A new approach to optic disc detection in human retinal images using the firefly algorithm.

Area of Science:

• Ophthalmology
• Computer Science
• Artificial Intelligence

Background:

• Accurate optic disc detection is crucial for diagnosing various retinal diseases.
• Traditional methods often lack efficiency and accuracy.
• Intelligent algorithms show promise for automated medical image analysis.

Purpose of the Study:

• To present a novel automated method for optic disc detection in human retinal images.
• To leverage the firefly algorithm for enhanced accuracy and efficiency.
• To evaluate the proposed method's performance on standard retinal image datasets.

Main Methods:

• Utilized the firefly algorithm, inspired by firefly social behavior, for optic disc localization.
• Employed pixel light intensity in retinal images to guide the firefly algorithm's search.
• The algorithm converges towards the brightest area, identifying the optic disc.

Main Results:

• Achieved 100% accuracy on the DRIVE dataset.
• Obtained 95% accuracy on the STARE dataset and 94.38% on the DiaRetDB1 dataset.
• Demonstrated efficient detection times, averaging 2.13s (DRIVE), 2.81s (STARE), and 3.52s (DiaRetDB1).

Conclusions:

• The proposed firefly algorithm-based method offers high capability and accuracy for optic disc detection.
• The algorithm provides a fast and reliable solution for automated retinal image analysis.
• This approach holds significant potential for clinical applications in ophthalmology.