Search

Purpose Stage is an important feature to identify in retinal images of infants at risk of retinopathy of prematurity (ROP). The purpose of this study was to implement a convolutional neural network (CNN) for binary detection of stages 1, 2, and 3 in ROP and to evaluate its generalizability across different populations and camera systems. Design Diagnostic validation study of CNN for stage detection. Participants Retinal fundus images obtained from preterm infants during routine ROP screenings. Methods Two datasets were used: 5943 fundus images obtained by RetCam camera (Natus Medical, Pleasanton, CA) from 9 North American institutions and 5049 images obtained by 3nethra camera (Forus Health Incorporated, Bengaluru, India) from 4 hospitals in Nepal. Images were labeled based on the presence of stage by 1 to 3 expert graders. Three CNN models were trained using 5-fold cross-validation on datasets from North America alone, Nepal alone, and a combined dataset and were evaluated on 2 held-out test sets consisting of 708 and 247 images from the Nepali and North American datasets, respectively. Main Outcome Measures Convolutional neural network performance was evaluated using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, and specificity. Results Both the North American– and Nepali-trained models demonstrated high performance on a test set from the same population: AUROC, 0.99; AUPRC, 0.98; sensitivity, 94%; and AUROC, 0.97; AUPRC, 0.91; and sensitivity, 73%; respectively. However, the performance of each model decreased to AUROC of 0.96 and AUPRC of 0.88 (sensitivity, 52%) and AUROC of 0.62 and AUPRC of 0.36 (sensitivity, 44%) when evaluated on a test set from the other population. Compared with the models trained on individual datasets, the model trained on a combined dataset achieved improved performance on each respective test set: sensitivity improved from 94% to 98% on the North American test set and from 73% to 82% on the Nepali test set. Conclusions A CNN can identify accurately the presence of ROP stage in retinal images, but performance depends on the similarity between training and testing populations. We demonstrated that internal and external performance can be improved by increasing the heterogeneity of the training dataset features of the training dataset, in this case by combining images from different populations and cameras.

Purpose To assess accuracy and adherence of visual field (VF) home monitoring in a pilot sample of patients with glaucoma. Design Prospective longitudinal feasibility and reliability study. Methods Twenty adults (median 71 years) with an established diagnosis of glaucoma were issued a tablet perimeter (Eyecatcher) and were asked to perform 1 VF home assessment per eye, per month, for 6 months (12 tests total). Before and after home monitoring, 2 VF assessments were performed in clinic using standard automated perimetry (4 tests total, per eye). Results All 20 participants could perform monthly home monitoring, though 1 participant stopped after 4 months (adherence: 98% of tests). There was good concordance between VFs measured at home and in the clinic (r = 0.94, P Conclusions Home monitoring of VFs is viable for some patients and may provide clinically useful data.

This article examines the efficacy of educational partnerships by sport management and business programs with professional sports clubs. We utilize a case study of the Lock Haven University partner...

Purpose Aggressive posterior retinopathy of prematurity (AP-ROP) is a vision-threatening disease with a significant rate of progression to retinal detachment. The purpose of this study was to characterize AP-ROP quantitatively by demographics, rate of disease progression, and a deep learning-based vascular severity score. Design Retrospective analysis. Participants The Imaging and Informatics in ROP cohort from 8 North American centers, consisting of 947 patients and 5945 clinical eye examinations with fundus images, was used. Pretreatment eyes were categorized by disease severity: none, mild, type 2 or pre-plus, treatment-requiring (TR) without AP-ROP, TR with AP-ROP. Analyses compared TR with AP-ROP and TR without AP-ROP to investigate differences between AP-ROP and other TR disease. Methods A reference standard diagnosis was generated for each eye examination using previously published methods combining 3 independent image-based gradings and 1 ophthalmoscopic grading. All fundus images were analyzed using a previously published deep learning system and were assigned a score from 1 through 9. Main Outcome Measures Birth weight, gestational age, postmenstrual age, and vascular severity score. Results Infants who demonstrated AP-ROP were more premature by birth weight (617 g vs. 679 g; P = 0.01) and gestational age (24.3 weeks vs. 25.0 weeks; P Conclusions Premature infants in North America with AP-ROP are born younger and demonstrate disease earlier than infants with less severe ROP. Disease severity is quantifiable with a deep learning-based score, which correlates with clinically identified categories of disease, including AP-ROP. The rate of progression to peak disease is greatest in eyes that demonstrate AP-ROP compared with other treatment-requiring eyes. Analysis of quantitative characteristics of AP-ROP may help improve diagnosis and treatment of an aggressive, vision-threatening form of ROP.

To investigate late retinal findings and complications of eyes with a history of retinopathy of prematurity (ROP) that did not meet treatment criteria and did not receive treatment during infancy.Retrospective, nonconsecutive, noncomparative, multicenter case series.Three hundred sixty-three eyes of 186 patients.Data were requested from multiple providers on premature patients with a history of ROP and no treatment during infancy who demonstrated late retinal findings or complications and included age, gender, gestational age and weight, zone and stage at infancy, visual acuity, current retina vascularization status, vitreous character, presence of peripheral retinal findings such as lattice retinal tears and detachments (RDs), retinoschisis, and fluorescein findings.Rate of RDs and factors conferring a higher risk of RDs.The average age was 34.5 years (range, 7-76 years), average gestational age was 26.6 weeks (range, 23-34 weeks), and average birth weight was 875 g (range, 425-1590 g). Findings included lattice in 196 eyes (54.0%), atrophic holes in 126 eyes (34.7%), retinal tears in 111 eyes (30.6%), RDs in 140 eyes (38.6 %), tractional retinoschisis in 44 eyes (11.9%), and visible vitreous condensation ridge-like interface in 112 eyes (30.5%). Fluorescein angiography (FA) was performed in 113 eyes, of which 59 eyes (52.2%) showed leakage and 16 eyes (14.2%) showed neovascularization. Incomplete vascularization posterior to zone 3 was common (71.6% of eyes). Retinal detachments were more likely in patients with a gestational age of 29 weeks or less (P0.05) and in eyes with furthest vascularization to posterior zone 2 eyes compared with zone 3 eyes (P = 0.009).Eyes with ROP not meeting the treatment threshold during infancy showed various late retinal findings and complications, of which RDs were the most concerning. Complications were seen in all age groups, including patients born after the Early Treatment for Retinopathy of Prematurity Study. Contributing factors to RDs included atrophic holes within peripheral avascular retina, visible vitreous condensation ridge-like interface with residual traction, and premature vitreous syneresis. We recommend regular examinations and consideration of ultra-widefield FA examinations. Prospective studies are needed to explore the frequency of complications and benefit of prophylactic treatment and if eyes treated with anti-vascular endothelial growth factor therapy are at risk of similar findings and complications.

Purpose To report the natural history of untreated neovascular age-related macular degeneration (nAMD) regarding subsequent macular atrophy. Design Prospective cohort within a randomized, controlled trial of oral micronutrient supplements. Participants Age-Related Eye Disease Study (AREDS) participants (55–80 years) who demonstrated nAMD during follow-up (1992–2005), prior to anti–vascular endothelial growth factor (VEGF) therapy. Methods Color fundus photographs were collected at annual study visits and graded centrally for late age-related macular degeneration (AMD). Incident macular atrophy after nAMD was examined by Kaplan-Meier analysis and proportional hazards regression. Main Outcome Measures Incident macular atrophy after nAMD. Results Of the 4757 AREDS participants, 708 eyes (627 participants) demonstrated nAMD during follow-up and were eligible. The cumulative risks of incident macular atrophy after untreated nAMD were 9.6% (standard error, 1.2%), 31.4% (standard error, 2.2%), 43.1% (standard error, 2.6%), and 61.5% (standard error, 4.3%) at 2, 5, 7, and 10 years, respectively. This corresponded to a linear risk of 6.5% per year. The cumulative risk of central involvement was 30.4% (standard error, 3.2%), 43.4% (standard error, 3.8%), and 57.0% (standard error, 4.8%) at first appearance of atrophy, 2 years, and 5 years, respectively. Geographic atrophy (GA) in the fellow eye was associated with increased risk of macular atrophy (hazard ratio [HR], 1.70; 95% confidence interval [CI], 1.17–2.49; P = 0.006). However, higher 52-single nucleotide polymorphism AMD genetic risk score was not associated with increased risk of macular atrophy (HR, 1.03; 95% CI, 0.90–1.17; P = 0.67). Similarly, no significant differences were observed according to SNPs at CFH, ARMS2, or C3. Conclusions The rate of incident macular atrophy after untreated nAMD is relatively high, increasing linearly over time and affecting half of eyes by 8 years. Hence, factors other than anti-VEGF therapy are involved in atrophy development, including natural progression to GA. Comparison with studies of treated nAMD suggests it may not be necessary to invoke a large effect of anti-VEGF therapy on inciting macular atrophy, although a contribution remains possible. Central involvement is present in one third of eyes at the outset (similar to pure GA) and increases linearly to half at 3 years.

Retrospective evaluation of a deep learning-derived retinopathy of prematurity (ROP) vascular severity score in an operational ROP screening program demonstrated high diagnostic performance for detection of type 2 or worse ROP. To our knowledge, this is the first report in the literature that evaluated the use of artificial intelligence for ROP screening and represents a proof of concept. With further prospective validation, this technology might improve the accuracy, efficiency, and objectivity of diagnosis and facilitate earlier detection of disease progression in patients with potentially blinding ROP.

Purpose: To characterize retinopathy of prematurity (ROP) training practices in international residency and fellowship programs. Methods: A publicly available online-based platform ( http://www.SurveyMonkey.com ) was used to develop a 28-question multiple-choice survey that targeted ROP screening and treatment methods. The authors solicited training programs in the Philippines, Thailand, and Taiwan. Results: Programs from three countries participated in the survey, and a total of 95 responses collected from residents, fellows, and attending ophthalmologists were analyzed. A descriptive analysis demonstrated that 45 participants (47%) reported 1% to 33% of ROP screenings were performed under direct supervision of attending ophthalmologists, and 35 (37%) reported the use of formal assessments. The majority of participants (Country A: 87%, Country B: 71%, and Country C: 75%) estimated 1% to 33% of their practice was spent screening for ROP. Notably, 44 participants (46%) reported performing zero laser photocoagulation treatments for ROP during training (Country A: 65%, Country B: 38%, and Country C: 38%). Conclusions: International ophthalmology trainees perform a limited number of ROP examinations and laser interventions. ROP screenings are often unsupervised and lead to no formal evaluation by an attending ophthalmologist. Limited ROP training among ophthalmologists may lead to misdiagnosis and ultimately mismanagement of a patient. Loss of vision and exposure to unwarranted treatments are among the implications of such errors. The findings highlight the need to improve ROP training in international ophthalmology residency and fellowship programs. [ J Pediatr Ophthalmol Strabismus . 2019;56(5):282–287.]

Objective To determine which pediatric populations, if any, benefit from exogenous melatonin supplementation. Methods PubMed was utilized for the purposes of this systematic review. The studies selected evaluated melatonin use in pediatric special populations and included randomized controlled trials, crossover studies, and meta-analyses. Each study’s objectives, measures of outcomes, and dosing strategies of melatonin were reviewed along with the results and author’s conclusions. Results Our analysis of the available data offers mixed results and recommendations with regard to the decision of whether to add supplementation of melatonin. Conclusion With further regulation of melatonin supplements, it may be plausible to hold larger, multicenter trials and come to a firm recommendation in the future. At this time, we believe that the benefit of exogenous melatonin supplementation outweighs the risks of adverse events and therefore would recommend its use in aiding patients in improving their sleep. Exogenous supplementation with melatonin should be used at the physician’s and patient’s discretion.

Purpose: Retinopathy of prematurity (ROP) is the leading cause of visual impairment in premature infants, and middle-income nations are currently experiencing the “third epidemic” of ROP. Screening programs are essential to prevent negative visual outcomes, but screening efforts require a great amount of resources from healthcare systems and are difficult to marshal, particularly in geographically isolated or resource-limited settings. Telemedical screening programs using remote digital fundus imaging (RDFI) systems hold the promise of alleviating many of the burdens that currently make screening for ROP logistically challenging. Methods: Literature review of the current evidence for RDFI telescreening for ROP, with editorial discussion and recommendations. Results: In this review, we summarize the robust body of literature regarding the efficacy of RDFI, the feasibility of telescreening programs, and experiences from current live telescreening programs. We discuss the strengths and limitations of the current evidence and of the screening programs and consider the best practices in developing de novo telemedical screening programs for ROP. The review concludes with a discussion of promising future areas of research and development. Conclusions: RDFI ROP screening programs can be accurate and reliable. They show promise in improving many current challenges in screening infants for ROP, may be able to improve some aspects of care, and have been demonstrated to be cost-effective.

ObjectivesTo explore the acceptability of home visual field (VF) testing using Eyecatcher among people with glaucoma participating in a 6-month home monitoring pilot study.DesignQualitative study using face-to-face semistructured interviews. Transcripts were analysed using thematic analysis.SettingParticipants were recruited in the UK through an advertisement in the International Glaucoma Association (now Glaucoma UK) newsletter.ParticipantsTwenty adults (10 women; median age: 71 years) with a diagnosis of glaucoma were recruited (including open angle and normal tension glaucoma; mean deviation=2.5 to −29.9 dB).ResultsAll participants could successfully perform VF testing at home. Interview data were coded into four overarching themes regarding experiences of undertaking VF home monitoring and attitudes towards its wider implementation in healthcare: (1) comparisons between Eyecatcher and Humphrey Field Analyser (HFA); (2) capability using Eyecatcher; (3) practicalities for effective wider scale implementation; (4) motivations for home monitoring.ConclusionsParticipants identified a broad range of benefits to VF home monitoring and discussed areas for service improvement. Eyecatcher was compared positively with conventional VF testing using HFA. Home monitoring may be acceptable to at least a subset of people with glaucoma.

Optical coherence tomography (OCT) and OCT angiography (OCTA) enable noninvasive structural and angiographic imaging of the eye. Portable handheld OCT/OCTA systems are required for imaging patients in the supine position. Examples include infants in the neonatal intensive care unit (NICU) and operating room (OR). The speed of image acquisition plays a pivotal role in acquiring high-quality OCT/OCTA images, particularly with the handheld system, since both the operator hand tremor and subject motion can cause significant motion artifacts. In addition, having a large field of view and the ability of real-time data visualization are critical elements in rapid disease screening, reducing imaging time, and detecting peripheral retinal pathologies. The arrangement of optical components is less flexible in the handheld system due to the limitation of size and weight. In this paper, we introduce a 400-kHz, 55-degree field of view handheld OCT/OCTA system that has overcome many technical challenges as a portable OCT system as well as a high-speed OCTA system. We demonstrate imaging premature infants with retinopathy of prematurity (ROP) in the NICU, a patient with incontinentia pigmenti (IP), and a patient with X-linked retinoschisis (XLRS) in the OR using our handheld OCT system. Our design may have the potential for improving the diagnosis of retinal diseases and help provide a practical guideline for designing a flexible and portable OCT system.

Purpose\ud In the UK, most referrals to the hospital eye service (HES) originate from community optometrists (CO). This audit investigates the quality of referrals, replies, and communication between CO and the HES.\ud \ud Methods\ud Optometric referrals and replies were extracted from three practices in England. If no reply letter was found, the records were searched at each local HES unit, and additional replies or records copied. De‐identified referrals, replies and records were audited by a panel against established standards to evaluate whether the referrals were necessary, accurate and directed to the appropriate professional. The referral rate (RR) and referral reply rate (RRR) were calculated.\ud \ud Results\ud A total of 459 de‐identified referrals were extracted. The RR ranged from 3.6%–8.7%. The proportion of referred patients who were seen in the HES unit was 63%–76%. From the CO perspective, the proportion of referrals for which they received replies ranged from 26%–49%. Adjusting the number of referrals for cases when it would be reasonable to expect an HES reply, RRR becomes 38%–62%. Patients received a copy of the reply in 3%–21% of cases. Referrals were made to the appropriate service in over 95% of cases, were judged necessary in 93%–97% and were accurate in 81%–98% of cases. The referral reply addressed the reason for the referral in 93%–97% and was meaningful in 94%–99% of cases. The most common conditions referred were glaucoma, cataract, anterior segment lesions, and neurological/ocular motor anomalies. The CO/HES dyad (pairing) in the area with the lowest average household income had the highest RR.\ud \ud Conclusions\ud In contrast with the Royal College of Ophthalmologists/College of Optometrists joint statement on sharing patient information, CO referrals often do not elicit a reply to the referring CO. Replies from the HES to COs are important for patient care, benefitting patients and clinicians, and minimising unnecessary HES appointments.

BACKGROUND AND OBJECTIVE: To identify factors associated with successful treatment discontinuation in eyes with retinal vein occlusions (RVOs) and macular edema (ME) in real-world settings. PATIENTS AND METHODS: Retrospective study of 214 eyes with RVO and ME with 24-month follow-up at five academic centers. Regression analyses identified factors associated with (1) successful treatment discontinuation for at least 6 months without fluid recurrence and (2) best-corrected visual acuity (BCVA) at 24 months. RESULTS: Forty percent of eyes with branch RVO and 35% with central RVO (CRVO) / hemi-retinal RVO (HRVO) successfully discontinued therapy without fluid recurrence, with median time to discontinuation of 6 and 7 months, respectively. Lower 6-month central subfield thickness was associated with greater likelihood of treatment discontinuation within 24 months for eyes with CRVO/HRVO ( P = .001), whereas better 6-month BCVA was associated with better 24-month BCVA for all RVO subtypes ( P < .001). CONCLUSION: Early anatomic response at 6 months is associated with greater likelihood of stopping treatments. [ Ophthalmic Surg Lasers Imaging Retina . 2021;52:84–92.]

Purpose:\ud \ud While there are numerous studies comparing open-view autorefractors to subjective refraction or other open-view autorefractors, most studies between closed and open-view autorefraction tend to focus on children rather than young adults. The aim of this study was to determine the concordance in non-cycloplegic refractive error between two modern objective autorefractors: the closed-view monocular Topcon TRK-2P and the binocular open-view Grand Seiko WR-5500.\ud \ud Methods:\ud \ud Fifty young adults aged 20–29 years (mean age 22 ± 1.6 years) underwent non-cycloplegic autorefraction using the Grand Seiko WAM-5500 (open view) and Topcon TRK-2P (closed-view) autorefractors on both eyes. Findings were expressed as the isolated spherical component and were also converted from clinical to vector notation: Mean Spherical Error (MSE) and the astigmatic components J0 and J45.\ud \ud Results:\ud \ud Mean MSE ± SD was −1.00 ± 2.40D for the Grand Seiko WAM-5500 compared to −1.23 ± 2.29D for the Topcon TRK-2P. Up to seventy-six percent of the cohort had mean spherical errors from the Topcon TRK-2P which fell within ±0.50D of the Grand Seiko reading and 58% fell within ±0.25D. Mean differences between the two instruments were statistically significant for all components (J0, spherical, and MSE) (p 0.05).\ud \ud Conclusions:\ud \ud The differences in non-cycloplegic MSE between these two instruments are small, but statistically significant. From a clinical perspective the Topcon TRK-2P may serve as a useful starting point for subjective refraction, but additional work is needed to help further minimise differences between the instruments.

Purpose: To explore the feasibility of using various easy-to-obtain biomarkers to monitor non-compliance (measurement error) during visual field assessments.Methods: Forty-two healthy adults (42 eyes) and seven glaucoma patients (14 eyes) underwent two same-day visual field assessments. An ordinary webcam was used to compute seven potential biomarkers of task compliance, based primarily on eye gaze, head pose, and facial expression. We quantified the association between each biomarker and measurement error, as defined by (1) test-retest differences in overall test scores (mean sensitivity), and (2) failures to respond to visible stimuli on individual trials (stimuli -3 dB or more brighter than threshold).Results: In healthy eyes, three of the seven biomarkers were significantly associated with overall (test-retest) measurement error (P = 0.003-0.007), and at least two others exhibited possible trends (P = 0.052-0.060). The weighted linear sum of all seven biomarkers was associated with overall measurement error, in both healthy eyes (r = 0.51, P Conclusions: Inexpensive, autonomous measures of task compliance are associated with measurement error in visual field assessments, in terms of both the overall reliability of a test and failures to respond on particular trials ("lapses"). This could be helpful for identifying low-quality assessments and for improving assessment techniques (e.g., by discounting suspect responses or by automatically triggering comfort breaks or encouragement).Translational Relevance: This study explores a potential way of improving the reliability of visual field assessments, a crucial but notoriously unreliable clinical measure.

Background Although microscopic positive margins appear to have no independent prognostic impact in papillary thyroid cancer (PTC), this may not be the case in pT4a tumors. Methods Retrospective analysis of 610 patients with PTC, 39 with pT4a tumors, to determine if microscopic positive margins impact disease-free survival (DFS) in pT4a PTC. Results On univariate analysis, microscopic positive margins were not associated with reduced DFS in patients with no extrathyroidal extension (ETE) (hazard ratio [HR], 1.7; P = 0.32), microscopic ETE (HR, 1.6; P = 0.36), or macroscopic ETE limited to strap muscles (HR, 1.2; P = 0.87). In contrast, microscopic positive margins were associated with reduced DFS in T4a disease (HR, 4.1; P = 0.04). Disease recurrence was nodal, distant, or biochemical, and did not occur directly at the site of positive margins. Conclusion Although microscopic positive margins do not influence DFS in the majority of patients with PTC, they are associated with a fourfold increased risk of recurrence in pT4a disease.

FMS-like tyrosine kinase 3 (FLT3) is a receptor tyrosine kinase that is responsible for the proliferation and survival of hematopoietic stem cells in acute myeloid leukemia. Although patients with FLT3 mutations have similar rates of remission following induction chemotherapy, relapse rates are significantly higher and patients with FLT3 mutations have significantly worse outcomes for overall survival and disease-free survival. Early FLT3 inhibitors, such as sorafenib, were non-selective and inhibited several tyrosine kinase receptors resulting in significant toxicity. The treatment of FLT3-positive acute myeloid leukemia has advanced recently with the development of a several FLT3-targeting agents that are either approved or in development. Midostaurin represents the first FDA-approved treatment targeted against FLT3, and there are several promising agents currently undergoing clinical trials. Although certain mutations confer resistance to earlier generation FLT3-targeted tyrosine kinase inhibitors, newer agents show activity in the presence of these mutations.

Topic Retinopathy of prematurity (ROP) is a proliferative retinal vascular disease in premature infants and is a major cause of childhood blindness worldwide. In addition to known clinical risk factors such as low birth weight and gestational age, there is a growing body of evidence supporting a genetic basis for ROP. Clinical Relevance Although comorbidities and environmental factors—most notably gestational age and oxygen—have been identified as contributing to ROP outcomes in premature infants, some infants progress to severe disease despite absence of these clinical risk factors. The contribution of genetic factors may explain these differences and allow better detection and treatment of infants at risk for severe ROP. Methods To comprehensively review genetic factors that potentially contribute to the development and severity of ROP, we conducted a literature search focusing on the genetic basis for ROP. Terms related to other heritable retinal vascular diseases such as “familial exudative vitreoretinopathy,” as well as to genes implicated in animal models of ROP, were also used to capture research in diseases with similar pathogenesis to ROP in humans with known genetic components. Results Contributions across several genetic domains are described, including vascular endothelial growth factor, the Wnt signaling pathway, insulin-like growth factor 1, inflammatory mediators, and brain-derived neurotrophic factor. Conclusions Most candidate gene studies of ROP have limitations such as inability to replicate results, conflicting results from various studies, small sample size, and differences in clinical characterization. Additional difficulty arises in separating the contribution of genetic factors such as Wnt signaling to ROP and prematurity. Although studies have implicated involvement of multiple signaling pathways in ROP, the genetics of ROP have not been clearly elucidated. Next-generation sequencing and genome-wide association studies have potential to expand future understanding of underlying genetic risk factors and pathophysiology of ROP.

Background Shoulder dislocations are common injuries among athletes. Patients with instability after their injury often require stabilization procedures for treatment. The primary outcome measure was to see whether there was any correlation between the side of traumatic shoulder dislocation and dominance of hand. Secondary outcomes were to look at subgroups of age and sporting discipline. Materials and methods This study recruited all patients with a frank dislocation that required arthroscopic surgical stabilization who attended the same private orthopedic surgeon. Exclusion criteria included injury without frank dislocation, nonsport-related injuries, and ambidexterity. Data were collected for 325 of 365 patients (89.0% response rate) Results There were 278 right hand-dominant patients (85.5%), with 136 (48.9%) requiring arthroscopic stabilization of their dominant side for dislocation. Of the remaining 47 left hand-dominant patients, 17 (36.2%) required operations on their dominant arm. In total, 153 patients (47.1%) dislocated their dominant shoulder and 172 (52.9%) dislocated their nondominant shoulder, with an odds ratio of 1.692 (95% confidence interval, 0.893-3.205). Conclusions This study suggests that there is no statistical significance between the side of shoulder dislocation and hand dominance of patients with shoulder dislocation. Future research could investigate further the causal relationship between hand dominance and mechanisms of injury.

BACKGROUND The prognostic significance of microscopic positive margins in papillary thyroid carcinoma (PTC) remains unclear. The aim of this study was to determine if microscopic positive margins are associated with increased risk of disease recurrence. METHODS This is a retrospective analysis of 610 patients with PTC using multivariate Cox regression to evaluate the association between microscopic positive margins and disease-free survival. RESULTS Microscopic positive margins were found in 67 (11%) patients and associated with extrathyroidal extension (P

Background The American Joint Committee on Cancer (AJCC) removed microscopic extrathyroidal extension (ETE) from the 8th edition T staging for papillary thyroid cancer (PTC) based on increasing evidence that it is not an independent prognostic factor. Objectives We compared the prognostic performance of AJCC 7th (pT7) and 8th (pT8) edition T stage systems, particularly in patients ≥55 years old without macroscopic ETE or distant metastases in whom T classification affects AJCC Tumor Node Metastasis (TNM) stage. Method A retrospective analysis of disease-free survival (DFS) in 577 patients with PTC comparing pT8 vs pT7 using the Akaike information criterion (AIC), Harrell’s C-index, and Proportion of Variation Explained (PVE). Results Of 105 patients with AJCC7 T3 disease, 74 were down-staged. Overall, the prognostic performance of pT7 and pT8 was similar. However, in patients ≥55 years old without macroscopic ETE or distant metastases, pT8 was inferior to pT7 on the basis of higher AIC, lower C-index (0.67 vs 0.76), and lower PVE (30% vs 45%). In this subset, microscopic ETE was associated with multiple other adverse prognostic features and reduced DFS (hazard ratio, 2.8; 95% confidence interval, 1.5 to 5.2; P = 0.002), irrespective of tumor size. Discussion In our cohort, pT8 was inferior to pT7 in patients ≥55 years old without macroscopic ETE or distant metastases in whom T classification affects TNM stage. Microscopic ETE was strongly associated with other adverse prognostic factors and reduced DFS in this patient subgroup and may be an effective surrogate for disease biology in PTC, irrespective of whether it is an independent prognostic factor.

PURPOSE: To evaluate a tele-education system developed to improve diagnostic competency in retinopathy of prematurity (ROP) by ophthalmologists-in-training in Mexico. DESIGN: Prospective, randomized cohort study. PARTICIPANTS: Fifty-eight ophthalmology residents and fellows from a training program in Mexico consented to participate. Twenty-nine of 58 trainees (50%) were randomized to the educational intervention (pretest, ROP tutorial, ROP educational chapters, and posttest), and 29 of 58 trainees (50%) were randomized to a control group (pretest and posttest only). METHODS: A secure web-based educational system was created using clinical cases (20 pretest, 20 posttest, and 25 training chapter-based) developed from a repository of over 2500 unique image sets of ROP. For each image set used, a reference standard ROP diagnosis was established by combining the clinical diagnosis by indirect ophthalmoscope examination and image-based diagnosis by multiple experts. Trainees were presented with image-based clinical cases of ROP during a pretest, posttest, and training chapters. MAIN OUTCOME MEASURES: The accuracy of ROP diagnosis (e.g., plus disease, zone, stage, category) was determined using sensitivity and specificity calculations from the pretest and posttest results of the educational intervention group versus control group. The unweighted kappa statistic was used to analyze the intragrader agreement for ROP diagnosis by the ophthalmologists-in-training during the pretest and posttest for both groups. RESULTS: Trainees completing the tele-education system had statistically significant improvements (P < 0.01) in the accuracy of ROP diagnosis for plus disease, zone, stage, category, and aggressive posterior ROP (AP-ROP). Compared with the control group, trainees who completed the ROP tele-education system performed better on the posttest for accurately diagnosing plus disease (67% vs. 48%; P = 0.04) and the presence of ROP (96% vs. 91%; P < 0.01). The specificity for diagnosing AP-ROP (94% vs. 78%; P < 0.01), type 2 ROP or worse (92% vs. 84%; P = 0.04), and ROP requiring treatment (89% vs. 79%; P < 0.01) was better for the trainees completing the tele-education system compared with the control group. Intragrader agreement improved for identification of plus disease, zone, stage, and category of ROP after completion of the educational intervention. CONCLUSIONS: A tele-education system for ROP education was effective in improving the diagnostic accuracy of ROP by ophthalmologists-in-training in Mexico. This system has the potential to increase competency in ROP diagnosis and management for ophthalmologists-in-training from middle-income nations.

Purpose:To describe a series of retinal arterial occlusions in healthy children.Methods:Chart review from multiple US and international institutions.Results:Five episodes affecting otherwise health...

Using medical images to evaluate disease severity and change over time is a routine and important task in clinical decision making. Grading systems are often used, but are unreliable as domain experts disagree on disease severity category thresholds. These discrete categories also do not reflect the underlying continuous spectrum of disease severity. To address these issues, we developed a convolutional Siamese neural network approach to evaluate disease severity at single time points and change between longitudinal patient visits on a continuous spectrum. We demonstrate this in two medical imaging domains: retinopathy of prematurity (ROP) in retinal photographs and osteoarthritis in knee radiographs. Our patient cohorts consist of 4861 images from 870 patients in the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) cohort study and 10,012 images from 3021 patients in the Multicenter Osteoarthritis Study (MOST), both of which feature longitudinal imaging data. Multiple expert clinician raters ranked 100 retinal images and 100 knee radiographs from excluded test sets for severity of ROP and osteoarthritis, respectively. The Siamese neural network output for each image in comparison to a pool of normal reference images correlates with disease severity rank (ρ = 0.87 for ROP and ρ = 0.89 for osteoarthritis), both within and between the clinical grading categories. Thus, this output can represent the continuous spectrum of disease severity at any single time point. The difference in these outputs can be used to show change over time. Alternatively, paired images from the same patient at two time points can be directly compared using the Siamese neural network, resulting in an additional continuous measure of change between images. Importantly, our approach does not require manual localization of the pathology of interest and requires only a binary label for training (same versus different). The location of disease and site of change detected by the algorithm can be visualized using an occlusion sensitivity map-based approach. For a longitudinal binary change detection task, our Siamese neural networks achieve test set receiving operator characteristic area under the curves (AUCs) of up to 0.90 in evaluating ROP or knee osteoarthritis change, depending on the change detection strategy. The overall performance on this binary task is similar compared to a conventional convolutional deep-neural network trained for multi-class classification. Our results demonstrate that convolutional Siamese neural networks can be a powerful tool for evaluating the continuous spectrum of disease severity and change in medical imaging.

BACKGROUND Lymphovascular invasion (LVI) is an established adverse prognostic factor in many cancers, however, there are few studies assessing its significance in papillary thyroid carcinoma (PTC). We aimed to determine if LVI is an independent prognostic factor in PTC. METHODS We conducted a single institution retrospective analysis of 610 patients with PTC treated between 1987 and 2016. LVI was defined as the presence or absence of cancer cells in blood vessels and/or lymphatics on histopathology. Multivariate Cox regression analysis was used to evaluate the association between LVI and recurrence-free survival (RFS). RESULTS The study cohort included 481 (78.9%) females and 129 (21.1%) males, with a median age of 47.6 years and median follow-up of 3.4 years. LVI was present in 56 (9.2%) patients and was associated with nodal metastases (P

Purpose: To describe a process for identifying birth weight (BW) and gestational age (GA) screening guidelines in Mongolia. Methods: This was a prospective cohort study in a tertiary care hospital in Ulaanbataar, Mongolia, of 193 premature infants with GA of 36 weeks or younger and/or BW of 2,000 g or less) with regression analysis to determine associations between BW and GA and the development of retinopathy of prematurity (ROP). Results: As BW and GA decreased, the relative risk of developing ROP increased. The relative risk of developing any stage of ROP in infants born at 29 weeks or younger was 2.91 (95% CI: 1.55 to 5.44; P < .001] compared to older infants. The relative risk of developing any type of ROP in infants with BW of less than 1,200 g was 2.41 (95% CI: 1.35 to 4.29; P = .003] and developing type 2 or worse ROP was 2.05 (95% CI: 0.99 to 4.25; P = .05). Conclusions: Infants in Mongolia with heavier BW and older GA who fall outside of current United States screening guidelines of GA of 30 weeks or younger and/or BW of 1,500 g or less developed clinically relevant ROP. [ J Pediatr Ophthalmol Strabismus . 2020;57(5):333–339.]

Purpose Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed by clinical ophthalmoscopic examinations or reading retinal images. Plus disease, defined as abnormal tortuosity and dilation of the posterior retinal blood vessels, is the most important feature to determine treatment-requiring ROP. We aimed to create a complete, publicly available and feature-extraction-based pipeline, I-ROP ASSIST, that achieves convolutional neural network (CNN)-like performance when diagnosing plus disease from retinal images. Methods We developed two datasets containing 100 and 5512 posterior retinal images, respectively. After segmenting retinal vessels, we detected the vessel centerlines. Then, we extracted features relevant to ROP, including tortuosity and dilation measures, and used these features in the classifiers including logistic regression, support vector machine and neural networks to assess a severity score for the input. We tested our system with fivefold cross-validation and calculated the area under the curve (AUC) metric for each classifier and dataset. Results For predicting plus versus not-plus categories, we achieved 99% and 94% AUC on the first and second datasets, respectively. For predicting pre-plus or worse versus normal categories, we achieved 99% and 88% AUC on the first and second datasets, respectively. The CNN method achieved 98% and 94% for predicting two categories on the second dataset. Conclusions Our system combining automatic retinal vessel segmentation, tracing, feature extraction and classification is able to diagnose plus disease in ROP with CNN-like performance. Translational Relevance The high performance of I-ROP ASSIST suggests potential applications in automated and objective diagnosis of plus disease.

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The diagnosis of ROP is subclassified by zone, stage, and plus disease, with each area demonstrating significant intra- and interexpert subjectivity and disagreement. In addition to improved efficiencies for ROP screening, artificial intelligence may lead to automated, quantifiable, and objective diagnosis in ROP. This review focuses on the development of artificial intelligence for automated diagnosis of plus disease in ROP and highlights the clinical and technical challenges of both the development and implementation of artificial intelligence in the real world.

Purpose Retinopathy of prematurity is a leading cause of childhood blindness worldwide, but clinical diagnosis is subjective, which leads to treatment differences. Our goal was to determine objective differences in the diagnosis of plus disease between clinicians using an automated retinopathy of prematurity (ROP) vascular severity score. Design This retrospective cohort study used data from the Imaging and Informatics in ROP Consortium, which comprises 8 tertiary care centers in North America. Fundus photographs of all infants undergoing ROP screening examinations between July 1, 2011, and December 31, 2016, were obtained. Participants Infants meeting ROP screening criteria who were diagnosed with plus disease and treatment initiated by an examining physician based on ophthalmoscopic examination results. Methods An ROP severity score (1–9) was generated for each image using a deep learning (DL) algorithm. Main Outcome Measures The mean, median, and range of ROP vascular severity scores overall and for each examiner when the diagnosis of plus disease was made. Results A total of 5255 clinical examinations in 871 babies were analyzed. Of these, 168 eyes were diagnosed with plus disease by 11 different examiners and were included in the study. The mean ± standard deviation vascular severity score for patients diagnosed with plus disease was 7.4 ± 1.9, median was 8.5 (interquartile range, 5.8–8.9), and range was 1.1 to 9.0. Within some examiners, variability in the level of vascular severity diagnosed as plus disease was present, and 1 examiner routinely diagnosed plus disease in patients with less severe disease than the other examiners (P Conclusions We observed variability both between and within examiners in the diagnosis of plus disease using DL. Prospective evaluation of clinical trial data using an objective measurement of vascular severity may help to define better the minimum necessary level of vascular severity for the diagnosis of plus disease or how other clinical features such as zone, stage, and extent of peripheral disease ought to be incorporated in treatment decisions.

ObjectivesTo test the hypothesis that a shopping centre Pop-Up health check combining an intraocular pressure (IOP) check with a general health check (blood pressure (BP)) is more readily accepted by the general public than an IOP check only. We investigate public awareness of IOP compared with BP and the feasibility of measuring IOP in large numbers in a Pop-Up.DesignA cross-sectional study using a tailor-made healthcare Pop-Up.SettingThe ‘Feeling the Pressure’ Pop-Up was sited in eight regionally-different shopping centres in England.ParticipantsAdult members of the public in shopping centres.MethodsOn one day we measured IOP only and on another measured BP and IOP. IOP was measured by Icare IC100 tonometer (Helsinki, Finland). Potential participants were asked about their awareness of IOP and BP and when they last visited their optometrist.ResultsMore people attended the combined BP + IOP days (461; 60%; 95% CI 56% to 64%) than IOP-only days (307; 40%, 95% CI 37% to 43%) over 16 days of testing. We recorded IOP in 652 participants (median (IQR) age and IOP of 54 (42 to 68) years and 13 (11 to 15) mm Hg, respectively). Fewer people reported awareness about IOP (19%, 95% CI 16% to 23%) compared with BP (71%, 95% CI 66% to 75%). Of 768 participants, 60 (8%) reported no previous optometric eye examination and 185 (24%) reported >2 years since their most recent examination.ConclusionsMeasuring IOP in large numbers of the public via a shopping centre Pop-Up is feasible. Public engagement was greater when a BP check was offered alongside an IOP check, suggesting unfamiliar health checks can be promoted by aligning them with a more familiar check. Our findings hint at strategies for public health schemes that engage the public with their eye health.

PURPOSE: To evaluate adverse events of fluorescein angiography (FA) in pediatric patients. DESIGN: Single-institution retrospective chart review. PARTICIPANTS: Patients 0 to 18 years of age who underwent FA between January 2010 and December 2015 at a single institution in the United States. METHODS: Pediatric patients who underwent FA by 3 surgeons were included in the study. Patients with fewer than 24 hours of documented follow-up were excluded. Significant adverse events within 24 hours of FA were evaluated. Detailed intraoperative and perioperative physiological parameters, including heart rate, blood pressure, oxygen saturation, and ventilation parameters, in inpatients undergoing simultaneous examination under anesthesia were reviewed. Peri-injection effects of FA were evaluated by 2-tailed paired t test comparison of mean 5-minute preinjection and 5-minute postinjection physiological data. MAIN OUTCOME MEASURES: Significant adverse events associated with FA. RESULTS: One hundred fifteen patients with a total of 214 FA examinations were included. No significant adverse events were associated directly with FA. Comparison of mean 5-minute preinjection and postinjection physiologic parameters in 27 patients who underwent intravenous FA during EUA did not reveal significant changes associated with FA. A significant difference was found in average patient age between inpatient (2.5 years) and outpatient (10.7 years) FA (P < 0.00001). The youngest patients who underwent successful FA were 3.8 years old in the outpatient setting and 32 weeks’ postmenstrual age in the inpatient setting. Patients younger than 3.8 years accounted for most (77.6%; n = 85) inpatient FA examinations. Excluding patients with a need or likely need for laser or surgery, the reasons for inpatient FA in patients older than 3.8 years included the lack of availability of outpatient ultra-widefield FA (UWFA) and more challenging situations in patients with developmental delay. CONCLUSIONS: Fluorescein angiography was not found to be associated directly with systemic adverse events in pediatric patients in this study. Younger patients more commonly were found to require an inpatient FA, whereas older patients older than 4 years underwent outpatient UWFA.

IMPORTANCE: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide, but treatment failure and disease recurrence are important causes of adverse outcomes in patients with treatment-requiring ROP (TR-ROP). OBJECTIVES: To apply an automated ROP vascular severity score obtained using a deep learning algorithm and to assess its utility for objectively monitoring ROP regression after treatment. DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study used data from the Imaging and Informatics in ROP consortium, which comprises 9 tertiary referral centers in North America that screen high volumes of at-risk infants for ROP. Images of 5255 clinical eye examinations from 871 infants performed between July 2011 and December 2016 were assessed for eligibility in the present study. The disease course was assessed with time across the numerous examinations for patients with TR-ROP. Infants born prematurely meeting screening criteria for ROP who developed TR-ROP and who had images captured within 4 weeks before and after treatment as well as at the time of treatment were included. MAIN OUTCOMES AND MEASURES: The primary outcome was mean (SD) ROP vascular severity score before, at time of, and after treatment. A deep learning classifier was used to assign a continuous ROP vascular severity score, which ranged from 1 (normal) to 9 (most severe), at each examination. A secondary outcome was the difference in ROP vascular severity score among eyes treated with laser or the vascular endothelial growth factor antagonist bevacizumab. Differences between groups for both outcomes were assessed using unpaired 2-tailed t tests with Bonferroni correction. RESULTS: Of 5255 examined eyes, 91 developed TR-ROP, of which 46 eyes met the inclusion criteria based on the available images. The mean (SD) birth weight of those patients was 653 (185) g, with a mean (SD) gestational age of 24.9 (1.3) weeks. The mean (SD) ROP vascular severity scores significantly increased 2 weeks prior to treatment (4.19 [1.75]), peaked at treatment (7.43 [1.89]), and decreased for at least 2 weeks after treatment (4.00 [1.88]) (all P

Purpose:To determine the accuracy and reliability of diagnosing aggressive posterior retinopathy of prematurity (AP-ROP).Methods:A total of 1220 eye examinations from 230 infants were prospectively obtained at 8 major ROP centers. An ophthalmologist at each center provided a clinical diagnosis using indirect ophthalmoscopy. Wide-angle retinal images were then obtained, which were independently read by 2 ROP experts using a web-based system for an image-based diagnosis. Sensitivity and specificity of image-based AP-ROP diagnosis by the ROP experts were calculated using the clinical diagnosis as the reference standard. Agreement of AP-ROP diagnosis through image-based diagnosis and clinical diagnosis was calculated using the unweighted κ statistic.Results:One hundred four (9%) of the 1220 examinations had a clinical diagnosis of AP-ROP. Sensitivity and specificity for the presence of AP-ROP were 35% and 96% for expert 1 and 17% and 99% for expert 2. Using the κ statistic, expert image-based versus clinical diagnostic agreement for the diagnosis of AP-ROP was 0.34 (fair) for expert 1 and 0.24 (fair) for expert 2. Agreement for the diagnosis of AP-ROP between the image-based diagnoses of expert 1 and expert 2 was 0.49 (moderate).Conclusion:There are inconsistencies between the clinical diagnosis of AP-ROP (as determined by indirect ophthalmoscopy) and the image-based diagnosis of AP-ROP. This may have important implications for ROP management and the current international ROP classification system.

Purpose To determine expert agreement on relative retinopathy of prematurity (ROP) disease severity and whether computer-based image analysis can model relative disease severity, and to propose consideration of a more continuous severity score for ROP. Design We developed 2 databases of clinical images of varying disease severity (100 images and 34 images) as part of the Imaging and Informatics in ROP (i-ROP) cohort study and recruited expert physician, nonexpert physician, and nonphysician graders to classify and perform pairwise comparisons on both databases. Participants Six participating expert ROP clinician-scientists, each with a minimum of 10 years of clinical ROP experience and 5 ROP publications, and 5 image graders (3 physicians and 2 nonphysician graders) who analyzed images that were obtained during routine ROP screening in neonatal intensive care units. Methods Images in both databases were ranked by average disease classification (classification ranking), by pairwise comparison using the Elo rating method (comparison ranking), and by correlation with the i-ROP computer-based image analysis system. Main Outcome Measures Interexpert agreement (weighted κ statistic) compared with the correlation coefficient (CC) between experts on pairwise comparisons and correlation between expert rankings and computer-based image analysis modeling. Results There was variable interexpert agreement on diagnostic classification of disease (plus, preplus, or normal) among the 6 experts (mean weighted κ, 0.27; range, 0.06–0.63), but good correlation between experts on comparison ranking of disease severity (mean CC, 0.84; range, 0.74–0.93) on the set of 34 images. Comparison ranking provided a severity ranking that was in good agreement with ranking obtained by classification ranking (CC, 0.92). Comparison ranking on the larger dataset by both expert and nonexpert graders demonstrated good correlation (mean CC, 0.97; range, 0.95–0.98). The i-ROP system was able to model this continuous severity with good correlation (CC, 0.86). Conclusions Experts diagnose plus disease on a continuum, with poor absolute agreement on classification but good relative agreement on disease severity. These results suggest that the use of pairwise rankings and a continuous severity score, such as that provided by the i-ROP system, may improve agreement on disease severity in the future.

Purpose To identify the most common areas for discrepancy in retinopathy of prematurity (ROP) classification between experts. Design Prospective cohort study. Participants A total of 281 infants were identified as part of a multicenter, prospective, ROP cohort study from 7 participating centers. Each site had participating ophthalmologists who provided the clinical classification after routine examination using binocular indirect ophthalmoscopy (BIO) and obtained wide-angle retinal images, which were independently classified by 2 study experts. Methods Wide-angle retinal images (RetCam; Clarity Medical Systems, Pleasanton, CA) were obtained from study subjects, and 2 experts evaluated each image using a secure web-based module. Image-based classifications for zone, stage, plus disease, and overall disease category (no ROP, mild ROP, type II or pre-plus, and type I) were compared between the 2 experts and with the clinical classification obtained by BIO. Main Outcome Measures Inter-expert image-based agreement and image-based versus ophthalmoscopic diagnostic agreement using absolute agreement and weighted kappa statistic. Results A total of 1553 study eye examinations from 281 infants were included in the study. Experts disagreed on the stage classification in 620 of 1553 comparisons (40%), plus disease classification (including pre-plus) in 287 of 1553 comparisons (18%), zone in 117 of 1553 comparisons (8%), and overall ROP category in 618 of 1553 comparisons (40%). However, agreement for presence versus absence of type 1 disease was >95%. There were no differences between image-based and clinical classification except for zone III disease. Conclusions The most common area of discrepancy in ROP classification is stage, although inter-expert agreement for clinically significant disease, such as presence versus absence of type 1 and type 2 disease, is high. There were no differences between image-based grading and clinical examination in the ability to detect clinically significant disease. This study provides additional evidence that image-based classification of ROP reliably detects clinically significant levels of ROP with high accuracy compared with the clinical examination.

BACKGROUND AND OBJECTIVES In papillary thyroid cancer (PTC), the adverse prognostic impact of extrathyroidal extension (macro-ETE) invading the subcutaneous soft tissues, larynx, trachea, esophagus, or recurrent laryngeal nerve (T4a disease) is well established. We investigated whether the extent of macro-ETE, defined as "limited" with single structure involvement (lim-ETE) and "extensive" with multiple structures involved (ext-ETE), influences prognosis in T4a PTC. METHODS A retrospective analysis of 610 patients with PTC identified 39 with T4a disease, including 26 with lim-ETE and 13 with ext-ETE. Univariate Cox regression was used to assess the relationship between the extent of macro-ETE and recurrence-free survival (RFS). RESULTS Ext-ETE was associated with a five times increased risk of recurrence compared to lim-ETE (HR 5.0, P

Purpose: Retinopathy of prematurity (ROP) is widely regarded worldwide as a major cause of childhood blindness, however until recently the disease has not been recognized in most of the African continent. As a result of changing economic conditions, there is growing evidence that the population at risk for ROP in Africa is increasing. This report aims to summarize the published literature on ROP from Africa. Methods: We performed a systematic literature review of the English and French online literature databases by applying a general search strategy initially on May 1, 2017 with repeat inquiry on May 20, 2018. Search phrases included multiple variants of terms including "ROP", "retinopathy of prematurity", in conjunction with each of the individual 54 recognized sovereign African states. Findings: A total of 25 individual studies from six African nations were identified: South Africa (10), Egypt (7), Nigeria (4), with the nations of Sudan, Rwanda, and Kenya each having one respective study. Two countries (South Africa and Kenya) have developed national ROP policies for primary and secondary prevention. Summary: Review of the published literature suggests that ROP is emerging in Africa, however, there are published data from 6/54 (11%) African nations. Blindness from ROP is often preventable with appropriate primary and secondary prevention. This report provides compelling evidence that these efforts should be undertaken to implement and evaluate regionally appropriate ROP prevention programs in a growing number of African countries.

For three species of Aloe L. (Asphodelaceae subfam. Alooideae), A. canis S.Lane, A. suffulta Reynolds, and A. lateritia Engl., which are rare in Malawi, detailed habitat information is given to facilitate their recollection in that country. Aloe canis, a Malawian endemic, was observed at three localities in the 1970s by T.P. Campbell-Barker and published as new by S. Lane in 1991; it now may be extinct in the wild in Malawi but, as far as we could ascertain, has persisted ex situ as a single plant in cultivation. Aloe suffulta from Mozambique, Zimbabwe, and South Africa was collected in Malawi only once in the 1970s by T.P. Campbell-Barker, and A. lateritia from Kenya and Tanzania only twice during 1967–68 by B.J. Hargreaves, and in 1991 by P. Downs (†). These collections of A. suffulta and A. lateritia were not supported by preserved specimens.

Supervised deep learning approaches provide state-of-the-art performance on medical image classification tasks for disease screening. However, these methods require large labeled datasets that involve resource-intensive expert annotation. Further, disease screening applications have low prevalence of abnormal samples; this class imbalance makes the task more akin to anomaly detection. While the machine learning community has proposed unsupervised deep learning methods for anomaly detection, they have yet to be characterized on medical images where normal vs. anomaly distinctions may be more subtle and variable. In this work, we characterize existing unsupervised anomaly detection methods on retinal fundus images, and find that they require significant fine tuning and offer unsatisfactory performance. We thus propose an efficient and effective transfer-learning based approach for unsupervised anomaly detection. Our method employs a deep convolutional neural network trained on ImageNet as a feature extractor, and subsequently feeds the learned feature representations into an existing unsupervised anomaly detection method. We show that our approach significantly outperforms baselines on two natural image datasets and two retinal fundus image datasets, all with minimal fine-tuning. We further show the ability to leverage very small numbers of labelled anomalies to improve performance. Our work establishes a strong unsupervised baseline for image-based anomaly detection, alongside a flexible and scalable approach for screening applications.

BACKGROUND AND OBJECTIVE: To report on the microbiology, management, and visual outcomes of intravitreal injection (IVI)-associated, culture-proven endophthalmitis. PATIENTS AND METHODS: All patients seen at a tertiary referral center with culture-proven endophthalmitis associated with an IVI between June 2007 and July 2017 were included in this retrospective analysis. RESULTS: Thirty-five patients with culture-positive endophthalmitis following IVI were identified. All gram-positive organisms (34 of 35) were susceptible to vancomycin. Cases due to pathogens associated with oral or respiratory flora were common (31.4%, n = 11), presented earlier (2.0 days vs. 4.6 days, P < .001), were more likely to undergo pars plana vitrectomy (81.8% vs. 25.0%, P = .002) and had worse visual acuity outcomes. CONCLUSION: IVI-associated endophthalmitis pathogens and anti-microbial susceptibilities in the Pacific Northwest are similar to those reported from other geographic locations. Bacteria associated with the oral and respiratory flora are common isolates that result in a more aggressive course and worse visual outcomes. [ Ophthalmic Surg Lasers Imaging Retina . 2019;50:33–38.]

BackgroundPrior 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.MethodsClinical 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.Results4861 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; pConclusionThe 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.

Labels generated by human experts via comparisons exhibit smaller variance compared to traditional sample labels. Collecting comparison labels is challenging over large datasets, as the number of comparisons grows quadratically with the dataset size. We study the following experimental design problem: given a budget of expert comparisons, and a set of existing sample labels, we determine the comparison labels to collect that lead to the highest classification improvement. We study several experimental design objectives motivated by the Bradley-Terry model. The resulting optimization problems amount to maximizing submodular functions. We experimentally evaluate the performance of these methods over synthetic and real-life datasets.

Background Improving detection of elevated blood pressure (BP) remains a public health need. We present results from a Pop-Up health check stationed in shopping centres in England. We hypothesise the rate of case detection is related to measurable ‘unhealthiness’ of the shopping centres. Methods A Pop-Up health check was sited in four and three shopping centres sampled from the top ten unhealthiest and top 15 healthiest shopping regions respectively, following a report ranking towns/cities based on their unhealthy and healthy retail outlets. On one day in each shopping centre, people were approached and consented to BP testing. Outcome measure was people flagged with BP ≥ 140/90 mmHg (cases). Results We detected 45 (22.6%) and 20 (13.1%) cases from testing 199 and 152 adults in the unhealthy and healthy locations respectively (relative risk 1.72; 95% confidence interval: 1.06 to 2.78). A measure of unhealthy retail outlets (e.g. fast-food outlets) within each shopping centre was associated with detection rate (R2 = 0.61; p = 0.04). Conclusion An association exists between cases of suspect hypertension found in a health check Pop-Up and measured ‘unhealthiness’ of the shopping centre site. Results hint at strategies for public testing of BP, potentially in the context of reducing health inequalities. Electronic supplementary material The online version of this article (10.1186/s12889-018-6370-0) contains supplementary material, which is available to authorized users.

Retinopathy of prematurity (ROP) is a disease that affects premature infants, where abnormal growth of the retinal blood vessels can lead to blindness unless treated accordingly. Infants considered at risk of severe ROP are monitored for symptoms of plus disease, characterized by arterial tortuosity and venous dilation at the posterior pole, with a standard photographic definition. Disagreement among ROP experts in diagnosing plus disease has driven the development of computer-based methods that classify images based on hand-crafted features extracted from the vasculature. However, most of these approaches are semi-automated, which are time-consuming and subject to variability. In contrast, deep learning is a fully automated approach that has shown great promise in a wide variety of domains, including medical genetics, informatics and imaging. Convolutional neural networks (CNNs) are deep networks which learn rich representations of disease features that are highly robust to variations in acquisition and image quality. In this study, we utilized a U-Net architecture to perform vessel segmentation and then a GoogLeNet to perform disease classification. The classifier was trained on 3,000 retinal images and validated on an independent test set of patients with different observed progressions and treatments. We show that our fully automated algorithm can be used to monitor the progression of plus disease over multiple patient visits with results that are consistent with the experts’ consensus diagnosis. Future work will aim to further validate the method on larger cohorts of patients to assess its applicability within the clinic as a treatment monitoring tool.

PURPOSE OF REVIEW: An update and overview of the literature on current telemedicine applications in retina. RECENT FINDINGS: The application of telemedicine to the field of Ophthalmology and Retina has been growing with advancing technologies in ophthalmic imaging. Retinal telemedicine has been most commonly applied to diabetic retinopathy and retinopathy of prematurity in adult and pediatric patients respectively. Telemedicine has the potential to alleviate the growing demand for clinical evaluation of retinal diseases. Subsequently, automated image analysis and deep learning systems may facilitate efficient processing of large, increasing numbers of images generated in telemedicine systems. Telemedicine may additionally improve access to education and standardized training through tele-education systems. SUMMARY: Telemedicine has the potential to be utilized as a useful adjunct but not a complete replacement for physical clinical examinations. Retinal telemedicine programs should be carefully and appropriately integrated into current clinical systems.

Retinopathy of prematurity (ROP) is a retinal vasoproliferative disease that affects premature infants. Despite improvements in neonatal care and management guidelines, ROP remains a leading cause of childhood blindness worldwide. Current screening guidelines are primarily based on two risk factors: birth weight and gestational age; however, many investigators have suggested other risk factors, including maternal factors, prenatal and perinatal factors, demographics, medical interventions, comorbidities of prematurity, nutrition, and genetic factors. We review the existing literature addressing various possible ROP risk factors. Although there have been contradictory reports, and the risk may vary between different populations, understanding ROP risk factors is essential to develop predictive models, to gain insights into pathophysiology of retinal vascular diseases and diseases of prematurity, and to determine future directions in management of and research in ROP.

Pediatric ophthalmologists were surveyed to determine current practice patterns regarding ophthalmic imaging for children and to identify perceived barriers to the adoption of imaging technologies in their practices. Some form of imaging was available in the majority of practices (94%), but its use varied widely among different clinical scenarios. The two most frequently perceived barriers to performing imaging in children were cooperation and lack of sufficient data supporting ophthalmic imaging in clinical practice.

Importance Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. Optical coherence tomography (OCT) has improved the care of adults with vitreoretinal disease, and OCT angiography (OCTA) is demonstrating promise as a technique to visualize the retinal vasculature with lower risk and cost than fluorescein angiography. However, to date, there are no commercially available devices able to obtain ultra–wide-field OCT or OCTA images in neonates. Objective To obtain ultra–wide-field OCT and OCTA images in neonates with ROP using a prototype handheld OCT and OCTA device. Design, Setting, and Participants This observational case series was conducted from March 1 to April 1, 2017, in an academic medical center among 4 neonates with ROP in the neonatal intensive care unit and in the operating room. Main Outcomes and Measures Acquisition of wide-field OCT and OCTA images using a handheld prototype OCTA and ultra–wide-field OCT device. Results Images were obtained from 4 neonates (1 girl and 3 boys; mean age, 38 weeks’ postmenstrual age [range, 34-43 weeks]) with various stages of ROP: 3 in the neonatal intensive care unit and 1 in the operating room. The system can obtain noncontact en face OCT images and horizontal line scans with an approximately 40° field of view and up to 100° (ultra–wide-field) using a contact lens–based approach in a single 2-second scan. In addition, 20° × 20° (approximately 4 × 4-mm) OCTA scans were obtained in patients with ROP in a single 2-second scan. Conclusions and Relevance Optical coherence tomography and OCTA are gaining popularity in pediatric retinal imaging. This study reports on OCTA and ultra–wide-field OCT images in 4 neonates with various stages of ROP that were obtained using a prototype handheld device. Additional studies will be needed to prove the clinical value of this technology.