Automated Segmentation of Optic Nerve Head Structures With Optical Coherence Tomography

Abstract

PURPOSE. To quantify and characterize the difference between automated and manual segmentation of optic nerve head structures with spectral-domain optical coherence tomography (SD-OCT). METHODS. Optic nerve head radial scans in 107 glaucoma patients and 48 healthy controls were conducted with SD-OCT. Independent segmentations of the internal limiting membrane (ILM) and Bruch's membrane opening (BMO) were performed manually with custom software and with an automated algorithm in each radial scan. The minimum distance between BMO and ILM, termed BMO-minimum rim width (BMO-MRW) was calculated with each segmentation method. Absolute differences between automated and manual segmentations of ILM (Delta ILM) and BMO (Delta BMO), and the resulting computation of BMO-MRW (Delta BMO-MRW) were computed. Finally, the relationship between image quality score and Delta ILM and Delta BMO was explored. RESULTS. The median (interquartile range, IQR) Delta ILM was 8.9 (6.5, 13.4) mu m in patients and 7.3 (5.3, 9.9) mu m in controls. The corresponding values for Delta BMO were 11.5 (6.6, 22.1) mu m and 12.4 (6.8, 25.4) mu m. Subject-averaged Delta ILM was higher in patients than controls (P < 0.01); however, mean Delta BMO was not (P = 0.09). The median (IQR) subject-averaged absolute Delta BMO-MRW was 13.4 (10.6, 16.8) mu m in patients and 12.1 (10.0, 16.8) mu m in controls and not statistically different (P = 0.21). Mean image quality score was statistically higher in controls than patients (P = 0.03) but not related to subject-averaged Delta ILM or Delta BMO. CONCLUSIONS. In individual scans, the median difference in ILM and BMO segmentations was < 2 and < 3 image pixels, respectively. There were no differences between patients and controls in Delta BMO-MRW.