Macular Vessel Density and Ganglion Cell/Inner Plexiform Layer Thickness and Their Combinational Index Using...

Area of Science:

• Ophthalmology
• Medical Imaging
• Artificial Intelligence

Background:

• Glaucoma is a leading cause of irreversible blindness.
• Early detection and accurate diagnosis are crucial for managing glaucoma.
• Assessing structural and vascular changes in the macula may aid in glaucoma diagnosis.

Purpose of the Study:

• To evaluate the relationship between macular vessel density and ganglion cell-inner plexiform layer thickness (GCIPLT).
• To compare the diagnostic performance of macular vessel density and GCIPLT in glaucoma detection.
• To develop and assess a novel combined parameter using an artificial neural network.

Main Methods:

• 173 subjects (100 test, 73 training) including healthy, early, and advanced glaucoma patients.
• Macular GCIPLT and vessel density measured via Spectralis and Topcon OCT, respectively.
• Artificial neural network used to create a combined parameter; diagnostic performance evaluated using AUROC.

Main Results:

• Significant correlation found between macular vessel density and GCIPLT (r=0.27 to 0.56).
• Macular GCIPLT showed superior diagnostic power (AUROC=0.67-0.81) compared to vessel density (AUROC=0.50-0.60).
• The combined neural network parameter achieved significantly higher diagnostic performance (AUROC=0.87).

Conclusions:

• Macular vessel density is decreased in glaucoma and linearly correlated with GCIPLT.
• GCIPLT is a better diagnostic indicator than macular vessel density alone.
• An artificial neural network combining both parameters offers superior diagnostic performance for glaucoma.