Bilateral Progressive Optic Neuropathy in a Patient with Familial Amyloid Polyneuropathy: Amyloid Deposits in the Optic Nerve Head?

Familial amyloid polyneuropathy is a rare autosomal dominant hereditary disease. Optic nerve involvement is frequently observed secondary to uncontrolled glaucoma but, rarely, an ischaemic optic neuropathy can occur. In this case report we describe a patient who presented with bilateral progressive visual loss and constriction of his visual fields. Fundus examination showed intense paleness of both optic discs with elevated, poorly defined margins that seemed to be infiltrated. Fundus autofluorescence and enhanced-depth imaging optical coherence tomography ruled out the presence of optic disc drusen. Orbital magnetic resonance imaging ruled out any sign of orbital compression, inflammation or infiltration of the optic nerve. The mechanism of small vessel amyloid infiltration and a possible vessel compression by amyloid in the optic nerve head is discussed.

Bilateral Marginal Corneal Infiltrates: A Novel Ocular Manifestation of DRESS Syndrome.

BACKGROUND: Drug reaction with eosinophilia and systemic symptoms, known as DRESS syndrome, is a rare drug induced hypersensitivity reaction syndrome. METHODS: case resport. RESULTS: We describe a patient who presented with acute erythematous rash on her face, fever>38ºC, lymphadenopathy, blood abnormalities, and reaction suspected to be amoxicillin clavulanate-related. The patient also had an associated bilateral redness of the conjunctiva, peripheral corneal infiltrates, and anterior chamber with 3+ cells. CONCLUSION: We describe the first occurrence of bilateral marginal corneal infiltrates and acute anterior uveitis associated with amoxicillin clavulanate-induced DRESS syndrome and discuss its pathogenesis.

Early Progressive Circumpapillary Lesion as Atypical Presentation of Multiple Evanescent White Dot Syndrome: A Case Report.

Classical clinical findings of multiple evanescent white dot syndrome (MEWDS) include multiple, small white dots scattered throughout the posterior pole, foveal granularity, posterior vitreous cells, and mild optic disc swelling. We describe the case of a 35-year-old man who was admitted to our department with an unusual presentation of MEWDS at the early onset of the disease. A unilateral circumpapillary retinal white spot was observed. Spectral domain optical coherence tomography demonstrated irregularities of the retinal pigment epithelium and disruptions of the outer retinal layers around the optic nerve without other abnormalities. A few days later, the lesion spread centrifugally from the peripapillary region and along the vascular arcades. This distinctive appearance in an early stage of the disease may suggest a disorder other than MEWDS, which can lead to a misdiagnosis and unnecessary treatment.

Artificial Intelligence to Identify Retinal Fundus Images, Quality Validation, Laterality Evaluation, Macular Degeneration, and Suspected Glaucoma.

PURPOSE: To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON). PATIENTS AND METHODS: Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina's tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity. RESULTS: Determination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%). CONCLUSION: Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.