future advancements in AI-powered haematological diagnostics with planned clinical validation.