Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus...

Area of Science:

• Ophthalmology
• Medical Imaging
• Computer Vision

Background:

• Glaucoma is a leading cause of irreversible blindness globally.
• Accurate and early diagnosis of glaucoma is crucial for vision preservation.
• Current diagnostic methods often rely on manual interpretation or less precise imaging analysis.

Purpose of the Study:

• To develop an automated glaucoma diagnosis system using digital fundus images.
• To enhance diagnostic accuracy by focusing on specific image regions and features.
• To compare the proposed method's performance against existing glaucoma detection techniques.

Main Methods:

• Wavelet feature extraction applied to segmented optic disc images.
• Blood vessels were removed from the optic disc region prior to analysis.
• Optimized genetic feature selection combined with various machine learning algorithms.
• Performance evaluation using accuracy metrics.

Main Results:

• Wavelet features from the segmented optic disc demonstrated higher clinical significance than whole or sub-fundus images.
• The proposed automated method achieved an accuracy of 94.7% for glaucoma identification.
• The new approach showed improved classification accuracy compared to existing methods.

Conclusions:

• Feature extraction from the segmented, blood vessel-removed optic disc is a more effective strategy for glaucoma detection.
• The developed image processing technique offers a promising automated solution for accurate glaucoma diagnosis.
• This method has the potential to improve early detection rates and patient outcomes in glaucoma management.