Interactive Blood Vessel Segmentation from Retinal Fundus Image Based on Canny Edge Detector.

Area of Science:

• Ophthalmology
• Medical Imaging
• Computer Vision

Background:

• Fundus photography is crucial for monitoring eye diseases.
• Retinal vessel segmentation is essential for accurate diagnosis.
• Existing methods may lack interactivity and precision.

Purpose of the Study:

• To propose an interactive blood vessel segmentation method for retinal fundus images.
• To enhance the analysis of specific retinal vessels for disease detection.
• To provide a user-friendly tool for medical professionals.

Main Methods:

• Utilized Canny edge detection for vessel segmentation.
• Implemented a semi-automated approach via a graphical user interface (GUI).
• Pre-processing involved green channel extraction, CLAHE, and retinal outline removal.

Main Results:

• Successfully segmented specific blood vessels interactively.
• Enabled highlighting of particular vessels through adjustable edge detection parameters.
• Demonstrated potential for detailed analysis and detection of abnormal vessels.

Conclusions:

• The proposed interactive Canny edge detection method offers an effective tool for retinal vessel analysis.
• This approach facilitates focused examination of retinal vasculature for diagnosing eye conditions.
• The GUI-based system improves usability for optometrists and ophthalmologists.