Retinopathy Of Prematurity Disease Research Articles

Symmetry of disease in retinopathy of prematurity

Symmetry of disease in retinopathy of prematurity

How is plus disease diagnosed in ROP? Insights from a deep learning computer-based image analysis system with occlusion analysis

Diagnosis of plus disease in retinopathy of prematurity (ROP) is subjective and variable. We have shown that computer-based image analysis can diagnose plus disease with comparable or better accuracy than experts. This study uses outputs from a deep learning algorithm to identify vascular features considered most significant by experts for plus disease diagnosis.

Plus disease in retinopathy of prematurity: should diagnosis be eye-based or quadrant-based?

Plus disease in retinopathy of prematurity: should diagnosis be eye-based or quadrant-based?

Vitreous Bands Identified by Handheld Spectral-Domain Optical Coherence Tomography Among Premature Infants

Handheld spectral-domain optical coherence tomography (SD-OCT) can provide insights into the complex interactions occurring at the vitreoretinal interface in retinopathy of prematurity (ROP) to enhance our understanding of ROP pathology. To characterize vitreous bands in premature infants with use of handheld SD-OCT. Prospective cohort study conducted from July 7, 2015, to February 28, 2017, at 2 university-based neonatal intensive care units. Seventy-three premature infants who required routine ROP screening examination were recruited. Informed consent was obtained from all legal guardians. Trained graders who were masked to the clinical assessment analyzed each SD-OCT scan of the right eye for vitreoretinal findings. A third trained grader mediated disagreements. Associations between the presence of vitreous bands in premature infants with ROP diagnoses and the presence of other vitreoretinal SD-OCT findings were investigated. Of the 73 infants recruited, 6 infants' parents withdrew their children from the study, and 2 infants were too hemodynamically unstable for imaging, leaving a total of 65 participants. Of these, 32 (49%) were female, 36 (55%) were white, 10 (15%) were Hispanic, 3 (5%) were Native American, 4 (6%) were African American, 4 (7%) were Asian/Pacific Islander, and 8 (12%) were other. The mean (SD) gestational age was 28 (2.7) weeks, the mean (SD) birth weight was 997 g (286 g), and the mean (SD) postmenstrual age at imaging was 34 (3) weeks (mean [SD] total of 3 [2] imaging sessions). Comparing the 24 infants (37%) who had a right eye vitreous band at any time with the 41 (63%) who did not, no difference in mean birth weight, gestational age, postmenstrual age at imaging, sex, or race/ethnicity was identified. No associations with ROP stage (eg, in 6 [25%] infants with vitreous bands vs 4 [9.8%] in those without; P = .23), presence of plus disease (2 [8%] vs 2 [5%]; P = .84), or type 1 ROP (3 [12%] vs 3 [7%]; P = .66) were identified. Vitreous bands were associated with epiretinal membrane detected on SD-OCT (P = .001) with an odds ratio of 9.4 (95% CI, 2.8-31.3) in 15 [62%] infants with vitreous bands vs 6 [15%] in those without. Vitreous bands were also associated with cystoid macular edema (in 15 [62%] infants with vitreous bands vs 1 [27%] in those without; P = .005) with an odds ratio of 4.5 (95% CI, 1.5-13.3). In this study, the development of vitreous bands was associated with both cystoid macular edema and epiretinal membrane. These findings suggest a tractional pathogenesis to these entities among premature infants. This study did not find a direct association between vitreous bands and severe ROP. Additional study is needed to determine whether vitreous bands represent subclinical hyaloidal organization leading to retinal detachment in advanced ROP.

Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide. The decision to treat is primarily based on the presence of plus disease, defined as dilation and tortuosity of retinal vessels. However, clinical diagnosis of plus disease is highly subjective and variable. To implement and validate an algorithm based on deep learning to automatically diagnose plus disease from retinal photographs. A deep convolutional neural network was trained using a data set of 5511 retinal photographs. Each image was previously assigned a reference standard diagnosis (RSD) based on consensus of image grading by 3 experts and clinical diagnosis by 1 expert (ie, normal, pre-plus disease, or plus disease). The algorithm was evaluated by 5-fold cross-validation and tested on an independent set of 100 images. Images were collected from 8 academic institutions participating in the Imaging and Informatics in ROP (i-ROP) cohort study. The deep learning algorithm was tested against 8 ROP experts, each of whom had more than 10 years of clinical experience and more than 5 peer-reviewed publications about ROP. Data were collected from July 2011 to December 2016. Data were analyzed from December 2016 to September 2017. A deep learning algorithm trained on retinal photographs. Receiver operating characteristic analysis was performed to evaluate performance of the algorithm against the RSD. Quadratic-weighted κ coefficients were calculated for ternary classification (ie, normal, pre-plus disease, and plus disease) to measure agreement with the RSD and 8 independent experts. Of the 5511 included retinal photographs, 4535 (82.3%) were graded as normal, 805 (14.6%) as pre-plus disease, and 172 (3.1%) as plus disease, based on the RSD. Mean (SD) area under the receiver operating characteristic curve statistics were 0.94 (0.01) for the diagnosis of normal (vs pre-plus disease or plus disease) and 0.98 (0.01) for the diagnosis of plus disease (vs normal or pre-plus disease). For diagnosis of plus disease in an independent test set of 100 retinal images, the algorithm achieved a sensitivity of 93% with 94% specificity. For detection of pre-plus disease or worse, the sensitivity and specificity were 100% and 94%, respectively. On the same test set, the algorithm achieved a quadratic-weighted κ coefficient of 0.92 compared with the RSD, outperforming 6 of 8 ROP experts. This fully automated algorithm diagnosed plus disease in ROP with comparable or better accuracy than human experts. This has potential applications in disease detection, monitoring, and prognosis in infants at risk of ROP.

Accuracy and Reliability of Eye-Based vs Quadrant-Based Diagnosis of Plus Disease in Retinopathy of Prematurity

Presence of plus disease in retinopathy of prematurity is the most critical element in identifying treatment-requiring disease. However, there is significant variability in plus disease diagnosis. In particular, plus disease has been defined as 2 or more quadrants of vascular abnormality, and it is not clear whether it is more reliably and accurately diagnosed by eye-based assessment of overall retinal appearance or by quadrant-based assessment combining grades of 4 individual quadrants. To compare eye-based vs quadrant-based diagnosis of plus disease and to provide insight for ophthalmologists about the diagnostic process. In this multicenter cohort study, we developed a database of 197 wide-angle retinal images from 141 preterm infants from neonatal intensive care units at 9 academic institutions (enrolled from July 2011 to December 2016). Each image was assigned a reference standard diagnosis based on consensus image-based and clinical diagnosis. Data analysis was performed from February 2017 to September 2017. Six graders independently diagnosed each of the 4 quadrants (cropped images) of the 197 eyes (quadrant-based diagnosis) as well as the entire image (eye-based diagnosis). Images were displayed individually, in random order. Quadrant-based diagnosis of plus disease was made when 2 or more quadrants were diagnosed as indicating plus disease by combining grades of individual quadrants post hoc. Intragrader and intergrader reliability (absolute agreement and κ statistic) and accuracy compared with the reference standard diagnosis. Of the 141 included preterm infants, 65 (46.1%) were female and 116 (82.3%) white, and the mean (SD) gestational age was 27.0 (2.6) weeks. There was variable agreement between eye-based and quadrant-based diagnosis among the 6 graders (Cohen κ range, 0.32-0.75). Four graders showed underdiagnosis of plus disease with quadrant-based diagnosis compared with eye-based diagnosis (by McNemar test). Intergrader agreement of quadrant-based diagnosis was lower than that of eye-based diagnosis (Fleiss κ, 0.75 [95% CI, 0.71-0.78] vs 0.55 [95% CI, 0.51-0.59]). The accuracy of eye-based diagnosis compared with the reference standard diagnosis was substantial to near-perfect, whereas that of quadrant-based plus disease diagnosis was only moderate to substantial for each grader. Graders had lower reliability and accuracy using quadrant-based diagnosis combining grades of individual quadrants than with eye-based diagnosis, suggesting that eye-based diagnosis has advantages over quadrant-based diagnosis. This has implications for more precise definitions of plus disease regarding the criterion of 2 or more quadrants, clinical care, computer-based image analysis, and education for all ophthalmologists who manage retinopathy of prematurity.

Plus Disease in Retinopathy of Prematurity—Investigating Its Definition

Plus Disease in Retinopathy of Prematurity—Investigating Its Definition

A national telemedicine network for retinopathy of prematurity screening

To report the results of retinopathy of prematurity (ROP) screening by a telemedicine system in Chile and evaluate its usefulness for referring patients who require treatment. Premature infants at risk of developing ROP from 11 neonatal intensive care units were included. Screening was performed on all infants born at a gestational age of <32weeks and/or birth weight of <1500g. A trained nonphysician operator used an imaging system to capture retinal images, which were reviewed by two independent ROP experts. All infants that required treatment were referred for further evaluation. The study included 2,048 eyes of 1,024 premature infants. Mean gestational age was 28.8±2.2weeks, and mean birth weight was 1128±279g. A total of 5,263 telemedicine examinations were performed and reported. The average number of image sets per patient was 2.6±2.5. Of the 5,263 images, 4,903 (93%) were recorded to at least the end of zone II; 5,172 (98%) were graded as having good quality, allowing for staging of ROP disease. Forty-two infants (4%) were referred for treatment. Discharged patients with ROP type 2 that regressed did not present with any complications or adverse effects during 6months' follow-up. Our study demonstrates the utility of telemedicine screening for ROP with ophthalmologist readers in a developing country. Telemedicine screening was able to detect treatment-requiring ROP. Most of the images had good quality and showed the end of zone II, two variables sufficient to discharge patients.

Imaging Systems for Diagnosis and Following of the Retinopathy of Prematurity

In recent years, there have been a lot of changes in the diagnosis and follow-up imaging systems of Retinopathy of Prematurity (ROP) in the light of technological developments. Advanced imaging systems play a major role in accurately diagnosing and staging ROP disease, making timely treatment decisions, and documenting and sharing data. In addition, due to increasing medicolegal problems, advanced wide-field digital imaging systems and better fundus photographs are needed. In this study, the properties of conventional imaging systems and new wide-angle imaging systems used for diagnosis and follow-up of ROP were evaluated.

An international comparison of retinopathy of prematurity grading performance within the Benefits of Oxygen Saturation Targeting II trials

PurposeTo investigate whether the observed international differences in retinopathy of prematurity (ROP) treatment rates within the Benefits of Oxygen Saturation Targeting (BOOST) II trials might have been caused by international variation in ROP disease grading.MethodsGroups of BOOST II trial ophthalmologists in UK, Australia, and New Zealand (ANZ), and an international reference group (INT) used a web based system to grade a selection of RetCam images of ROP acquired during the BOOST II UK trial. Rates of decisions to treat, plus disease grading, ROP stage grading, ROP zone grading, inter-observer variation within groups and intra-observer variation within groups were measured.ResultsForty-two eye examinations were graded. UK ophthalmologists diagnosed treat-requiring ROP more frequently than ANZ ophthalmologists, 13.9 (3.49) compared to 9.4 (4.46) eye examinations, P=0.038. UK ophthalmologists diagnosed plus disease more frequently than ANZ ophthalmologists, 14.1 (6.23) compared to 8.5 (3.24) eye examinations, P=0.021. ANZ ophthalmologists diagnosed stage 2 ROP more frequently than UK ophthalmologists, 20.2 (5.8) compared to 12.7 (7.1) eye examinations, P=0.026. There were no other significant differences in the grading of ROP stage or zone. Inter-observer variation was higher within the UK group than within the ANZ group. Intra-observer variation was low in both groups.ConclusionsWe have found evidence of international variation in the diagnosis of treatment-requiring ROP. Improved standardisation of the diagnosis of treatment-requiring ROP is required. Measures might include improved training in the grading of ROP, using an international approach, and further development of ROP image analysis software.

Using an Image Fusion Methodology to Improve Efficiency and Traceability of Posterior Pole Vessel Analysis by ROPtool.

Background:The diagnosis of plus disease in retinopathy of prematurity (ROP) largely determines the need for treatment; however, this diagnosis is subjective. To make the diagnosis of plus disease more objective, semi-automated computer programs (e.g. ROPtool) have been created to quantify vascular dilation and tortuosity. ROPtool can accurately analyze blood vessels only in images with very good quality, but many still images captured by indirect ophthalmoscopy have insufficient image quality for ROPtool analysis.Purpose:To evaluate the ability of an image fusion methodology (robust mosaicing) to increase the efficiency and traceability of posterior pole vessel analysis by ROPtool.Materials and Methodology:We retrospectively reviewed video indirect ophthalmoscopy images acquired during routine ROP examinations and selected the best unenhanced still image from the video for each infant. Robust mosaicing was used to create an enhanced mosaic image from the same video for each eye. We evaluated the time required for ROPtool analysis as well as ROPtool’s ability to analyze vessels in enhanced vs. unenhanced images.Results:We included 39 eyes of 39 infants. ROPtool analysis was faster (125 vs. 152 seconds; p=0.02) in enhanced vs. unenhanced images, respectively. ROPtool was able to trace retinal vessels in more quadrants (143/156, 92% vs 115/156, 74%; p=0.16) in enhanced mosaic vs. unenhanced still images, respectively and in more overall (38/39, 97% vs. 34/39, 87%; p=0.07) enhanced mosaic vs. unenhanced still images, respectively.Conclusion:Retinal image enhancement using robust mosaicing advances efforts to automate grading of posterior pole disease in ROP.

Computer-assisted quantification of pre-plus and plus disease in images obtained using Pictor versus video indirect ophthalmoscopy: a pilot study

Subjectivity in the diagnosis of plus disease in retinopathy of prematurity has prompted the creation of computer programs to objectively measure vascular characteristics. ROPtool is a semiautomated computer program that analyzes retinal vascular dilation and tortuosity. To explore its ability to trace images taken with a FDA-approved, portable, handheld noncontact digital fundus camera (Pictor), we compared ROPtool analysis of Pictor still images acquired by nonophthalmologists to video indirect ophthalmoscopy (VIO) still images acquired by ophthalmologists. ROPtool could trace more Pictor versus VIO images. In addition, receiver operating characteristic curves showed that accuracy for diagnosing pre-plus or plus disease was higher using Pictor versus VIO images.

Retinopathy of prematurity: A comprehensive risk analysis for prevention and prediction of disease.

BackgroundRetinopathy of prematurity (ROP) is a blinding morbidity of preterm infants. Our current screening criteria have remained unchanged since their inception and lack the ability to identify those at greatest risk.ObjectivesWe sought to comprehensively analyze numerous proposed maternal, infant, and environmental ROP risk variables in a robustly phenotyped population using logistic regression to determine the most predictive model for ROP development and severity. We further sought to determine the statistical interaction between significant ROP risk variables, which has not previously been done in the field of ROP. We hypothesize that our comprehensive analysis will allow for better identification of risk variables that independently correlate with ROP disease. Going forward, this may allow for improved infant risk stratification along a time continuum from prenatal to postnatal development, making prevention more feasible.MethodsWe performed a retrospective cohort analysis of preterm infants referred for ROP screening in one neonatal intensive care unit from 2010–2015. The primary outcome measure was presence of ROP. Secondary outcome measures were ROP requiring treatment and severe ROP not clearly meeting current treatment criteria. Univariate, stepwise regression and statistical interaction analyses of 57 proposed ROP risk variables was performed to identify variables which were significantly associated with each outcome measure.ResultsWe identified 457 infants meeting our inclusion criteria. Within this cohort, numerous factors showed a significant individual association with our ROP outcome measures; however, stepwise regression analysis found the most predictive model for overall ROP risk included estimated gestational age, birth weight, the need for any surgery, and maternal magnesium prophylaxis. The corresponding Area Under the Curve (AUC) for this model was 0.8641, while the traditional model of gestational age and birth weight predicted ROP disease less well with an AUC of 0.8489. Development of severe ROP was best predicted by estimated gestational age (week), the need for any surgery and increased probability of death or moderate-severe BPD at 7 days. Finally, the model most predictive for type 1 ROP included estimated gestational age (week) and the presence of severe chronic lung disease. No significant statistical interaction was found between variables.ConclusionsOur work is unique as we report comprehensive analysis of the greatest number of proposed ROP risk variables to date in a robustly phenotyped population. We describe novel risk models for our ROP outcome measures and demonstrate independence of these variables using statistical modeling not previously applied to ROP. This may better allow for individual infant risk stratification and importantly mitigation of future risk.

Plus Disease in Retinopathy of Prematurity: Diagnostic Trends in 2016 Versus 2007

To identify any temporal trends in the diagnosis of plus disease in retinopathy of prematurity (ROP) by experts. Reliability analysis. ROP experts were recruited in 2007 and 2016 to classify 34 wide-field fundus images of ROP as plus, pre-plus, or normal, coded as "3," "2," and "1," respectively, in the database. The main outcome was the average calculated score for each image in each cohort. Secondary outcomes included correlation on the relative ordering of the images in 2016 vs 2007, interexpert agreement, and intraexpert agreement. The average score for each image was higher for 30 of 34 (88%) images in 2016 compared with 2007, influenced by fewer images classified as normal (P < .01), a similar number of pre-plus (P= .52), and more classified as plus (P < .01). The mean weighted kappa values in 2006 were 0.36 (range 0.21-0.60), compared with 0.22 (range 0-0.40) in 2016. There was good correlation between rankings of disease severity between the 2 cohorts (Spearman rank correlation ρ= 0.94), indicating near-perfect agreement on relative disease severity. Despite good agreement between cohorts on relative disease severity ranking, the higher average score and classifications for each image demonstrate that experts are diagnosing pre-plus and plus disease at earlier stages of disease severity in 2016, compared with 2007. This has implications for patient care, research, and teaching, and additional studies are needed to better understand this temporal trend in image-based plus disease diagnosis.

Plus Disease in Retinopathy of Prematurity: More Than Meets the ICROP?

Retinopathy of prematurity (ROP), a vasoproliferative retinal disease affecting premature infants, is a leading cause of childhood blindness throughout the world. Plus disease, defined as venous dilatation and arteriolar tortuosity within the posterior retinal vessels greater than or equal to that of a standard published photograph, is the most critical finding in identifying treatment-requiring ROP. Despite an internationally accepted definition of plus disease, there is significant variability in diagnostic process and outcome, producing variable levels of reported intra- and interexpert agreement. Several potential explanations for poor agreement have been proposed, including attention to undefined vascular features such as venous tortuosity, focus on narrower or wider field of view, unfamiliarity with digital images, the magnification and apparent severity of the standard photograph, and cut-off point differences among experts as to the level of tortuosity and dilation sufficient for "plus disease" along a continuum. Moreover, differences in diagnostic consistency among groups of experts separated both geographically and chronologically have been reported. These findings have implications for clinical care, research, and education, and highlight the need for a more precise definition of plus disease and objective diagnostic methods for ROP.

Real-world scenario of retinopathy of prematurity in Kerala

Objective: The objective was to study the incidence and risk factors predisposing to retinopathy of prematurity (ROP) and to assess the outcome after laser photocoagulation. Design: This was a retrospective cohort observational study. Materials and Methods: Infants admitted to a Neonatal Intensive Care Unit of 12 referral hospitals in Kerala between May 2015 and June 2016 were followed up till retinal vascularization completes. Preterm infants with birth weight 34 weeks were screened for ROP at 4 weeks after birth or 31–33 postconceptional age, whichever was later. Infants with birth weight >1700 g and gestation >35 weeks were screened only on neonatologist's discretion. All infants were screened according to the Indian guidelines of type 1 and 2 ROP. We treated both eyes of all infants showing threshold ROP. Statistical analysis was done using SPSS version 16 (SPSS Inc., Chicago, IL, USA). Results: The incidence of ROP in 622 infants screened was 158 (25.4%), of which threshold ROP was seen in 61 (9.80%). No ROP was found in infants weighing >2000 g or with a gestational age >36 weeks. Risk factors predisposing to ROP were hours on ventilator, hemoglobin%, oxygen therapy, and number of blood transfusions, which were more significant in infants with type 1 or threshold ROP than type 2 ROP. Out of 97 infants with type 2 ROP, we saw stage 1 in 31 (30.92%), stage 2 in 59 (60.82%), and stage 3 in 7 (7.21%) infants. 61 (9.80%) infants with threshold ROP were treated with laser photocoagulation. Aggressive posterior ROP or rush disease was seen in 29 (47.54%) of 61 infants with type 1 ROP. Only 2 (3.27%) infants showed falciform fold over macula and 1 (1.63%) infant was blind due to retinal detachment. Conclusion: One-fourth of the infants showed ROP, of which one-tenth needed laser photocoagulation, the outcome of which was good. Risk factors predisposing to ROP were low hemoglobin, high oxygen therapy, increased number of blood transfusions, and hours of ventilator.

Plus Disease in Retinopathy of Prematurity: A Continuous Spectrum of Vascular Abnormality as a Basis of Diagnostic Variability

To identify patterns of interexpert discrepancy in plus disease diagnosis in retinopathy of prematurity (ROP). We developed 2 datasets of clinical images as part of the Imaging and Informatics in ROP study and determined a consensus reference standard diagnosis (RSD) for each image based on 3 independent image graders and the clinical examination results. We recruited 8 expert ROP clinicians to classify these images and compared the distribution of classifications between experts and the RSD. Eight participating experts with more than 10 years of clinical ROP experience and more than 5 peer-reviewed ROP publications who analyzed images obtained during routine ROP screening in neonatal intensive care units. Expert classification of images of plus disease in ROP. Interexpert agreement (weighted κ statistic) and agreement and bias on ordinal classification between experts (analysis of variance [ANOVA]) and the RSD (percent agreement). There was variable interexpert agreement on diagnostic classifications between the 8 experts and the RSD (weighted κ, 0-0.75; mean, 0.30). The RSD agreement ranged from 80% to 94% for the dataset of 100 images and from 29% to 79% for the dataset of 34 images. However, when images were ranked in order of disease severity (by average expert classification), the pattern of expert classification revealed a consistent systematic bias for each expert consistent with unique cut points for the diagnosis of plus disease and preplus disease. The 2-way ANOVA model suggested a highly significant effect of both image and user on the average score (dataset A: P < 0.05 and adjusted R2= 0.82; and dataset B: P < 0.05 and adjusted R2=0.6615). There is wide variability in the classification of plus disease by ROP experts, which occurs because experts have different cut points for the amounts of vascular abnormality required for presence of plus and preplus disease. This has important implications for research, teaching, and patient care for ROP and suggests that a continuous ROP plus disease severity score may reflect more accurately the behavior of expert ROP clinicians and may better standardize classification in the future.

Plus Disease in Retinopathy of Prematurity: Improving Diagnosis by Ranking Disease Severity and Using Quantitative Image Analysis

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. 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. 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. 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. 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. 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). 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.

A shift in retinopathy of prematurity diagnosis at treatment: a 10-year retrospective review

The severity of retinopathy of prematurity (ROP) for which treatment is recommended is well defined by the results of the Early Treatment of ROP trial. This study evaluates whether there has been a change over the past decade in the characteristics of ROP (stage, zone and plus disease) at the time of treatment.

Expert Diagnosis of Plus Disease in Retinopathy of Prematurity From Computer-Based Image Analysis.

Published definitions of plus disease in retinopathy of prematurity (ROP) reference arterial tortuosity and venous dilation within the posterior pole based on a standard published photograph. One possible explanation for limited interexpert reliability for a diagnosis of plus disease is that experts deviate from the published definitions. To identify vascular features used by experts for diagnosis of plus disease through quantitative image analysis. A computer-based image analysis system (Imaging and Informatics in ROP [i-ROP]) was developed using a set of 77 digital fundus images, and the system was designed to classify images compared with a reference standard diagnosis (RSD). System performance was analyzed as a function of the field of view (circular crops with a radius of 1-6 disc diameters) and vessel subtype (arteries only, veins only, or all vessels). Routine ROP screening was conducted from June 29, 2011, to October 14, 2014, in neonatal intensive care units at 8 academic institutions, with a subset of 73 images independently classified by 11 ROP experts for validation. The RSD was compared with the majority diagnosis of experts. The primary outcome measure was the percentage of accuracy of the i-ROP system classification of plus disease, with the RSD as a function of the field of view and vessel type. Secondary outcome measures included the accuracy of the 11 experts compared with the RSD. Accuracy of plus disease diagnosis by the i-ROP computer-based system was highest (95%; 95% CI, 94%-95%) when it incorporated vascular tortuosity from both arteries and veins and with the widest field of view (6-disc diameter radius). Accuracy was 90% or less when using only arterial tortuosity and 85% or less using a 2- to 3-disc diameter view similar to the standard published photograph. Diagnostic accuracy of the i-ROP system (95%) was comparable to that of 11 expert physicians (mean 87%, range 79%-99%). Experts in ROP appear to consider findings from beyond the posterior retina when diagnosing plus disease and consider tortuosity of both arteries and veins, in contrast with published definitions. It is feasible for a computer-based image analysis system to perform comparably with ROP experts, using manually segmented images.