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 segmentation and feature discovery of age-related macular degeneration and Stargardt disease via self-attended neural networks.

Age-related macular degeneration (AMD) and Stargardt disease are the leading causes of blindness for the elderly and young adults respectively. Geographic atrophy (GA) of AMD and Stargardt atrophy are their end-stage outcomes. Efficient methods for segmentation and quantification of these atrophic lesions are critical for clinical research. In this study, we developed a deep convolutional neural network (CNN) with a trainable self-attended mechanism for accurate GA and Stargardt atrophy segmentation. Compared with traditional post-hoc attention mechanisms which can only visualize CNN features, our self-attended mechanism is embedded in a fully convolutional network and directly involved in training the CNN to actively attend key features for enhanced algorithm performance. We applied the self-attended CNN on the segmentation of AMD and Stargardt atrophic lesions on fundus autofluorescence (FAF) images. Compared with a preexisting regular fully convolutional network (the U-Net), our self-attended CNN achieved 10.6% higher Dice coefficient and 17% higher IoU (intersection over union) for AMD GA segmentation, and a 22% higher Dice coefficient and a 32% higher IoU for Stargardt atrophy segmentation. With longitudinal image data having over a longer time, the developed self-attended mechanism can also be applied on the visual discovery of early AMD and Stargardt features.

Prevalence of Focal Inner, Middle, and Combined Retinal Thinning in Diabetic Patients and Its Relationship With Systemic and Ocular Parameters.

Purpose: To determine the prevalence of focal inner, middle, and combined inner/middle retinal thinning (FIRT, FMRT, and FCRT, respectively) in different stages of diabetic retinopathy (DR) without diabetic macular edema and to assess the relationship between such findings with ocular and systemic parameters. Methods: This was a cross-sectional, comparative study comprising healthy participants and diabetic patients with different stages of DR. Forty-nine horizontal macular B-scans from the selected eye were obtained using spectral-domain optical coherence tomography (SD-OCT) and analyzed for the presence of FIRT, FMRT, or FCRT and any relationship with systemic and ocular parameters. Focal retinal thinning (FRT) was subjectively defined as any evidence of inner and/or middle retinal thinning. Results: A total of 190 participants (52 healthy participants and 138 diabetic patients) were included. A higher prevalence of FRT was observed in eyes with advanced DR versus healthy eyes and versus diabetic eyes with no DR or mild DR. FIRT and FCRT were significantly greater in eyes with proliferative DR treated with pan-retinal photocoagulation, and FMRT was significantly more common in eyes with severe nonproliferative DR. FRT was significantly more common in patients with coronary artery disease and was positively correlated with diabetes duration, serum creatinine, and glycosylated hemoglobin and negatively correlated with age, estimated glomerular filtration rate, and visual acuity. Conclusions: FRT occurs in all stages of DR and is increasingly prevalent with increasing severity of DR. Translational Relevance: OCT identification of FRT may provide a surrogate biomarker of retinal and systemic disease in diabetic patients.