Deep Learning to Distinguish ABCA4-Related Stargardt Disease from PRPH2-Related Pseudo-Stargardt Pattern Dystrophy

(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease (“pseudo-Stargardt pattern dystrophy”, PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing ABCA4-related STGD1 from the PRPH2/RDS-related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs). Transfer learning was then used to update the weights of a ResNet50V2 used to classify the 370 FAF images into STGD1 and PSPD. Retina specialists evaluated the same dataset. The performance of the CNN and that of retina specialists were compared in terms of accuracy, sensitivity, and precision. (3) Results: The CNN accuracy on the test dataset of 111 images was 0.882. The AUROC was 0.890, the precision was 0.883 and the sensitivity was 0.883. The accuracy for retina experts averaged 0.816, whereas for retina fellows it averaged 0.724. (4) Conclusions: This proof-of-concept study demonstrates that, even with small databases, a pretrained CNN is able to distinguish between STGD1 and PSPD with good accuracy.

Multifocal Pattern Dystrophy Simulating Fundus Flavimaculatus: Multimodal Imaging for Early Diagnosis

Multifocal pattern dystrophy simulating fundus flavimaculatus (MPDSFF) is a clinical entity characterized by several clinicopathological, angiographic, tomographic, and electrophysiological findings. A 58-year-old caucasian female patient presented with bilateral floaters and metamorphopsia. Best-corrected visual acuity (VA) was 6/6 in both eyes and intraocular pressure was 14 and 15 mm Hg, respectively. Fundus examination, optical coherence tomography (OCT), autofluoresence (AF), fluorescein angiography (FA) and pattern Electroretinogram were employed for the diagnosis of this case. Clinical and imaging findings were consistent with MPDSFF. Noticeable progression was observed in OCT scans 6 months following the baseline visit, while no significant changes were observed over the following 12 months. Prognosis of VA in MPDSFF patients may remain relatively good even in the presence of considerable anatomic changes. Disease progression may be slow and significant reduction in VA may present only secondary to a choroidal neovascular membrane. Patient follow-up should include OCT scans, PERG, and AF in addition to VA and dilated fundus examination every 6–12 months. As relevant literature is limited and no effective treatment modality has been employed for this clinical entity, the identification of the cellular death pathway in pattern dystrophies may lead to an applicable management approach.

Blocking cell fusion inhibits age-induced polyploidy and maintains epithelial organization in Drosophila

A characteristic of normal aging and age-related diseases is the remodeling of a tissue's cellular organization through polyploid cell growth. Polyploidy arises from an increase in nuclear ploidy or the number of nuclei per cell. However, it is not known whether age-induced polyploidy is an adaption to stressors or a precursor to degeneration. Here, we find that the adult fruit fly's abdominal epithelium becomes polyploid with age through generation of large multinucleated cells that make up more than 40% of the tissue area. The syncytia arise by cell fusion, not endomitosis. Epithelial multinucleation is also a characteristic of macular degeneration, including Ctnna1tvrm5, a mouse model for pattern dystrophy. Similarly, we find that the knockdown of alpha-catenin enhances multinucleation in the fly epithelium. We further show that age-induced polyploidy can be suppressed by inhibiting cell fusion revealing a means to maintain tissue organization in older animals.

Multimodal Imaging in a Case with Bilateral Choroidal Folds

We highlight the use of multimodal imaging to diagnose and report what is, to our knowledge, a novel presentation of bilateral choroidal neovascularization (CNV) and prominent macular choroidal folds (CFs) in a patient with pattern dystrophy. An 81-year-old Caucasian male presented with painless, blurry central vision in both eyes. Color fundus photography, spectral-domain optical coherence tomography (SD-OCT), fluorescein angiography (FA), fundus autofluorescence, and brightness scan ultrasonography supported the diagnosis of pattern dystrophy with bilateral CNV and CF. In the right eye, visually significant CNV worsened post-bevacizumab treatment but responded well to aflibercept. During 4-year follow-up, Snellen visual acuity remained excellent in both eyes at 20/20, including the treatment-naïve left eye. CFs remained markedly stable in both eyes.

Fundus flavimaculatus-like in myotonic dystrophy: a case report

Background Myotonic dystrophy is an inherited disease characterized by progressive muscle weakness and myotonia. It is a multisystemic disorder that affects different parts of the body, including the eye. Dysfunction of ocular muscles, ptosis and cataract are the most common ophthalmologic manifestations, but it can also present with pigmentary changes in the retina. This report presents and discusses an unusual case of a pigmented pattern dystrophy simulating a fundus flavimaculatus in a patient with myotonic dystrophy. Case presentation We present a case of a woman with a history of myotonic dystrophy and complaints of progressive vision loss who presented bilateral retinal pigmentary changes in posterior pole and midperiphery. The characteristics and distribution of pigmented deposits, as well as ancillary tests, showed a retinal phenotype compatible with a multifocal pattern dystrophy or a fundus flavimaculatus. Conclusions There are a few publications about retinal disorders in patients with myotonic dystrophy. When macular area is affected it tends to adopt a patterned-shape defined as butterfly dystrophy or reticular dystrophy. To our knowledge, this is the first report of a patient with myotonic dystrophy and multifocal pattern dystrophy or fundus flavimaculatus.