Characterization of optic disc in human retinal images using tsallis entropy based method

Area of Science:

• Ophthalmology
• Medical Imaging
• Biomedical Engineering

Background:

• Automated analysis of retinal images is crucial for diagnosing eye conditions.
• Accurate optic disc detection is a fundamental step in retinal image analysis.

Purpose of the Study:

• To present a method for optic disc identification in human retinal images using Tsallis entropy.
• To evaluate the effectiveness of Tsallis entropy with and without morphological preprocessing for optic disc segmentation.

Main Methods:

• Utilized conventional Tsallis entropy for retinal image segmentation.
• Applied morphological preprocessing to enhance segmentation results.
• Determined an optimal threshold for separating the optic disc from other retinal structures.
• Analyzed performance based on entropic index, visual quality, pixel distribution, and optic disc size.

Main Results:

• Conventional Tsallis entropy with morphological preprocessing successfully segmented the optic disc.
• Optimal detection efficiency was achieved with an entropic index of 4.
• The optic disc index proved useful in differentiating normal from abnormal retinal images.

Conclusions:

• Morphological preprocessing significantly improves optic disc segmentation using Tsallis entropy.
• The developed method shows high detection efficiency and potential for diagnosing retinal diseases.
• The optic disc index is a valuable parameter for clinical assessment of retinal health.