Artifical Intelligence Enabled OCT Segmentation

Abstract

Purpose : To develop an OCT segmentation algorithm capable of consistent performance across different OCT devices, addressing a significant interoperability challenge in ophthalmic diagnostics.

Methods : 329 OCT volume scans of normal eyes from Heidelberg Spectralis were converted into DICOM format, manually segmented using a semi automated algorithm by certified graders. Using a predefined 3D Unet Transformer architecture, a model was trained to segment the total retinal thickness between the internal limiting membrane and the retinal pigment epithelium layer using 259 (78.7%) images. The remaining 70 (21.3%) images were used to test the algorithm based on the manual segmentation. Dice coefficient was used to measure the degree of overlap for the 2 layers of segmentations.

Results : Average (±SD) central subfield thickness (CST) for the manual segmentation was 255±22 µm while the average for the AI-predicted segmentation was 256±22 µm. The difference between the manual and AI-predicted segmentation within the CST was an average of 2.70±6.63µm with the dice coefficient average was 0.992. When comparing across the 6mm ring, the average retinal thickness for the manual segmentation was 260±16 µm with the AI-predicted retinal thickness having similar results of 261±15 µm.

Conclusions : This AI model provides a reliable segmentation of total retinal thickness for Heidelberg Spectralis OCT volume scans. This segmentation model is currently being expanded to other OCT devices and to eyes with pathology can provide a universal and efficient method to segment OCT scans in diverse clinical settings.

This abstract was presented at the 2024 ARVO Imaging in the Eye Conference, held in Seattle, WA, May 4, 2024.