Shared-hole graph search with adaptive constraints for 3D optic nerve head optical coherence tomography image...

Area of Science:

• Ophthalmology
• Medical Imaging
• Computational Biology

Background:

• The optic nerve head (ONH) is critical for diagnosing and monitoring glaucoma using spectral domain optical coherence tomography (SD-OCT).
• Accurate retinal layer segmentation in SD-OCT images is challenging due to the complex "hole" structure within the ONH region.
• Existing segmentation methods often struggle with the precision required for clinical applications.

Purpose of the Study:

• To develop and validate a robust 3D segmentation method for ONH-centered SD-OCT images.
• To overcome the segmentation difficulties posed by the ONH "hole" structure.
• To enhance the accuracy of retinal layer and optic disc boundary segmentation for glaucoma assessment.

Main Methods:

• A novel 3D segmentation approach for ONH-centered SD-OCT images was developed.
• The method utilizes a modified graph search algorithm incorporating shared-hole and locally adaptive constraints.
• The algorithm was applied to segment both the optic disc boundary and nine distinct retinal surfaces.

Main Results:

• The proposed method achieved accurate segmentation of the optic disc boundary and nine retinal surfaces.
• A mean unsigned border positioning error of 7.27 ± 5.40 µm was obtained for retinal layer segmentation.
• A mean Dice coefficient of 0.925 ± 0.03 was achieved for optic disc region detection, demonstrating high accuracy.

Conclusions:

• The developed 3D segmentation method significantly improves the accuracy of retinal layer and optic disc segmentation in SD-OCT images.
• This advancement holds promise for more precise glaucoma detection and tracking.
• The method's effectiveness in handling the challenging ONH "hole" structure offers a valuable tool for ophthalmological research and clinical practice.