[Automatic detection of microaneurysms in colour fundus images]

Area of Science:

• Ophthalmology
• Medical Imaging
• Computer Vision

Background:

• Diabetic retinopathy is a leading cause of vision loss.
• Early detection of microaneurysms is crucial for timely intervention.
• Current screening methods can be resource-intensive.

Purpose of the Study:

• To develop and clinically evaluate an automated tool for microaneurysm detection.
• To facilitate diabetic retinopathy diagnosis in general screening programs.

Main Methods:

• Image acquisition using a retinal camera.
• Image processing including inversion, green channel enhancement, and high-pass filtering.
• Microaneurysm candidate detection via adaptive prediction filters and region growth.
• Selection based on circularity, intensity, and contrast criteria.

Main Results:

• The automated tool correctly identified 252 out of 297 microaneurysms in 20 retinal images.
• Achieved a mean sensitivity of 89%.
• Reported a false positive rate of 93%.

Conclusions:

• The developed tool shows promise for use in primary care screening programs.
• Further algorithm development is necessary to decrease the false positive rate.
• Potential to improve efficiency and accessibility of diabetic retinopathy screening.