Probing Deposit-Driven Age-Related Macular Degeneration Via Thicknesses of Outer Retinal Bands and Choroid: ALSTAR2 Baseline.

Purpose: We aimed to identify structural differences in normal eyes, early age-related macular degeneration (AMD), and intermediate AMD eyes using optical coherence tomography (OCT) in a well-characterized, large cross-sectional cohort. Methods: Subjects ≥ 60 years with healthy normal eyes, as well as early or intermediate AMD were enrolled in the Alabama Study on Age-related Macular Degeneration 2 (ALSTAR2; NCT04112667). Using Spectralis HRA + OCT2, we obtained macular volumes for each participant. An auto-segmentation software was used to segment six layers and sublayers: photoreceptor inner and outer segments, subretinal drusenoid deposits (SDDs), retinal pigment epithelium + basal lamina (RPE + BL), drusen, and choroid. After manually refining the segmentations of all B-scans, mean thicknesses in whole, central, inner and outer rings of the ETDRS grid were calculated and compared among groups. Results: This study involved 502 patients, 252 were healthy, 147 had early AMD, and 103 had intermediate AMD eyes (per Age-Related Eye Disease Study [AREDS] 9-step). Intermediate AMD eyes exhibited thicker SDD and drusen, thinner photoreceptor inner segments, and RPE compared to healthy and early AMD eyes. They also had thicker photoreceptor outer segments than early AMD eyes. Early AMD eyes had thinner photoreceptor outer segments than normal eyes but a thicker choroid than intermediate AMD eyes. Using the Beckman scale, 42% of the eyes initially classified as early AMD shifted to intermediate AMD, making thickness differences for photoreceptor outer segments and choroid insignificant. Conclusions: With AMD stages, the most consistent structural differences involve appearance of drusen and SDD, followed by RPE + BL thickness, and then thickness of photoreceptor inner and outer segments. Structural changes in the transition from aging to intermediate AMD include alterations in the outer retinal bands, including the appearance of deposits on either side of the RPE.

Reverse engineering for reconstructing baseline features of dry age-related macular degeneration in optical coherence tomography.

Age-related macular degeneration (AMD) is the most widespread cause of blindness and the identification of baseline AMD features or biomarkers is critical for early intervention. Optical coherence tomography (OCT) imaging produces a 3D volume consisting of cross sections of retinal tissue while fundus fluorescence (FAF) imaging produces a 2D mapping of retina. FAF has been a good standard for assessing dry AMD late-stage geographic atrophy (GA) while OCT has been used for assessing early AMD biomarkers beyond as well. However, previous approaches in large extent defined AMD features subjectively based on clinicians' observation. Deep learning-an objective artificial intelligence approach, may enable to discover 'true' salient AMD features. We develop a novel reverse engineering approach which bases on the backbone of a fully convolutional neural network to objectively identify and visualize AMD early biomarkers in OCT from baseline exams before significant atrophy occurs. Utilizing manually annotated GA regions on FAF from a follow-up visit as ground truth, we segment GA regions and reconstruct early AMD features in baseline OCT volumes. In this preliminary exploration, compared with ground truth, we achieve baseline GA segmentation accuracy of 0.95 and overlapping ratio of 0.65. The reconstructions consistently highlight that large druse and druse clusters with or without mixed hyper-reflective focus lesion on baseline OCT cause the conversion of GA after 12 months. However, hyper-reflective focus lesions and subretinal drusenoid deposit lesions alone are not seen such conversion after 12 months. Further research with larger dataset would be needed to verify these findings.

Automated Retinal Layer Segmentation Using Graph-based Algorithm Incorporating Deep-learning-derived Information.

Regular drusen, an accumulation of material below the retinal pigment epithelium (RPE), have long been established as a hallmark early feature of nonneovascular age-related macular degeneration (AMD). Advances in imaging have expanded the phenotype of AMD to include another extracellular deposit, reticular pseudodrusen (RPD) (also termed subretinal drusenoid deposits, SDD), which are located above the RPE. We developed an approach to automatically segment retinal layers associated with regular drusen and RPD in spectral domain (SD) optical coherence tomography (OCT) images. More specifically, a shortest-path algorithm enhanced with probability maps generated through a fully convolutional neural network was used to segment drusen and RPD, as well as 11 retinal layers in SD-OCT volumes. This algorithm achieves a mean difference that is within the subpixel accuracy range drusen and RPD, alongside the other 11 retinal layers, highlighting the high robustness of this algorithm for this dataset. To the best of our knowledge, this is the first report of a validated algorithm for the automated segmentation of the retinal layers including early AMD features of RPD and regular drusen separately on SD-OCT images.