Comparison of strategies for grading retinal images of premature infants for referral warranted retinopathy of prematurity.
Ontology highlight
ABSTRACT:
SUBMITTER: Rogers DL
PROVIDER: S-EPMC5502683 | biostudies-literature | 2017 Apr
REPOSITORIES: biostudies-literature
Publications
Comparison of strategies for grading retinal images of premature infants for referral warranted retinopathy of prematurity.
Rogers David L DL Bremer Don L DL Fellows Rae R RR Baumritter Agnieshka A Daniel Ebenezer E Pastilli Max M Ying Gui-Shang GS Quinn Graham E GE
Journal of AAPOS : the official publication of the American Association for Pediatric Ophthalmology and Strabismus 20170320 2
<h4>Purpose</h4>To determine the accuracy of identifying referral-warranted retinopathy of prematurity (RW-ROP, defined as any zone I ROP, stage 3 or worse, or plus disease) from retinal image sets using three grading protocols: a single optic disk-centered image, a set of 3 horizontal images, and a 5-image set.<h4>Methods</h4>In this secondary analysis of images from the e-ROP study, a weighted sample of 250 image sets from 250 infants (125 with RW-ROP and 125 without RW-ROP) was randomly selec ...[more]
Similar Datasets
Project description:IMPORTANCE:Detection of treatment-requiring retinopathy of prematurity (ROP) involves serial eye examinations. An ROP prediction model using predictive factors could identify high-risk infants and reduce required eye examinations. OBJECTIVE:To determine predictive factors for the development of referral-warranted (RW) ROP. DESIGN, SETTING, AND PARTICIPANTS:This multicenter observational cohort study included secondary analysis of data from the Telemedicine Approaches to Evaluating Acute-Phase Retinopathy of Prematurity Study. Infants included in the study had a birth weight (BW) of less than 1251 g. EXPOSURES:Serial ROP examinations of premature infants who had 2 or more ROP examinations. MAIN OUTCOMES AND MEASURES:Incidence of RW-ROP (defined as the presence of plus disease, zone I ROP, or ROP stage 3 or greater in either eye) and associations with predictive factors. RESULTS:Among 979 infants without RW-ROP at first study-related eye examination (median postmenstrual age, 33 weeks; range, 29-40 weeks) who underwent at least 2 eye examinations, 149 (15.2%) developed RW-ROP. In a multivariate model, significant predictors for RW-ROP were male sex (odds ratio [OR], 1.80; 95% CI, 1.13-2.86 vs female), nonblack race (OR, 2.76; 95% CI, 1.50-5.08 for white vs black race and OR, 4.81; 95% CI, 2.19-10.6 for other vs black race), low BW (OR, 5.16; 95% CI, 1.12-7.20 for ?500 g vs >1100 g), younger gestational age (OR, 9.79; 95% CI, 3.49-27.5 for ?24 weeks vs ?28 weeks), number of quadrants with preplus disease (OR, 7.12; 95% CI, 2.53-20.1 for 1-2 quadrants and OR, 18.4; 95% CI, 4.28-79.4 for 3-4 quadrants vs no preplus disease), stage 2 ROP (OR, 4.13; 95% CI, 2.13-8.00 vs no ROP), the presence of retinal hemorrhage (OR, 4.36; 95% CI, 1.57-12.1 vs absence), the need for respiratory support (OR, 4.99; 95% CI, 1.89-13.2 for the need for controlled mechanical ventilator; OR, 11.0; 95% CI, 2.26-53.8 for the need for high-frequency oscillatory ventilation vs no respiratory support), and slow weight gain (OR, 2.44; 95% CI, 1.22-4.89 for weight gain ?12 g/d vs >18 g/d). These characteristics predicted the development of RW-ROP significantly better than BW and gestational age (area under receiver operating characteristic curve, 0.88 vs 0.78; P?<?.001). CONCLUSIONS AND RELEVANCE:When controlling for very low BW and prematurity, the presence of preplus disease, stage 2 ROP, retinal hemorrhage, and the need for ventilation at time of first study-related eye examination were strong independent predictors for RW-ROP. These predictors may help identify infants in need of timely eye examinations.
| S-EPMC4416963 | biostudies-literature
Project description:ObjectivesTo describe adverse events (AEs) and noteworthy clinical or ocular findings associated with retinopathy of prematurity (ROP) evaluation procedures.Study designDescriptive analysis of predefined AEs and noteworthy findings reported in a prospective observational cohort study of infants <1251 g birth weight who had ROP study visits consisting of both binocular indirect ophthalmoscopy (BIO) and digital retinal imaging. We compared infant characteristics during ROP visits with and without AEs. We compared respiratory support, nutrition, and number of apnea, bradycardia, or hypoxia events 12 hours before and after ROP visits.ResultsA total of 1257 infants, mean birth weight 802 g, had 4263 BIO and 4048 imaging sessions (total 8311 procedures). No serious AEs were related to ROP visits. Sixty-five AEs were reported among 61 infants for an AE rate of 4.9% infants (61/1257) or 0.8% total procedures (65/8311 BIO + imaging). Most AEs were due to apnea, bradycardia, and/or hypoxia (68%), tachycardia (16%), or emesis (8%). At ROP visit, infants with AEs, compared with those without, were more likely to be on mechanical ventilation (26% vs 12%, P = .04) even after adjustment for weight and postmenstrual age. Noteworthy clinical findings were reported during 8% BIO and 15% imaging examinations. Respiratory and nutrition support were not significantly different before and after ROP evaluations.ConclusionsRetinal imaging by nonphysicians combined with BIO was safe. Noteworthy clinical findings occurred during both procedures. Ventilator support was a risk factor for AEs. Monitoring rates of AEs and noteworthy findings are important to the safe implementation of ROP imaging protocols.Trial registrationClinicaltrials.gov: NCT01264276.
| S-EPMC4661087 | biostudies-literature
Project description:ImportanceMost premature infants will not develop retinopathy of prematurity (ROP) of clinical relevance, yet screening evaluations often continue beyond hospital discharge, even for those infants without ROP.ObjectivesTo identify the characteristics of infants at low risk for ROP, for whom further postdischarge screening may be of limited value.Design, setting, and participantsThis study took place in North American neonatal intensive care units where clinicians had expertise in ROP. Infants with birth weight less than 1251 g who were born at or transferred into an Telemedicine Approaches to Evaluating Acute-Phase ROP (e-ROP) study center were enrolled. The study included post hoc analysis of prospectively collected in-hospital ROP examination results among infants enrolled in the e-ROP study. We characterized infants without ROP and performed logistic regression on the subset of infants who were 27 to 33 weeks' gestational age to determine characteristics associated with the absence of ROP during all in-hospital examinations.Main outcomes and measuresThe main measure was the absence of ROP prior to hospital discharge; the main outcome was treatment for ROP.ResultsA total of 1257 infants born at 22 to 35 weeks' gestation (median [interquartile range (IQR)], 26 [25-28] weeks) with birth weights less than 1251 g (median [IQR], 860 [690-1040] g) underwent 4113 ROP examinations between 31 and 47 weeks' postmenstrual age. Overall, 1153 examinations (38%) showed no ROP, and 456 infants (36%) did not have ROP prior to study center discharge or study end point. Among infants without ROP during examinations at 32 and 33 weeks' postmenstrual age, 16 (9.4%) and 14 (5.3%) subsequently underwent ROP treatment, respectively. At hospital discharge, there was no ROP in 59% of infants of 27 to 33 weeks' gestational age, compared with 15% of those who were less than 27 weeks' gestational age (difference, 44% [95% CI, 38.5%-48.1%]; P ≤ .001). With more than 85% follow-up among infants without ROP by 37 weeks' postmenstrual age, none (95% CI, 0%-0.98%) were treated for ROP. In multivariate analysis of infants born at 27 to 33 weeks' gestation, larger birth weight (OR, 4.1 [95% CI, 1.6-10.3]) and higher gestational age (OR, 4.0 [95% CI, 1.5-10.8]) were significantly associated with absence of ROP.Conclusions and relevanceThese findings suggest that, for infants of 27 weeks' gestational age or greater and birth weights larger than 750 g, if no ROP has been detected by discharge at near-term postmenstrual age, then further ROP surveillance has limited value. Studies of all infants at risk are needed to develop more specific, objective criteria for termination of ROP surveillance and focus resources on infants at higher risk of ROP.Trial registrationClinicalTrials.gov Identifier: NCT01264276.
| S-EPMC6439829 | biostudies-literature
Project description:ImportanceA retinopathy of prematurity (ROP) diagnosis currently relies on indirect ophthalmoscopy assessed by experienced ophthalmologists. A deep learning algorithm based on retinal images may facilitate early detection and timely treatment of ROP to improve visual outcomes.ObjectiveTo develop a retinal image-based, multidimensional, automated, deep learning platform for ROP screening and validate its performance accuracy.Design, setting, and participantsA total of 14 108 eyes of 8652 preterm infants who received ROP screening from 4 centers from November 4, 2010, to November 14, 2019, were included, and a total of 52 249 retinal images were randomly split into training, validation, and test sets. Four main dimensional independent classifiers were developed, including image quality, any stage of ROP, intraocular hemorrhage, and preplus/plus disease. Referral-warranted ROP was automatically generated by integrating the results of 4 classifiers at the image, eye, and patient levels. DeepSHAP, a method based on DeepLIFT and Shapley values (solution concepts in cooperative game theory), was adopted as the heat map technology to explain the predictions. The performance of the platform was further validated as compared with that of the experienced ROP experts. Data were analyzed from February 12, 2020, to June 24, 2020.ExposureA deep learning algorithm.Main outcomes and measuresThe performance of each classifier included true negative, false positive, false negative, true positive, F1 score, sensitivity, specificity, receiver operating characteristic, area under curve (AUC), and Cohen unweighted κ.ResultsA total of 14 108 eyes of 8652 preterm infants (mean [SD] gestational age, 32.9 [3.1] weeks; 4818 boys [60.4%] of 7973 with known sex) received ROP screening. The performance of all classifiers achieved an F1 score of 0.718 to 0.981, a sensitivity of 0.918 to 0.982, a specificity of 0.949 to 0.992, and an AUC of 0.983 to 0.998, whereas that of the referral system achieved an F1 score of 0.898 to 0.956, a sensitivity of 0.981 to 0.986, a specificity of 0.939 to 0.974, and an AUC of 0.9901 to 0.9956. Fine-grained and class-discriminative heat maps were generated by DeepSHAP in real time. The platform achieved a Cohen unweighted κ of 0.86 to 0.98 compared with a Cohen κ of 0.93 to 0.98 by the ROP experts.Conclusions and relevanceIn this diagnostic study, an automated ROP screening platform was able to identify and classify multidimensional pathologic lesions in the retinal images. This platform may be able to assist routine ROP screening in general and children hospitals.
| S-EPMC8100867 | biostudies-literature
Project description:PurposeTo measure accuracy and speed for detection of vascular progression in retinopathy of prematurity (ROP) from serial images. Two strategies are compared: static side-by-side presentation and dynamic flickering of superimposed image pairs.DesignProspective comparative study.MethodsFifteen de-identified, wide-angle retinal image pairs were taken from infants who eventually developed plus disease. Image pairs representing vascular disease progression were taken ?1 week apart, and control images without progression were taken on the same day. Dynamic flickering pairs were created by digital image registration. Ten experts independently reviewed each image pair on a secure website using both strategies, and were asked to identify progression or state that images were identical. Accuracy and speed were measured, using examination date and ophthalmoscopic findings as a reference standard.ResultsUsing static images, experts were accurate in a mean (%) ± standard deviation (SD) of 11.4 of 15 (76%) ± 1.7 image pairs. Using dynamic flickering images, experts were accurate in a mean (%) ± SD of 11.3 of 15 (75%) ± 1.7 image pairs. There was no significant difference in accuracy between these strategies (P = .420). Diagnostic speed was faster using dynamic flickering (24.7 ± 8.3 seconds) vs static side-by-side images (40.3 ± 18.3 seconds) (P = .002). Experts reported higher confidence when interpreting dynamic flickering images (P = .001).ConclusionsRetinal imaging provides objective documentation of vascular appearance, with potentially improved ability to recognize ROP progression compared to standard ophthalmoscopy. Speed of identifying vascular progression was faster by review of dynamic flickering image pairs than by static side-by-side images, although there was no difference in accuracy.
| S-EPMC3266465 | biostudies-literature
Project description:PURPOSE:Bedside examination of premature infants at risk for retinopathy of prematurity (ROP) is predominantly performed with ophthalmoscopic en face viewing of the retina. While postmortem retinal microstructures have been studied at the vascular-avascular junction, a critical location for pathogenesis of ROP, to date this has not been possible in vivo. Here we present bedside, non-sedated in vivo cross-sectional imaging and analysis of retinal microstructures at the vascular-avascular junction in infants with ROP using handheld spectral-domain optical coherence tomography (SDOCT). DESIGN:Prospective observational study. PARTICIPANTS:Eleven preterm infants consented for research imaging during ROP screening examinations. METHODS:We imaged the vascular-avascular junction in the temporal retina using a SDOCT system (Envisu, Bioptigen Inc., NC) in 18 eyes from 11 preterm infants with zone I or II, stage 0 through 4 ROP. B-scan and en face images were analyzed and compared to historical light micrographs. MAIN OUTCOME MEASURES:SDOCT morphology at the vascular-avascular junction. RESULTS:Multiple bedside SDOCT findings at the vascular-avascular junction were comparable to historic light micrographs: thickened inner retinal ridge structure in stage 2 ROP was comparable to thickened vanguard and rear guard cells in micrographs; vascular tufts on the posterior retinal surface in stage 2 ROP, broad arcs of neovascularization above the retina in stage 3 ROP, and splitting of inner retinal layers into clefts on either side of neovascularization mimicked findings of historic light micrographs. A unique findings was thickening of the avascular inner retinal band adjacent to neovascularization. On SDOCT imaging over several weeks, neovascularization and retinal clefts diminished after intravitreal bevacizumab therapy. CONCLUSIONS:Retinal morphology at the vascular-avascular junction imaged with handheld SDOCT is consistent with known histopathology, and provide the advantage of monitoring change in vivo over time. These unique findings provide new insights into preterm retinal neurovascular development in ROP.
| S-EPMC6261282 | biostudies-literature
Project description:ImportanceTelemedicine in retinopathy of prematurity (ROP) has the potential for delivering timely care to premature infants at risk for serious ROP.ObjectiveTo describe the characteristics of eyes at risk for ROP to provide insights into what types of ROP are most easily detected early by image grading.Design, setting, and participantsSecondary analysis of eyes with referral-warranted (RW) ROP (stage 3 ROP, zone I ROP, plus disease) on diagnostic examination from the Telemedicine Approaches to Evaluating Acute-Phase Retinopathy of Prematurity (e-ROP) study was conducted from May 1, 2011, to October 31, 2013, in 1257 premature infants with birth weights less than 1251 g in 13 neonatal units in North America. Data analysis was performed between February 1, 2016, and June 5, 2017.InterventionsSerial imaging sessions with concurrent diagnostic examinations for ROP.Main outcomes and measuresTime of detecting RW-ROP on image evaluation compared with clinical examination.ResultsIn the e-ROP study, 246 infants (492 eyes) were included in the analysis; 138 (56.1%) were male. A total of 447 eyes had RW-ROP on diagnostic examination. Image grading in 123 infants (mean [SD] gestational age, 24.8 [1.4] weeks) detected RW-ROP earlier than diagnostic examination (early) in 191 (42.7%) eyes by about 15 days and detected RW-ROP in 123 infants (mean [SD] gestational age, 24.6 [1.5] weeks) at the same time (same) in 200 (44.7%) eyes. Most of the early eyes (153 [80.1%]) interpreted as being RW-ROP positive on imaging evaluation agreed with examination findings when the examination subsequently documented RW-ROP. At the sessions in which RW-ROP was first found by examination, stage 3 or more in 123 infants (mean [SD] gestational age, 24.8 [1.4] weeks) ROP was noted earlier on image evaluation in 151 of 191 early eyes (79.1%) and in 172 of 200 of same eyes (86.0%) (P = .08); the presence of zone I ROP was detected in 57 of 191 (29.8%) early eyes vs 64 of 200 (32.0%) same eyes (P = .90); and plus disease was noted in 30 of 191 (15.7%) early eyes and 45 of 200 (22.5%) same eyes (P = .08).Conclusions and relevanceIn both early and same eyes, zone I and/or stage 3 ROP determined a significant proportion of RW-ROP; plus disease played a relatively minor role. In most early RW-ROP eyes, the findings were consistent with clinical examination and/or image grading at the next session. Because ROP telemedicine is used more widely, development of standard approaches and protocols is essential.
| S-EPMC6005697 | biostudies-literature
Project description:ImportanceMeasurable competence derived from comprehensive and advanced training in grading digital images is critical in studies using a reading center to evaluate retinal fundus images from infants at risk for retinopathy of prematurity (ROP). Details of certification for nonphysician trained readers (TRs) have not yet been described.ObjectiveTo describe a centralized system for grading ROP digital images by TRs in the Telemedicine Approaches to Evaluating Acute-Phase Retinopathy of Prematurity (e-ROP) Study.Design, setting, and participantsMulticenter observational cohort study conducted from July 1, 2010, to June 30, 2014. The TRs were trained by experienced ROP specialists and certified to detect ROP morphology in digital retinal images under supervision of an ophthalmologist reading center director. An ROP reading center was developed with standard hardware, secure Internet access, and customized image viewing software with an electronic grading form. A detailed protocol for grading was developed. Based on results of TR gradings, a computerized algorithm determined whether referral-warranted ROP (RW-ROP; defined as presence of plus disease, zone I ROP, and stage 3 or worse ROP) was present in digital images from infants with birth weight less than 1251 g enrolled from May 25, 2011, through October 31, 2013. Independent double grading was done by the TRs with adjudication of discrepant fields performed by the reading center director.ExposureDigital retinal images.Main outcomes and measuresIntragrader and intergrader variability and monitoring for temporal drift.ResultsFour TRs underwent rigorous training and certification. A total of 5520 image sets were double graded, with 24.5% requiring adjudication for at least 1 component of RW-ROP. For individual RW-ROP components, the adjudication rate was 3.9% for plus disease, 12.4% for zone I ROP, and 16.9% for stage 3 or worse ROP. The weighted κ for intergrader agreement (n = 80 image sets) was 0.72 (95% CI, 0.52-0.93) for RW-ROP, 0.57 (95% CI, 0.37-0.77) for plus disease, 0.43 (95% CI, 0.24-0.63) for zone I ROP, and 0.67 (95% CI, 0.47-0.88) for stage 3 or worse ROP. The weighted κ for grade-regrade agreement was 0.77 (95% CI, 0.57-0.97) for RW-ROP, 0.87 (95% CI, 0.67-1.00) for plus disease, 0.70 (95% CI, 0.51-0.90) for zone I ROP, and 0.77 (95% CI, 0.57-0.97) for stage 3 or worse ROP.Conclusions and relevanceThese data suggest that the e-ROP system for training and certifying nonphysicians to grade ROP images under the supervision of a reading center director reliably detects potentially serious ROP with good intragrader and intergrader consistency and minimal temporal drift.
| S-EPMC4910817 | biostudies-literature
Project description:To report the training/certification process of nonphysician imagers, image quality, and factors that affected image quality in the National Eye Institute sponsored multicentered e-ROP study.Nonphysician imagers underwent rigorous training and certification in obtaining retinal images, with attention to clarity, focus, and optic disk placement. Image readers measured pupil size in pupil image and graded posterior pole, temporal, nasal, superior, and inferior retinal images and classified them as good, adequate, poor, or missing. Good and adequate images were deemed acceptable.In 4,003 image sessions of 1,257 infants, 3,453 (86.8%) were complete. Of 39,550 retinal images, 91.7% had acceptable quality, 5.6% poor, and 2.7% were missing. Inadequate pupil dilation negatively affected acceptable image quality: 54% acceptable images for pupil <5 mm versus 93% for >6 mm (P < 0.0001). When ventilatory equipment obstructed access to imaged infant, the percent of acceptable image quality decreased: 94% for no support versus 66.6% for oscillatory ventilation (P < 0.0001). Acceptable image quality rates improved from 87% to 90% (P = 0.03) from first 6 months to last 6 months at low patient volume centers, while high patient volume centers remained stable at 95%.Nonphysicians successfully obtained acceptable quality images for ROP evaluation. Skills improved with experience. Image quality was negatively affected by inadequate pupil dilation and the presence of obstructive ventilatory equipment.
| S-EPMC4936410 | biostudies-other
Project description:ImportanceLiterature and anecdotal evidence suggest a relationship between male sex and retinopathy of prematurity (ROP). It is not known whether a difference, if present, is sex-related pathophysiologic predisposition or sex difference in meeting ROP screening criteria.ObjectiveTo evaluate the association of sex with the development of treatment-warranted ROP.Data sourcesPubMed, Embase, and Web of Science databases were searched from 2000 to 2022. The search strategy used keywords including retinopathy of prematurity or ROP or retrolental fibroplasia and treatment or anti-VEGF or bevacizumab or ranibizumab or aflibercept or conbercept or laser or cryotherapy and gender or sex or male or female and medical subject headings terms.Study selectionAll studies reporting on treatment with anti-vascular endothelial growth factor, laser photocoagulation, and/or cryotherapy for ROP were identified. Studies reporting sex distribution in the treatment group were included in the meta-analysis. Exclusion criteria included case reports, case series of fewer than 10 treated patients, systematic reviews, conference abstracts, letters to the editor, animal studies, and non-English records.Data extraction and synthesisTwo reviewers independently screened and extracted the data following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The proportions of treated male and female infants were combined using random-effects meta-analysis.Main outcomes and measuresNumbers and percentages of male and female infants treated for ROP.ResultsOf 11 368 identified studies, 316 met inclusion criteria, yielding a total of 31 026 treated patients. A higher percentage of male infants were treated for ROP (55% [95% CI, 0.54%-0.55%]), with low heterogeneity between studies (I2 = 34%; P < .001). Thirty-eight studies reported sex distribution in the screened population (170 053 patients; 92 612 [53%] male vs 77 441 [47%] female). There was no significant difference in the odds of receiving treatment between screened male and female infants (pooled odds ratio, 1.04 [95% CI, 0.91-1.18]; P = .67).Conclusions and relevanceMore male infants are treated for ROP than female infants. This could be due to a known relative pathophysiological fragility of preterm male infants in addition to a difference in ROP screening rates, with more male infants meeting the criteria than female infants. These findings have implications for future studies and may prompt more careful clinical monitoring of male neonates.
| S-EPMC9539737 | biostudies-literature