Automated Region of Interest Selection Improves Deep Learning-Based Segmentation of Hyper-Reflective Foci in Optical Coherence Tomography Images.

Hyperreflective foci (HRF) have been associated with retinal disease progression and demonstrated as a negative prognostic biomarker for visual function. Automated segmentation of HRF in retinal optical coherence tomography (OCT) scans can be beneficial to identify the formation and movement of the HRF biomarker as a retinal disease progresses and can serve as the first step in understanding the nature and severity of the disease. In this paper, we propose a fully automated deep neural network based HRF segmentation model in OCT images. We enhance the model's performance by using a patch-based strategy that increases the model's compute on the HRF pixels. The patch-based strategy is evaluated against state of the art HRF segmentation pipelines on clinical retinal image data. Our results shows that the patch-based approach demonstrates a high precision score and intersection over union (IOU) using a ResNet34 segmentation model with Binary Cross Entropy loss function. The HRF segmentation pipeline can be used for analyzing HRF biomarkers for different retinopathies.

Health Equity and Disparities in ROP Care: A Need for Systematic Evaluation.

Retinopathy of prematurity (ROP) is a vasoproliferative retinal disorder that can have devastating visual sequelae if not managed appropriately. From an ophthalmology standpoint, ROP care is complex, since it spans multiple care settings and providers, including those in the neonatal intensive care unit (NICU), step down nurseries, and the outpatient clinic setting. This requires coordination and communication between providers, ancillary staff, and most importantly, effective communication with the patient's family members and caregivers. Often, factors related to the social determinants of health play a significant role in effective communication and care coordination with the family, and it is important for ophthalmologists to recognize these risk factors. The aim of this article is to (1) review the literature related to disparities in preterm birth outcomes and infants at risk for ROP; (2) identify barriers to ROP care and appropriate follow up, and (3) describe patient-oriented solutions and future directions for improving ROP care through a health equity lens.

POSTERIOR TRACTIONAL MEMBRANES FOLLOWING ANTI-VASCULAR ENDOTHELIAL GROWTH FACTOR FOR RETINOPATHY OF PREMATURITY.

PURPOSE: To report two cases of tractional membrane formation following treatment with anti-vascular endothelial growth factor therapy in infants with Stage-3 retinopathy of prematurity. METHODS: Retrospective review of electronic medical record for historical information, clinical examination documentation, and imaging from fundus photography, retinal ultrasonography, and fluorescein angiography. RESULTS: Two patients with Stage-3 retinopathy of prematurity, previously treated with laser therapy and intravitreal bevacizumab, were referred to our institution for tractional membranes. The first case is of a male infant with Zone-II disease that progressed to Stage 4A with evidence of inferotemporal tractional retinal detachment only in the left eye. The second case is of a male infant with stable Zone-I disease with an epiretinal membrane in the left eye.Pars plicata vitrectomy and membranectomy were required for both cases because of the concern for subsequent tractional retinal detachment. CONCLUSION: Formation of tractional retinal membranes has been associated with anti-vascular endothelial growth factor therapy. These cases describe the formation of posterior tractional membranes after anti-vascular endothelial growth factor therapy. This potential ocular outcome should be considered when determining treatment plans for retinopathy of prematurity.

Strengthening retinopathy of prematurity screening and treatment services in Nigeria: a case study of activities, challenges and outcomes 2017-2020.

OBJECTIVES: Retinopathy of prematurity (ROP) will become a major cause of blindness in Nigerian children unless screening and treatment services expand. This article aims to describe the collaborative activities undertaken to improve services for ROP between 2017 and 2020 as well as the outcome of these activities in Nigeria. DESIGN: Descriptive case study. SETTING: Neonatal intensive care units in Nigeria. PARTICIPANTS: Staff providing services for ROP, and 723 preterm infants screened for ROP who fulfilled screening criteria (gestational age <34 weeks or birth weight ≤2000 g, or sickness criteria). METHODS AND ANALYSIS: A WhatsApp group was initiated for Nigerian ophthalmologists and neonatologists in 2018. Members participated in a range of capacity-building, national and international collaborative activities between 2017 and 2018. A national protocol for ROP was developed for Nigeria and adopted in 2018; 1 year screening outcome data were collected and analysed. In 2019, an esurvey was used to collect service data from WhatsApp group members for 2017-2018 and to assess challenges in service provision. RESULTS: In 2017 only six of the 84 public neonatal units in Nigeria provided ROP services; this number had increased to 20 by 2018. Of the 723 babies screened in 10 units over a year, 127 (17.6%) developed any ROP; and 29 (22.8%) developed type 1 ROP. Only 13 (44.8%) babies were treated, most by intravitreal bevacizumab. The screening criteria were revised in 2020. Challenges included lack of equipment to regulate oxygen and to document and treat ROP, and lack of data systems. CONCLUSION: ROP screening coverage and quality improved after national and international collaborative efforts. To scale up and improve services, equipment for neonatal care and ROP treatment is urgently needed, as well as systems to monitor data. Ongoing advocacy is also essential.

Automated detection of early-stage ROP using a deep convolutional neural network.

BACKGROUND/AIM: To automatically detect and classify the early stages of retinopathy of prematurity (ROP) using a deep convolutional neural network (CNN). METHODS: This retrospective cross-sectional study was conducted in a referral medical centre in Taiwan. Only premature infants with no ROP, stage 1 ROP or stage 2 ROP were enrolled. Overall, 11 372 retinal fundus images were compiled and split into 10 235 images (90%) for training, 1137 (10%) for validation and 244 for testing. A deep CNN was implemented to classify images according to the ROP stage. Data were collected from December 17, 2013 to May 24, 2019 and analysed from December 2018 to January 2020. The metrics of sensitivity, specificity and area under the receiver operating characteristic curve were adopted to evaluate the performance of the algorithm relative to the reference standard diagnosis. RESULTS: The model was trained using fivefold cross-validation, yielding an average accuracy of 99.93%±0.03 during training and 92.23%±1.39 during testing. The sensitivity and specificity scores of the model were 96.14%±0.87 and 95.95%±0.48, 91.82%±2.03 and 94.50%±0.71, and 89.81%±1.82 and 98.99%±0.40 when predicting no ROP versus ROP, stage 1 ROP versus no ROP and stage 2 ROP, and stage 2 ROP versus no ROP and stage 1 ROP, respectively. CONCLUSIONS: The proposed system can accurately differentiate among ROP early stages and has the potential to help ophthalmologists classify ROP at an early stage.

Aggressive posterior retinopathy of prematurity in two cohorts of patients in South India: implications for primary, secondary, and tertiary prevention.

BACKGROUND: Aggressive posterior retinopathy of prematurity (APROP), which has a poor visual prognosis, is common in low- and middle-income countries (LMICs) as a result of suboptimal oxygen monitoring (primary prevention). The purpose of this study was to compare outcomes in APROP eyes treated with laser to eyes treated with antivascular endothelial growth factor (anti-VEGF) therapy. METHODS: The medical records of a cohort of APROP eyes treated with anti-VEGF (2010-2018) and another of eyes treated with laser photocoagulation (2002-2010) at the same institution in South India were reviewed retrospectively and compared. The main outcome was the proportion of eyes developing retinal detachment during resolution of acute ROP. RESULTS: A total of 398 eyes of 199 preterm babies with APROP were included: 168 eyes were treated with photocoagulation; 230, with anti-VEGF. From 2002 to 2010, compared to the more recent cohort, babies diagnosed with APROP tended to be heavier (P < 0.001), older (P < 0.001), and exposed to fewer days of oxygen (P = 0.02). In the laser-treated cohort, 17 of 168 eyes (10%) developed retinal detachment (7, stage 5; 12, stage 4), compared with 3 of 230 (1%) in the anti-VEGF cohort (all stage 4 [P = 0.002]). CONCLUSIONS: The incidence of retinal detachment was significantly lower in eyes treated with anti-VEGF compared with laser-.treated eyes In the absence of a randomized trial, these data suggest that anti-VEGF may lead to better anatomic outcomes, although questions remain concerning dosage, timing, and risks.

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity.

BACKGROUND: Prior work has demonstrated the near-perfect accuracy of a deep learning retinal image analysis system for diagnosing plus disease in retinopathy of prematurity (ROP). Here we assess the screening potential of this scoring system by determining its ability to detect all components of ROP diagnosis. METHODS: Clinical examination and fundus photography were performed at seven participating centres. A deep learning system was trained to detect plus disease, generating a quantitative assessment of retinal vascular abnormality (the i-ROP plus score) on a 1-9 scale. Overall ROP disease category was established using a consensus reference standard diagnosis combining clinical and image-based diagnosis. Experts then ranked ordered a second data set of 100 posterior images according to overall ROP severity. RESULTS: 4861 examinations from 870 infants were analysed. 155 examinations (3%) had a reference standard diagnosis of type 1 ROP. The i-ROP deep learning (DL) vascular severity score had an area under the receiver operating curve of 0.960 for detecting type 1 ROP. Establishing a threshold i-ROP DL score of 3 conferred 94% sensitivity, 79% specificity, 13% positive predictive value and 99.7% negative predictive value for type 1 ROP. There was strong correlation between expert rank ordering of overall ROP severity and the i-ROP DL vascular severity score (Spearman correlation coefficient=0.93; p<0.0001). CONCLUSION: The i-ROP DL system accurately identifies diagnostic categories and overall disease severity in an automated fashion, after being trained only on posterior pole vascular morphology. These data provide proof of concept that a deep learning screening platform could improve objectivity of ROP diagnosis and accessibility of screening.

Intravitreal injection of TIMP3 or the EGFR inhibitor erlotinib offers protection from oxygen-induced retinopathy in mice.

PURPOSE: Pathological neovascularization is a crucial component of proliferative retinopathies. Previous studies showed that inactivation of A disintegrin and metalloproteinase 17 (ADAM17), a membrane-anchored metalloproteinase that regulates epidermal growth factor receptor (EGFR) signaling, reduces pathological retinal neovascularization in a mouse model of oxygen-induced retinopathy (OIR). Here, we tested how genetic inactivation of a physiological ADAM17 inhibitor, the tissue inhibitor of matrix metalloproteinases-3 (TIMP3), or intravitreal injection of TIMP3 or of the EGFR inhibitor erlotinib influenced the outcome of OIR. METHODS: Wild-type mice were subjected to OIR in a chamber with 75% oxygen for 5 days beginning at postnatal day 7 (P7). Upon removal from the oxygen chamber at P12, they received a single intravitreal injection of TIMP3, erlotinib, or control. The central avascular area and neovascular tufts were measured after 5 days in room air (21% oxygen) at P17. Moreover, OIR experiments were performed with Timp3-/- mice and littermate controls. RESULTS: Timp3-/- mice showed greater revascularization of the central avascular area and developed equal or fewer neovascular tufts compared to littermate controls, depending on the genetic background. Wild-type mice injected with TIMP3 or erlotinib developed fewer neovascular tufts when compared to untreated littermates. Moreover, vessel regrowth into the avascular area was reduced in TIMP3-injected mice, but not in erlotinib-injected mice. CONCLUSIONS: These studies demonstrate that TIMP3 and erlotinib inhibit pathological neovascularization in the mouse retina, most likely due to inactivation of ADAM17 and the EGFR, respectively. Thus, TIMP3 and erlotinib emerge as attractive candidate antiangiogenic compounds for prevention and treatment of proliferative retinopathies.

Measurement of choroidal perfusion and thickness following systemic sildenafil (Viagra(®) ).

PURPOSE: To demonstrate anatomic and physiologic changes in the human choroid following systemic sildenafil citrate (Viagra®) using enhanced depth imaging spectral domain-optical coherence tomography (EDI-OCT) and swept-scan high-frequency digital ultrasound. METHODS: Seven healthy male subjects (mean age 32.7 years) were evaluated at baseline and 2 hr after ingesting 50 mg of sildenafil. Swept-scan high-frequency digital ultrasound and EDI-OCT were utilized to measure choroidal perfusion and thickness, respectively. Results were read by masked observers. The Wilcoxon signed-rank test and t-test were used to analyse differences in choroidal flow and thickness at baseline and 2 hr after ingestion of sildenafil. RESULTS: Two hours following sildenafil, increased choroidal perfusion was observed in 11 of 12 eyes measured by swept-scan high-frequency digital ultrasound. The mean increase was 3.46 (±2.00) times baseline with a range of 0.47-7.80 times baseline (p = 0.004). Increased choroidal thickness was observed in 12 of 12 eyes measured with EDI-OCT. The average choroidal thickness increased by 11.6% temporal to the fovea, 9.3% nasal to the fovea and 10.7% underneath the fovea (p < 0.001 for all values). CONCLUSIONS: Choroidal perfusion and thickness both increase in response to systemic sildenafil. These changes could secondarily affect retinal function, explain previously reported clinical symptoms and potentially be a useful adjunct for treatment of ocular diseases that would benefit from increased choroidal blood flow.

Pain assessment in premature infants treated with intravitreal antiangiogenic therapy for retinopathy of prematurity under topical anesthesia.

PURPOSE: To evaluate the physiological and behavioral pain response in premature infants receiving intravitreal bevacizumab injection (IVB) for retinopathy of prematurity (ROP) under topical anesthesia. METHODS: A prospective interventional non-comparative case series. Premature infants with high-risk prethreshold or threshold ROP received IVB using topical anesthesia with tetracaine eye drops. A Premature Infant Pain Profile was used to assess the pain response during the procedure. RESULTS: Nine premature infants requiring bilateral IVB therapy were included in the study. Mean gestational age was 28.7 ± 1.3 weeks, and birth weight was 1,200 ± 194 grams. The mean total pain score was found to be 8.7 ± 2.4 (range 5-14), indicating generally mild pain during the procedure. Eye squeeze was the most prominent indicator of pain. Most changes occurred at the beginning, with the insertion of the lid speculum and were hardly noted during the rest of the procedure including the injection itself. CONCLUSION: Topical anesthesia with tetracaine is an effective method for the relief of pain associated with intravitreal injections in premature infants with ROP.