Evaluation of retinal pigment epithelium changes in serous pigment epithelial detachment in age-related macular degeneration

Synthesizing the degree of polarization uniformity from non-polarization-sensitive optical coherence tomography signals using a neural network

Degree of polarization uniformity (DOPU) imaging obtained by polarization-sensitive optical coherence tomography (PS-OCT) has the potential to provide biomarkers for retinal diseases. It highlights abnormalities in the retinal pigment epithelium that are not always clear in the OCT intensity images. However, a PS-OCT system is more complicated than conventional OCT. We present a neural-network-based approach to estimate the DOPU from standard OCT images. DOPU images were used to train a neural network to synthesize the DOPU from single-polarization-component OCT intensity images. DOPU images were then synthesized by the neural network, and the clinical findings from ground truth DOPU and synthesized DOPU were compared. There is a good agreement in the findings for RPE abnormalities: recall was 0.869 and precision was 0.920 for 20 cases with retinal diseases. In five cases of healthy volunteers, no abnormalities were found in either the synthesized or ground truth DOPU images. The proposed neural-network-based DOPU synthesis method demonstrates the potential of extending the features of retinal non-PS OCT.

Nahinfrarot-Autofluoreszenz: klinische Anwendung und diagnostische Relevanz

Die Nahinfrarot-Autofluoreszenz (NIA) ist ein nicht-invasives Verfahren zur Untersuchung des retinalen Pigmentepithels (RPE) basierend auf der Darstellung des antioxidativen Schutzfaktors Melanin in den RPE-Zellen. Die NIA verbessert die Früherkennung chorioretinaler Erkrankungen, da bei vielen dieser Erkrankungen mit der NIA Strukturveränderungen des RPE nachweisbar sind, bevor sich in anderen Untersuchungen Krankheitszeichen erkennen lassen.

[Near-infrared Fundus Autofluorescence: Clinical Application and Diagnostic Relevance]

Near-infrared autofluorescence (NIA) is a non-invasive retinal imaging technique for examination of the retinal pigment epithelium (RPE) based on the autofluorescence of melanin. Melanin has several functions within the RPE cells, in one of them it serves as a protective antioxidative factor within the RPE cells and is involved in the phagocytosis of photoreceptor outer segments. Disorders that affect the photoreceptor-RPE complex result in alterations of RPE cells which are detectable by alterations of NIA. Therefore, NIA allows to detect early alterations in inherited and acquired chorioretinal disorders, frequently prior to ophthalmoscopical visualisation and often prior to alterations in lipofuscin associated fundus autofluorescence (FAF) or optical coherence tomography (OCT). Although NIA and FAF relate to disorders affecting the RPE, findings between both imaging methods differ and the area involved has been demonstrated to be larger in NIA compared to FAF in several disorders (e.g., age-related macular degeneration, retinitis pigmentosa, ABCA4-gene associated Stargardt disease and cone-rod dystrophy, light damage), indicating that NIA detects earlier alterations compared to FAF. In addition, due to the absence of blue-light filtering which limits foveal visualisation in FAF, foveal alterations can be much better detected using NIA. A reduced subfoveal NIA intensity is the earliest sign of autosomal dominant BEST1-associated disease, when FAF and OCT are still normal. In other disorders, a normal subfoveal NIA intensity is associated with good visual acuity. This review summarizes the present knowledge on NIA and demonstrates biomarkers for various chorioretinal disorders.