CASE PRESENTATION: A 33-year-old Malay man with underlying acquired immunodeficiency syndrome receiving highly active antiretroviral therapy was referred to the Opthalmology Department with complaints of blurry vision for the past 2 months. He had tested positive for and been diagnosed with COVID-19 1 month previously. Clinical examination of the fundus revealed extensive perivascular sheathing of both the artery and vein suggestive of FBA in the right eye. Laboratory testing of nasal swabs for COVID-19 polymerase chain reaction (PCR) and serum CMV antibody were positive. The patient was then admitted to the COVID-19 ward and treated with intravenous ganciclovir.
CONCLUSION: Clinicians should be aware of and take the necessary standard precautions for possible coexistence of COVID-19 in an immunocompromised patient presenting with blurred vision, eye redness, dry eye and foreign body sensation despite the absence of clinical features suggestive of COVID-19. Whether FBA is one of the ocular signs of co-infection of COVID-19 and CMV remains unknown. Further studies are needed to provide more information on ocular signs presented in patients with concurrent COVID-19 and CMV infections.
METHOD: This cross-sectional study is comprised of 203 participants, all purportedly healthy term new-born infants from the Obstetrics and Gynaecology ward at Hospital Kuala Lumpur over a 6 months period. The examination list includes external eye examination, red reflex test, and fundus imaging using a wide-field digital retinal imaging system (Phoenix Clinical ICON Paediatric Retinal Camera) by a trained Investigator. The pathologies detected were documented. The results were compared and correlated with similar studies published in the literature previously.
RESULTS: Total ocular abnormalities were detected in 34% of the infants. The most common finding was retinal haemorrhage in 29.6% of the infants, of which 53.3% occurred bilaterally. Spontaneous vaginal delivery (SVD) remained the greatest risk factor which has nearly 3.5 times higher risk of new-borns developing retinal haemorrhage compared to Lower Segment Caesarean Section (LSCS). There was a 6% increased likelihood of developing retinal haemorrhage for every 1-min increment in the duration of 2nd stage of labour.
CONCLUSION: Universal eye screening for all new-borns using a wide-field digital imaging system is realistically possible, safe, and useful in detecting posterior segment disorders. The most common abnormality detected is retinal haemorrhage.
Objective: To compare treatment outcomes of ranibizumab, 0.5 mg, plus prompt vPDT combination therapy with ranibizumab, 0.5 mg, monotherapy in participants with PCV for 24 months.
Design, Setting, and Participants: This 24-month, phase IV, double-masked, multicenter, randomized clinical trial (EVEREST II) was conducted among Asian participants from August 7, 2013, to March 2, 2017, with symptomatic macular PCV confirmed using indocyanine green angiography.
Interventions: Participants (N = 322) were randomized 1:1 to ranibizumab, 0.5 mg, plus vPDT (combination therapy group; n = 168) or ranibizumab, 0.5 mg, plus sham PDT (monotherapy group; n = 154). All participants received 3 consecutive monthly ranibizumab injections, followed by a pro re nata regimen. Participants also received vPDT (combination group) or sham PDT (monotherapy group) on day 1, followed by a pro re nata regimen based on the presence of active polypoidal lesions.
Main Outcomes and Measures: Evaluation of combination therapy vs monotherapy at 24 months in key clinical outcomes, treatment exposure, and safety. Polypoidal lesion regression was defined as the absence of indocyanine green hyperfluorescence of polypoidal lesions.
Results: Among 322 participants (mean [SD] age, 68.1 [8.8] years; 225 [69.9%] male), the adjusted mean best-corrected visual acuity (BCVA) gains at month 24 were 9.6 letters in the combination therapy group and 5.5 letters in the monotherapy group (mean difference, 4.1 letters; 95% CI, 1.0-7.2 letters; P = .005), demonstrating that combination therapy was superior to monotherapy by the BCVA change from baseline to month 24. Combination therapy was superior to monotherapy in terms of complete polypoidal lesion regression at month 24 (81 of 143 [56.6%] vs 23 of 86 [26.7%] participants; P
METHODS: In this work, we present a bit-plane slicing (BPS) and local binary pattern (LBP) based novel approach for glaucoma diagnosis. Firstly, our approach separates the red (R), green (G), and blue (B) channels from the input color fundus image and splits the channels into bit planes. Secondly, we extract LBP based statistical features from each of the bit planes of the individual channels. Thirdly, these features from the individual channels are fed separately to three different support vector machines (SVMs) for classification. Finally, the decisions from the individual SVMs are fused at the decision level to classify the input fundus image into normal or glaucoma class.
RESULTS: Our experimental results suggest that the proposed approach is effective in discriminating normal and glaucoma cases with an accuracy of 99.30% using 10-fold cross validation.
CONCLUSIONS: The developed system is ready to be tested on large and diverse databases and can assist the ophthalmologists in their daily screening to confirm their diagnosis, thereby increasing accuracy of diagnosis.
METHODS: The morphological features of the disc that is characteristic of glaucoma are clearly seen in the fundus images. However, manual inspection of the acquired fundus images may be prone to inter-observer variation. Therefore, a computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging. In this paper, we reviewed existing techniques to automatically diagnose glaucoma.
RESULTS: The use of CAD is very effective in the diagnosis of glaucoma and can assist the clinicians to alleviate their workload significantly. We have also discussed the advantages of employing state-of-art techniques, including deep learning (DL), when developing the automated system. The DL methods are effective in glaucoma diagnosis.
CONCLUSIONS: Novel DL algorithms with big data availability are required to develop a reliable CAD system. Such techniques can be employed to diagnose other eye diseases accurately.
DESIGN: Artificial intelligence (neural network) study.
METHODS: We assessed 1400 OCT scans of patients with neovascular AMD. Fifteen physical features for each eligible OCT, as well as patient age, were used as input data and corresponding recorded visual acuity as the target data to train, validate, and test a supervised neural network. We then applied this network to model the impact on acuity of defined OCT changes in subretinal fluid, subretinal hyperreflective material, and loss of external limiting membrane (ELM) integrity.
RESULTS: A total of 1210 eligible OCT scans were analyzed, resulting in 1210 data points, which were each 16-dimensional. A 10-layer feed-forward neural network with 1 hidden layer of 10 neurons was trained to predict acuity and demonstrated a root mean square error of 8.2 letters for predicted compared to actual visual acuity and a mean regression coefficient of 0.85. A virtual model using this network demonstrated the relationship of visual acuity to specific, programmed changes in OCT characteristics. When ELM is intact, there is a shallow decline in acuity with increasing subretinal fluid but a much steeper decline with equivalent increasing subretinal hyperreflective material. When ELM is not intact, all visual acuities are reduced. Increasing subretinal hyperreflective material or subretinal fluid in this circumstance reduces vision further still, but with a smaller gradient than when ELM is intact.
CONCLUSIONS: The supervised machine learning neural network developed is able to generate an estimated visual acuity value from OCT images in a population of patients with AMD. These findings should be of clinical and research interest in macular degeneration, for example in estimating visual prognosis or highlighting the importance of developing treatments targeting more visually destructive pathologies.