DeepLensNet: Deep Learning Automated Diagnosis and Quantitative Classification of Cataract Type and Severity.

PURPOSE: To develop deep learning models to perform automated diagnosis and quantitative classification of age-related cataract from anterior segment photographs. DESIGN: DeepLensNet was trained by applying deep learning models to the Age-Related Eye Disease Study (AREDS) dataset. PARTICIPANTS: A total of 18 999 photographs (6333 triplets) from longitudinal follow-up of 1137 eyes (576 AREDS participants). METHODS: Deep learning models were trained to detect and quantify nuclear sclerosis (NS; scale 0.9-7.1) from 45-degree slit-lamp photographs and cortical lens opacity (CLO; scale 0%-100%) and posterior subcapsular cataract (PSC; scale 0%-100%) from retroillumination photographs. DeepLensNet performance was compared with that of 14 ophthalmologists and 24 medical students. MAIN OUTCOME MEASURES: Mean squared error (MSE). RESULTS: On the full test set, mean MSE for DeepLensNet was 0.23 (standard deviation [SD], 0.01) for NS, 13.1 (SD, 1.6) for CLO, and 16.6 (SD, 2.4) for PSC. On a subset of the test set (substantially enriched for positive cases of CLO and PSC), for NS, mean MSE for DeepLensNet was 0.23 (SD, 0.02), compared with 0.98 (SD, 0.24; P = 0.000001) for the ophthalmologists and 1.24 (SD, 0.34; P = 0.000005) for the medical students. For CLO, mean MSE was 53.5 (SD, 14.8), compared with 134.9 (SD, 89.9; P = 0.003) for the ophthalmologists and 433.6 (SD, 962.1; P = 0.0007) for the medical students. For PSC, mean MSE was 171.9 (SD, 38.9), compared with 176.8 (SD, 98.0; P = 0.67) for the ophthalmologists and 398.2 (SD, 645.4; P = 0.18) for the medical students. In external validation on the Singapore Malay Eye Study (sampled to reflect the cataract severity distribution in AREDS), the MSE for DeepSeeNet was 1.27 for NS and 25.5 for PSC. CONCLUSIONS: DeepLensNet performed automated and quantitative classification of cataract severity for all 3 types of age-related cataract. For the 2 most common types (NS and CLO), the accuracy was significantly superior to that of ophthalmologists; for the least common type (PSC), it was similar. DeepLensNet may have wide potential applications in both clinical and research domains. In the future, such approaches may increase the accessibility of cataract assessment globally. The code and models are available at https://github.com/ncbi/deeplensnet.

ROLE OF OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY IN DETECTING AND MONITORING INFLAMMATORY CHOROIDAL NEOVASCULARIZATION.

PURPOSE: To investigate the utility of optical coherence tomography angiography (OCTA) for the detection of inflammatory choroidal neovascularization (iCNV) and monitoring their response to treatment. METHODS: A retrospective review of patients with a diagnosis of uveitis and associated iCNV with active exudation was performed. Active iCNV was determined by spectral domain OCT and/or fluorescein angiogram. Spectral domain OCTA outer retina to choriocapillaris slabs was evaluated for the presence of iCNV. Follow-up OCTA images were qualitatively assessed to determine whether regression of iCNV occurred after treatment. RESULTS: Thirteen eyes of 12 patients were included. The etiologies of uveitis include punctate inner choroidopathy (n = 4), multifocal choroiditis (n = 2), presumed sarcoid uveitis (n = 2), tuberculous choroiditis (n = 1), birdshot chorioretinopathy (n = 1), syphilitic uveitis (n = 1), serpiginous choroiditis (n = 1), and idiopathic panuveitis (n = 1). Inflammatory choroidal neovascularization was detected on en face OCTA in 10 of 13 eyes (76.9%). After iCNV treatment, en face OCTA demonstrated complete regression of iCNV in 5 of 10 eyes (50%), partial regression in 2 of 10 eyes (20%), and no regression in 3 of 10 eyes (30%). CONCLUSIONS: Optical coherence tomography angiography is an effective modality for detecting iCNV and could provide detailed visualization regarding location, morphologic structure, and flow of the iCNV and its response to therapy.

Fear of Blindness in Patients Undergoing Cataract Surgery.

BACKGROUND: Fear is a negative emotion induced by the threat of danger, pain and harm. Cataract surgery is one of the most performed surgeries in the world. The aim of this study was to investigate and analyze the predominant fears in patients undergoing cataract surgery. SUBJECTS AND METHODS: In this cross-sectional study 152 patients were examined. Self-designed questionnaires to examine emotions of the fear, anxiety, nervousness frequency gratitude was used and insecurity immediately before cataract surgery. We also examined what the greatest fear during the cataract surgery was. The fear of blindness was compared with other life fears such as cancer, memory loss, AIDS, stroke and heart attack. The presence of fear was compared in patients having had previous cataract surgery with those undergoing their first cataract surgery. Including criteria were adults with senile cataract. Excluding criteria was ocular co-morbidity, psychiatric disorders, inability to read, deafness and surgery under general anesthesia. Completed questionnaires were analyzed. Pearson's chi-squared test was used. RESULTS: Fear was the most frequent emotion before cataract surgery, present in 60.5% patients. Fear of blindness was the greatest fear during cataract surgery in 55.3% of patients. There was no statistically significant difference in fear in patients having undergone their first cataract surgery and patients before their second cataract surgery (p<0.05). CONCLUSION: Fear is the predominant emotion before cataract surgery which is in correlation to the leading life fear - fear of blindness. Good preoperative preparation and a trusting doctor-patient relationship are important for reducing the fear of the procedure.

GASTRIC CARCINOID TYPE 1 IN A PATIENT WITH AUTOIMMUNE POLYGLANDULAR SYNDROME: ADDITIONAL ENDOCRINOLOGICAL EVALUATION REQUIRED.

Autoimmune polyglandular syndrome by definition consists of two or more endocrinological insufficiencies or two organ specific autoimmune diseases. There are no stringent criteria for endocrinological evaluation of patients with one endocrine insufficiency. However, detailed endocrinological evaluation should be undertaken in patients with two autoimmune diseases. Additionally, follow up thereafter should be a must in these patients in order to avoid the possibility of not diagnosing subsequent autoimmune diseases that can occur. The aim of this case report is to point to the necessity of endocrinological screening to be made in patients presenting with gastric carcinoid type 1. We report on a 62-year-old woman who was diagnosed with primary hypothyroidism in 1993. In 2011, she was re-admitted to the hospital due to increasing fatigue. Macrocytic anemia, low vitamin B12 levels and positive parietal antibodies confirmed pernicious anemia. Furthermore, she underwent gastroscopy, which revealed two polyps in the corpus of the stomach and one in the fornix. Endoscopic mucosal resection was performed and histopathologic analysis confirmed three G1 gastric carcinoids (Ki67 2%). Additional endocrinological evaluation disclosed positive glutamic acid decarboxylase antibodies, but normal fasting and postprandial glucose and HbA1c. In 2013, she was diagnosed with glucose intolerance and subsequently with latent autoimmune diabetes of adulthood. Plasma glucose and HbA1c normalized after dietary intervention. Due to the increase of serum chromogranin A, prophylactic antrectomy was performed in 2014. The patient is still followed-up and has normal chromogranin A, gastrin and HbA1c levels.