Automated diagnosis and quantitative analysis of plus disease in retinopathy of prematurity based on deep convolutional neural networks

Image Analysis-Based Machine Learning for the Diagnosis of Retinopathy of Prematurity: A Meta-analysis and Systematic Review

TOPIC

To evaluate the performance of machine learning (ML) in the diagnosis of retinopathy of prematurity (ROP) and to assess whether it can be an effective automated diagnostic tool for clinical applications.

CLINICAL RELEVANCE

Early detection of ROP is crucial for preventing tractional retinal detachment and blindness in preterm infants, which has significant clinical relevance.

METHODS

Web of Science, PubMed, Embase, IEEE Xplore, and Cochrane Library were searched for published studies on image-based ML for diagnosis of ROP or classification of clinical subtypes from inception to October 1, 2022. The quality assessment tool for artificial intelligence-centered diagnostic test accuracy studies was used to determine the risk of bias (RoB) of the included original studies. A bivariate mixed effects model was used for quantitative analysis of the data, and the Deek's test was used for calculating publication bias. Quality of evidence was assessed using Grading of Recommendations Assessment, Development and Evaluation.

RESULTS

Twenty-two studies were included in the systematic review; 4 studies had high or unclear RoB. In the area of indicator test items, only 2 studies had high or unclear RoB because they did not establish predefined thresholds. In the area of reference standards, 3 studies had high or unclear RoB. Regarding applicability, only 1 study was considered to have high or unclear applicability in terms of patient selection. The sensitivity and specificity of image-based ML for the diagnosis of ROP were 93% (95% confidence interval [CI]: 0.90-0.94) and 95% (95% CI: 0.94-0.97), respectively. The area under the receiver operating characteristic curve (AUC) was 0.98 (95% CI: 0.97-0.99). For the classification of clinical subtypes of ROP, the sensitivity and specificity were 93% (95% CI: 0.89-0.96) and 93% (95% CI: 0.89-0.95), respectively, and the AUC was 0.97 (95% CI: 0.96-0.98). The classification results were highly similar to those of clinical experts (Spearman's R = 0.879).

CONCLUSIONS

Machine learning algorithms are no less accurate than human experts and hold considerable potential as automated diagnostic tools for ROP. However, given the quality and high heterogeneity of the available evidence, these algorithms should be considered as supplementary tools to assist clinicians in diagnosing ROP.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Automated diagnosis of plus disease in retinopathy of prematurity using quantification of vessels characteristics

The condition known as Plus disease is distinguished by atypical alterations in the retinal vasculature of neonates born prematurely. It has been demonstrated that the diagnosis of Plus disease is subjective and qualitative in nature. The utilization of quantitative methods and computer-based image analysis to enhance the objectivity of Plus disease diagnosis has been extensively established in the literature. This study presents the development of a computer-based image analysis method aimed at automatically distinguishing Plus images from non-Plus images. The proposed methodology conducts a quantitative analysis of the vascular characteristics linked to Plus disease, thereby aiding physicians in making informed judgments. A collection of 76 posterior retinal images from a diverse group of infants who underwent screening for Retinopathy of Prematurity (ROP) was obtained. A reference standard diagnosis was established as the majority of the labeling performed by three experts in ROP during two separate sessions. The process of segmenting retinal vessels was carried out using a semi-automatic methodology. Computer algorithms were developed to compute the tortuosity, dilation, and density of vessels in various retinal regions as potential discriminative characteristics. A classifier was provided with a set of selected features in order to distinguish between Plus images and non-Plus images. This study included 76 infants (49 [64.5%] boys) with mean birth weight of 1305 ± 427 g and mean gestational age of 29.3 ± 3 weeks. The average level of agreement among experts for the diagnosis of plus disease was found to be 79% with a standard deviation of 5.3%. In terms of intra-expert agreement, the average was 85% with a standard deviation of 3%. Furthermore, the average tortuosity of the five most tortuous vessels was significantly higher in Plus images compared to non-Plus images (p ≤ 0.0001). The curvature values based on points were found to be significantly higher in Plus images compared to non-Plus images (p ≤ 0.0001). The maximum diameter of vessels within a region extending 5-disc diameters away from the border of the optic disc (referred to as 5DD) exhibited a statistically significant increase in Plus images compared to non-Plus images (p ≤ 0.0001). The density of vessels in Plus images was found to be significantly higher compared to non-Plus images (p ≤ 0.0001). The classifier's accuracy in distinguishing between Plus and non-Plus images, as determined through tenfold cross-validation, was found to be 0.86 ± 0.01. This accuracy was observed to be higher than the diagnostic accuracy of one out of three experts when compared to the reference standard. The implemented algorithm in the current study demonstrated a commendable level of accuracy in detecting Plus disease in cases of retinopathy of prematurity, exhibiting comparable performance to that of expert diagnoses. By engaging in an objective analysis of the characteristics of vessels, there exists the possibility of conducting a quantitative assessment of the disease progression's features. The utilization of this automated system has the potential to enhance physicians' ability to diagnose Plus disease, thereby offering valuable contributions to the management of ROP through the integration of traditional ophthalmoscopy and image-based telemedicine methodologies.

Automatic zoning for retinopathy of prematurity with a key area location system

Retinopathy of prematurity (ROP) usually occurs in premature or low birth weight infants and has been an important cause of childhood blindness worldwide. Diagnosis and treatment of ROP are mainly based on stage, zone and disease, where the zone is more important than the stage for serious ROP. However, due to the great subjectivity and difference of ophthalmologists in the diagnosis of ROP zoning, it is challenging to achieve accurate and objective ROP zoning diagnosis. To address it, we propose a new key area location (KAL) system to achieve automatic and objective ROP zoning based on its definition, which consists of a key point location network and an object detection network. Firstly, to achieve the balance between real-time and high-accuracy, a lightweight residual heatmap network (LRH-Net) is designed to achieve the location of the optic disc (OD) and macular center, which transforms the location problem into a pixel-level regression problem based on the heatmap regression method and maximum likelihood estimation theory. In addition, to meet the needs of clinical accuracy and real-time detection, we use the one-stage object detection framework Yolov3 to achieve ROP lesion location. Finally, the experimental results have demonstrated that the proposed KAL system has achieved better performance on key point location (6.13 and 17.03 pixels error for OD and macular center location) and ROP lesion location (93.05% for AP50), and the ROP zoning results based on it have good consistency with the results manually labeled by clinicians, which can support clinical decision-making and help ophthalmologists correctly interpret ROP zoning, reducing subjective differences of diagnosis and increasing the interpretability of zoning results.

Identification of novel biomarkers for retinopathy of prematurity in preterm infants by use of innovative technologies and artificial intelligence

Retinopathy of prematurity (ROP) is a leading cause of preventable vision loss in preterm infants. While appropriate screening is crucial for early identification and treatment of ROP, current screening guidelines remain limited by inter-examiner variability in screening modalities, absence of local protocol for ROP screening in some settings, a paucity of resources and an increased survival of younger and smaller infants. This review summarizes the advancements and challenges of current innovative technologies, artificial intelligence (AI), and predictive biomarkers for the diagnosis and management of ROP. We provide a contemporary overview of AI-based models for detection of ROP, its severity, progression, and response to treatment. To address the transition from experimental settings to real-world clinical practice, challenges to the clinical implementation of AI for ROP are reviewed and potential solutions are proposed. The use of optical coherence tomography (OCT) and OCT angiography (OCTA) technology is also explored, providing evaluation of subclinical ROP characteristics that are often imperceptible on fundus examination. Furthermore, we explore several potential biomarkers to reduce the need for invasive procedures, to enhance diagnostic accuracy and treatment efficacy. Finally, we emphasize the need of a symbiotic integration of biologic and imaging biomarkers and AI in ROP screening, where the robustness of biomarkers in early disease detection is complemented by the predictive precision of AI algorithms.

An Artificial Intelligence System for Screening and Recommending the Treatment Modalities for Retinopathy of Prematurity

PURPOSE

The purpose of this study was to develop an artificial intelligence (AI) system for the identification of disease status and recommending treatment modalities for retinopathy of prematurity (ROP).

METHODS

This retrospective cohort study included a total of 24,495 RetCam images from 1075 eyes of 651 preterm infants who received RetCam examination at the Shenzhen Eye Hospital in Shenzhen, China, from January 2003 to August 2021. Three tasks included ROP identification, severe ROP identification, and treatment modalities identification (retinal laser photocoagulation or intravitreal injections). The AI system was developed to identify the 3 tasks, especially the treatment modalities of ROP. The performance between the AI system and ophthalmologists was compared using extra 200 RetCam images.

RESULTS

The AI system exhibited favorable performance in the 3 tasks, including ROP identification [area under the receiver operating characteristic curve (AUC), 0.9531], severe ROP identification (AUC, 0.9132), and treatment modalities identification with laser photocoagulation or intravitreal injections (AUC, 0.9360). The AI system achieved an accuracy of 0.8627, a sensitivity of 0.7059, and a specificity of 0.9412 for identifying the treatment modalities of ROP. External validation results confirmed the good performance of the AI system with an accuracy of 92.0% in all 3 tasks, which was better than 4 experienced ophthalmologists who scored 56%, 65%, 71%, and 76%, respectively.

CONCLUSIONS

The described AI system achieved promising outcomes in the automated identification of ROP severity and treatment modalities. Using such algorithmic approaches as accessory tools in the clinic may improve ROP screening in the future.

Vessels characteristics in familial exudative vitreoretinopathy and retinopathy of prematurity based on deep convolutional neural networks

Purpose

The purpose of this study was to investigate the quantitative retinal vascular morphological characteristics of Retinopathy of Prematurity (ROP) and Familial Exudative Vitreoretinopathy (FEVR) in the newborn by the application of a deep learning network with artificial intelligence.

Methods

Standard 130-degree fundus photographs centered on the optic disc were taken in the newborns. The deep learning network provided segmentation of the retinal vessels and the optic disc (OD). Based on the vessel segmentation, the vascular morphological characteristics, including avascular area, vessel angle, vessel density, fractal dimension (FD), and tortuosity, were automatically evaluated.

Results

201 eyes of FEVR, 289 eyes of ROP, and 195 eyes of healthy individuals were included in this study. The deep learning system of blood vessel segmentation had a sensitivity of 72% and a specificity of 99%. The vessel angle in the FEVR group was significantly smaller than that in the normal group and ROP group (37.43 ± 5.43 vs. 39.40 ± 5.61, 39.50 ± 5.58, P = 0.001, < 0.001 respectively). The normal group had the lowest vessel density, the ROP group was in between, and the FEVR group had the highest (2.64 ± 0.85, 2.97 ± 0.92, 3.37 ± 0.88 respectively). The FD was smaller in controls than in the FEVR and ROP groups (0.984 ± 0.039, 1.018 ± 0.039 and 1.016 ± 0.044 respectively, P < 0.001). The ROP group had the most tortuous vessels, while the FEVR group had the stiffest vessels, the controls were in the middle (11.61 ± 3.17, 8.37 ± 2.33 and 7.72 ± 1.57 respectively, P < 0.001).

Conclusions

The deep learning technology used in this study has good performance in the quantitative analysis of vascular morphological characteristics in fundus photography. Vascular morphology was different in the newborns of FEVR and ROP compared to healthy individuals, which showed great clinical value for the differential diagnosis of ROP and FEVR.

Fairness and generalisability in deep learning of retinopathy of prematurity screening algorithms: a literature review

BACKGROUND

Retinopathy of prematurity (ROP) is a vasoproliferative disease responsible for more than 30 000 blind children worldwide. Its diagnosis and treatment are challenging due to the lack of specialists, divergent diagnostic concordance and variation in classification standards. While artificial intelligence (AI) can address the shortage of professionals and provide more cost-effective management, its development needs fairness, generalisability and bias controls prior to deployment to avoid producing harmful unpredictable results. This review aims to compare AI and ROP study's characteristics, fairness and generalisability efforts.

METHODS

Our review yielded 220 articles, of which 18 were included after full-text assessment. The articles were classified into ROP severity grading, plus detection, detecting treatment requiring, ROP prediction and detection of retinal zones.

RESULTS

All the article's authors and included patients are from middle-income and high-income countries, with no low-income countries, South America, Australia and Africa Continents representation.Code is available in two articles and in one on request, while data are not available in any article. 88.9% of the studies use the same retinal camera. In two articles, patients' sex was described, but none applied a bias control in their models.

CONCLUSION

The reviewed articles included 180 228 images and reported good metrics, but fairness, generalisability and bias control remained limited. Reproducibility is also a critical limitation, with few articles sharing codes and none sharing data. Fair and generalisable ROP and AI studies are needed that include diverse datasets, data and code sharing, collaborative research, and bias control to avoid unpredictable and harmful deployments.

Artificial intelligence for the diagnosis of retinopathy of prematurity: A systematic review of current algorithms

BACKGROUND/OBJECTIVES

With the increasing survival of premature infants, there is an increased demand to provide adequate retinopathy of prematurity (ROP) services. Wide field retinal imaging (WFDRI) and artificial intelligence (AI) have shown promise in the field of ROP and have the potential to improve the diagnostic performance and reduce the workload for screening ophthalmologists. The aim of this review is to systematically review and provide a summary of the diagnostic characteristics of existing deep learning algorithms.

SUBJECT/METHODS

Two authors independently searched the literature, and studies using a deep learning system from retinal imaging were included. Data were extracted, assessed and reported using PRISMA guidelines.

RESULTS

Twenty-seven studies were included in this review. Nineteen studies used AI systems to diagnose ROP, classify the staging of ROP, diagnose the presence of pre-plus or plus disease, or assess the quality of retinal images. The included studies reported a sensitivity of 71%-100%, specificity of 74-99% and area under the curve of 91-99% for the primary outcome of the study. AI techniques were comparable to the assessment of ophthalmologists in terms of overall accuracy and sensitivity. Eight studies evaluated vascular severity scores and were able to accurately differentiate severity using an automated classification score.

CONCLUSION

Artificial intelligence for ROP diagnosis is a growing field, and many potential utilities have already been identified, including the presence of plus disease, staging of disease and a new automated severity score. AI has a role as an adjunct to clinical assessment; however, there is insufficient evidence to support its use as a sole diagnostic tool currently.

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

As the only blood vessels that can directly be seen in the whole body, pathological changes in retinal vessels are related to the metabolic state of the whole body and many systems, which seriously affect the vision and quality of life of patients. Timely diagnosis and treatment are key to improving vision prognosis. In recent years, with the rapid development of artificial intelligence, the application of artificial intelligence in ophthalmology has become increasingly extensive and in-depth, especially in the field of retinal vascular diseases. Research study results based on artificial intelligence and fundus images are remarkable and provides a great possibility for early diagnosis and treatment. This paper reviews the recent research progress on artificial intelligence in retinal vascular diseases (including diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, retinopathy of prematurity, and age-related macular degeneration). The limitations and challenges of the research process are also discussed.

Machine Learning-Based Integration of Metabolomics Characterisation Predicts Progression of Myopic Retinopathy in Children and Adolescents

Myopic retinopathy is an important cause of irreversible vision loss and blindness. As metabolomics has recently been successfully applied in myopia research, this study sought to characterize the serum metabolic profile of myopic retinopathy in children and adolescents (4-18 years) and to develop a diagnostic model that combines clinical and metabolic features. We selected clinical and serum metabolic data from children and adolescents at different time points as the training set (n = 516) and the validation set (n = 60). All participants underwent an ophthalmologic examination. Untargeted metabolomics analysis of serum was performed. Three machine learning (ML) models were trained by combining metabolic features and conventional clinical factors that were screened for significance in discrimination. The better-performing model was validated in an independent point-in-time cohort and risk nomograms were developed. Retinopathy was present in 34.2% of participants (n = 185) in the training set, including 109 (28.61%) with mild to moderate myopia. A total of 27 metabolites showed significant variation between groups. After combining Lasso and random forest (RF), 12 modelled metabolites (mainly those involved in energy metabolism) were screened. Both the logistic regression and extreme Gradient Boosting (XGBoost) algorithms showed good discriminatory ability. In the time-validation cohort, logistic regression (AUC 0.842, 95% CI 0.724-0.96) and XGBoost (AUC 0.897, 95% CI 0.807-0.986) also showed good prediction accuracy and had well-fitted calibration curves. Three clinical characteristic coefficients remained significant in the multivariate joint model (p < 0.05), as did 8/12 metabolic characteristic coefficients. Myopic retinopathy may have abnormal energy metabolism. Machine learning models based on metabolic profiles and clinical data demonstrate good predictive performance and facilitate the development of individual interventions for myopia in children and adolescents.

CM-SegNet: A deep learning-based automatic segmentation approach for medical images by combining convolution and multilayer perceptron

Accurate segmentation of lesions in medical images is of great significance for clinical diagnosis and evaluation. The low contrast between lesions and surrounding tissues increases the difficulty of automatic segmentation, while the efficiency of manual segmentation is low. In order to increase the generalization performance of segmentation model, we proposed a deep learning-based automatic segmentation model called CM-SegNet for segmenting medical images of different modalities. It was designed according to the multiscale input and encoding-decoding thoughts, and composed of multilayer perceptron and convolution modules. This model achieved communication of different channels and different spatial locations of each patch, and considers the edge related feature information between adjacent patches. Thus, it could fully extract global and local image information for the segmentation task. Meanwhile, this model met the effective segmentation of different structural lesion regions in different slices of three-dimensional medical images. In this experiment, the proposed CM-SegNet was trained, validated, and tested using six medical image datasets of different modalities and 5-fold cross validation method. The results showed that the CM-SegNet model had better segmentation performance and shorter training time for different medical images than the previous methods, suggesting it is faster and more accurate in automatic segmentation and has great potential application in clinic.

Early Diagnosis and Quantitative Analysis of Stages in Retinopathy of Prematurity Based on Deep Convolutional Neural Networks

Purpose

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness. An accurate and timely diagnosis of the early stages of ROP allows ophthalmologists to recommend appropriate treatment while blindness is still preventable. The purpose of this study was to develop an automatic deep convolutional neural network-based system that provided a diagnosis of stage I to III ROP with feature parameters.

Methods

We developed three data sets containing 18,827 retinal images of preterm infants. These retinal images were obtained from the ophthalmology department of Jiaxing Maternal and Child Health Hospital in China. After segmenting images, we calculated the region of interest (ROI). We trained our system based on segmented ROI images from the training data set, tested the performance of the classifier on the test data set, and evaluated the widths of the demarcation lines or ridges extracted by the system, as well as the ratios of vascular proliferation within the ROI on a comparison data set.

Results

The trained network achieved a sensitivity of 90.21% with 97.67% specificity for the diagnosis of stage I ROP, 92.75% sensitivity with 98.74% specificity for stage II ROP, and 91.84% sensitivity with 99.29% sensitivity for stage III ROP. When the system diagnosed normal images, the sensitivity and specificity reached 95.93% and 96.41%, respectively. The widths (in pixels) of the demarcation lines or ridges for normal, stage I, stage II, and stage III were 15.22 ± 1.06, 26.35 ± 1.36, and 30.75 ± 1.55. The ratios of the vascular proliferation within the ROI were 1.40 ± 0.29, 1.54 ± 0.26, and 1.81 ± 0.33. All parameters were statistically different among the groups. When physicians integrated quantitative parameters of the extracted features with their clinic diagnosis, the κ score was significantly improved.

Conclusions

Our system achieved a high accuracy of diagnosis for stage I to III ROP. It used the quantitative analysis of the extracted features to assist physicians in providing classification decisions.

Translational Relevance

The high performance of the system suggests potential applications in ancillary diagnosis of the early stages of ROP.

Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Coronavirus disease 2019 (COVID-19) pneumonia has erupted worldwide, causing massive population deaths and huge economic losses. In clinic, lung ultrasound (LUS) plays an important role in the auxiliary diagnosis of COVID-19 pneumonia. However, the lack of medical resources leads to the low using efficiency of the LUS, to address this problem, a novel automated LUS scoring system for evaluating COVID-19 pneumonia based on the two-stage cascaded deep learning model was proposed in this paper. 18,330 LUS images collected from 26 COVID-19 pneumonia patients were successfully assigned scores by two experienced doctors according to the designed four-level scoring standard for training the model. At the first stage, we made a secondary selection of these scored images through five ResNet-50 models and five-fold cross validation to obtain the available 12,949 LUS images which were highly relevant to the initial scoring results. At the second stage, three deep learning models including ResNet-50, Vgg-19, and GoogLeNet were formed the cascaded scored model and trained using the new dataset, whose predictive result was obtained by the voting mechanism. In addition, 1000 LUS images collected another 5 COVID-19 pneumonia patients were employed to test the model. Experiments results showed that the automated LUS scoring model was evaluated in terms of accuracy, sensitivity, specificity, and F1-score, being 96.1%, 96.3%, 98.8%, and 96.1%, respectively. They proved the proposed two-stage cascaded deep learning model could automatically score an LUS image, which has great potential for application to the clinics on various occasions.

Prediction of Refractive Error Based on Ultrawide Field Images With Deep Learning Models in Myopia Patients

Summary

Ultrawide field fundus images could be applied in deep learning models to predict the refractive error of myopic patients. The predicted error was related to the older age and greater spherical power.

Purpose

To explore the possibility of predicting the refractive error of myopic patients by applying deep learning models trained with ultrawide field (UWF) images.

Methods

UWF fundus images were collected from left eyes of 987 myopia patients of Eye and ENT Hospital, Fudan University between November 2015 and January 2019. The fundus images were all captured with Optomap Daytona, a 200° UWF imaging device. Three deep learning models (ResNet-50, Inception-v3, Inception-ResNet-v2) were trained with the UWF images for predicting refractive error. 133 UWF fundus images were also collected after January 2021 as an the external validation data set. The predicted refractive error was compared with the “true value” measured by subjective refraction. Mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient (R²) value were calculated in the test set. The Spearman rank correlation test was applied for univariate analysis and multivariate linear regression analysis on variables affecting MAE. The weighted heat map was generated by averaging the predicted weight of each pixel.

Results

ResNet-50, Inception-v3 and Inception-ResNet-v2 models were trained with the UWF images for refractive error prediction with R² of 0.9562, 0.9555, 0.9563 and MAE of 1.72(95%CI: 1.62–1.82), 1.75(95%CI: 1.65–1.86) and 1.76(95%CI: 1.66–1.86), respectively. 29.95%, 31.47% and 29.44% of the test set were within the predictive error of 0.75D in the three models. 64.97%, 64.97%, and 64.47% was within 2.00D predictive error. The predicted MAE was related to older age (P < 0.01) and greater spherical power(P < 0.01). The optic papilla and macular region had significant predictive power in the weighted heat map.

Conclusions

It was feasible to predict refractive error in myopic patients with deep learning models trained by UWF images with the accuracy to be improved.

Pathologic myopia: advances in imaging and the potential role of artificial intelligence

Pathologic myopia is a severe form of myopia that can lead to permanent visual impairment. The recent global increase in the prevalence of myopia has been projected to lead to a higher incidence of pathologic myopia in the future. Thus, imaging myopic eyes to detect early pathological changes, or predict myopia progression to allow for early intervention, has become a key priority. Recent advances in optical coherence tomography (OCT) have contributed to the new grading system for myopic maculopathy and myopic traction maculopathy, which may improve phenotyping and thus, clinical management. Widefield fundus and OCT imaging has improved the detection of posterior staphyloma. Non-invasive OCT angiography has enabled depth-resolved imaging for myopic choroidal neovascularisation. Artificial intelligence (AI) has shown great performance in detecting pathologic myopia and the identification of myopia-associated complications. These advances in imaging with adjunctive AI analysis may lead to improvements in monitoring disease progression or guiding treatments. In this review, we provide an update on the classification of pathologic myopia, how imaging has improved clinical evaluation and management of myopia-associated complications, and the recent development of AI algorithms to aid the detection and classification of pathologic myopia.

Avoiding use of lid speculum and indentation reduced infantile stress during retinopathy of prematurity examinations

PURPOSE

To study the safety and efficacy of indirect ophthalmoscopy with (Sp) or without (speculum free, SpF) the use of lid speculum and scleral indentation for retinopathy of prematurity (ROP) screening.

METHODS

In this crossover randomized controlled trial, preterm infants received either the Sp on their first and the SpF technique on their second examination a week later or vice versa. Video recordings of the infants' reactions were assessed by two observers, using Premature Infant Pain Profile-Revised score and the crying score of the Bernese Pain Scale for Neonates. Fundoscopy adequacy, its duration and adverse events within the first 24 hr postscreening were also recorded.

RESULTS

Thirty-seven infants with median (interquartile range) gestational age of 28.7 (28.0, 30.2) weeks and mean (standard deviation, SD) birth weight 1225 (377) grams were enrolled. The mydriasis-induced stress was similar between the Sp and SpF exam (mean difference [MD]: 0.78, 95% confidence interval [CI]: -0.83, 2.38; p = 0.33). The stress induced by fundoscopy (MD: 4.98, 95% CI: 3.58, 6.37; p < 0.001) and examination overall (MD: 2.32, 95% CI: 0.96, 3.67; p = 0.001) were higher in the Sp than in the SpF exam, and so was the crying score during fundoscopy (MD: 1.31, 95% CI: 1.06, 1.56; p < 0.001). Adverse events in the two groups were similar (p = 0.13). Fundoscopy was adequate in identifying the absence of treatment-requiring ROP in all cases, and lasted longer in the Sp than in the SpF exam (p < 0.001).

CONCLUSION

Our study suggests that the use of speculum and indentation should be reserved for the few cases where fundus visualization is insufficient for excluding the presence of severe ROP.

Morphological characteristics of retinal vessels in eyes with high myopia: Ultra-wide field images analyzed by artificial intelligence using a transfer learning system

Purpose

The purpose of this study is to investigate the retinal vascular morphological characteristics in high myopia patients of different severity.

Methods

317 eyes of high myopia patients and 104 eyes of healthy control subjects were included in this study. The severity of high myopia patients is classified into C0-C4 according to the Meta Analysis of the Pathologic Myopia (META-PM) classification and their vascular morphological characteristics in ultra-wide field imaging were analyzed using transfer learning methods and RU-net. Correlation with axial length (AL), best corrected visual acuity (BCVA) and age was analyzed. In addition, the vascular morphological characteristics of myopic choroidal neovascularization (mCNV) patients and their matched high myopia patients were compared.

Results

The RU-net and transfer learning system of blood vessel segmentation had an accuracy of 98.24%, a sensitivity of 71.42%, a specificity of 99.37%, a precision of 73.68% and a F1 score of 72.29. Compared with healthy control group, high myopia group had smaller vessel angle (31.12 ± 2.27 vs. 32.33 ± 2.14), smaller fractal dimension (Df) (1.383 ± 0.060 vs. 1.424 ± 0.038), smaller vessel density (2.57 ± 0.96 vs. 3.92 ± 0.93) and fewer vascular branches (201.87 ± 75.92 vs. 271.31 ± 67.37), all P < 0.001. With the increase of myopia maculopathy severity, vessel angle, Df, vessel density and vascular branches significantly decreased (all P < 0.001). There were significant correlations of these characteristics with AL, BCVA and age. Patients with mCNV tended to have larger vessel density (P < 0.001) and more vascular branches (P = 0.045).

Conclusion

The RU-net and transfer learning technology used in this study has an accuracy of 98.24%, thus has good performance in quantitative analysis of vascular morphological characteristics in Ultra-wide field images. Along with the increase of myopic maculopathy severity and the elongation of eyeball, vessel angle, Df, vessel density and vascular branches decreased. Myopic CNV patients have larger vessel density and more vascular branches.

Artificial intelligence-based detection of epimacular membrane from color fundus photographs

Epiretinal membrane (ERM) is a common ophthalmological disorder of high prevalence. Its symptoms include metamorphopsia, blurred vision, and decreased visual acuity. Early diagnosis and timely treatment of ERM is crucial to preventing vision loss. Although optical coherence tomography (OCT) is regarded as a de facto standard for ERM diagnosis due to its intuitiveness and high sensitivity, ophthalmoscopic examination or fundus photographs still have the advantages of price and accessibility. Artificial intelligence (AI) has been widely applied in the health care industry for its robust and significant performance in detecting various diseases. In this study, we validated the use of a previously trained deep neural network based-AI model in ERM detection based on color fundus photographs. An independent test set of fundus photographs was labeled by a group of ophthalmologists according to their corresponding OCT images as the gold standard. Then the test set was interpreted by other ophthalmologists and AI model without knowing their OCT results. Compared with manual diagnosis based on fundus photographs alone, the AI model had comparable accuracy (AI model 77.08% vs. integrated manual diagnosis 75.69%, χ² = 0.038, P = 0.845, McNemar’s test), higher sensitivity (75.90% vs. 63.86%, χ² = 4.500, P = 0.034, McNemar’s test), under the cost of lower but reasonable specificity (78.69% vs. 91.80%, χ² = 6.125, P = 0.013, McNemar’s test). Thus our AI model can serve as a possible alternative for manual diagnosis in ERM screening.

Artificial intelligence in myopia: current and future trends

PURPOSE OF REVIEW

Myopia is one of the leading causes of visual impairment, with a projected increase in prevalence globally. One potential approach to address myopia and its complications is early detection and treatment. However, current healthcare systems may not be able to cope with the growing burden. Digital technological solutions such as artificial intelligence (AI) have emerged as a potential adjunct for myopia management.

RECENT FINDINGS

There are currently four significant domains of AI in myopia, including machine learning (ML), deep learning (DL), genetics and natural language processing (NLP). ML has been demonstrated to be a useful adjunctive for myopia prediction and biometry for cataract surgery in highly myopic individuals. DL techniques, particularly convoluted neural networks, have been applied to various image-related diagnostic and predictive solutions. Applications of AI in genomics and NLP appear to be at a nascent stage.

SUMMARY

Current AI research is mainly focused on disease classification and prediction in myopia. Through greater collaborative research, we envision AI will play an increasingly critical role in big data analysis by aggregating a greater variety of parameters including genomics and environmental factors. This may enable the development of generalizable adjunctive DL systems that could help realize predictive and individualized precision medicine for myopic patients.

Accuracy of Deep Learning Algorithms for the Diagnosis of Retinopathy of Prematurity by Fundus Images: A Systematic Review and Meta-Analysis

Background

Retinopathy of prematurity (ROP) occurs in preterm infants and may contribute to blindness. Deep learning (DL) models have been used for ophthalmologic diagnoses. We performed a systematic review and meta-analysis of published evidence to summarize and evaluate the diagnostic accuracy of DL algorithms for ROP by fundus images.

Methods

We searched PubMed, EMBASE, Web of Science, and Institute of Electrical and Electronics Engineers Xplore Digital Library on June 13, 2021, for studies using a DL algorithm to distinguish individuals with ROP of different grades, which provided accuracy measurements. The pooled sensitivity and specificity values and the area under the curve (AUC) of summary receiver operating characteristics curves (SROC) summarized overall test performance. The performances in validation and test datasets were assessed together and separately. Subgroup analyses were conducted between the definition and grades of ROP. Threshold and nonthreshold effects were tested to assess biases and evaluate accuracy factors associated with DL models.

Results

Nine studies with fifteen classifiers were included in our meta-analysis. A total of 521,586 objects were applied to DL models. For combined validation and test datasets in each study, the pooled sensitivity and specificity were 0.953 (95% confidence intervals (CI): 0.946-0.959) and 0.975 (0.973-0.977), respectively, and the AUC was 0.984 (0.978-0.989). For the validation dataset and test dataset, the AUC was 0.977 (0.968-0.986) and 0.987 (0.982-0.992), respectively. In the subgroup analysis of ROP vs. normal and differentiation of two ROP grades, the AUC was 0.990 (0.944-0.994) and 0.982 (0.964-0.999), respectively.

Conclusions

Our study shows that DL models can play an essential role in detecting and grading ROP with high sensitivity, specificity, and repeatability. The application of a DL-based automated system may improve ROP screening and diagnosis in the future.

Intraoperative assessment of canine soft tissue sarcoma by deep learning enhanced optical coherence tomography

Soft tissue sarcoma (STS) is a locally aggressive and infiltrative tumour in dogs. Surgical resection is the treatment of choice for local tumour control. Currently, post-operative pathology is performed for surgical margin assessment. Spectral-domain optical coherence tomography (OCT) has recently been evaluated for its value for surgical margin assessment in some tumour types in dogs. The purpose of this study was to develop an automatic diagnosis system that can assist clinicians in real-time for OCT image interpretation of tissues at surgical margins. We utilized a ResNet-50 network to classify healthy and cancerous tissues. A patch-based approach was adopted to achieve accurate classification with limited training data (80 cancer images, 80 normal images) and the validation set (20 cancer images, 20 normal images). The proposed method achieved an average accuracy of 97.1% with an excellent sensitivity of 94.3% on the validation set; the quadratic weighted κ was 0.94 for the STS diagnosis. In an independent test data set of 20 OCT images (10 cancer images, 10 normal images), the proposed method correctly differentiated all the STS images. Furthermore, we proposed a diagnostic curve, which could be evaluated in real-time to assist clinicians in detecting the specific location of a lesion. In short, the proposed method is accurate, operates in real-time and is non-invasive, which could be helpful for future surgical guidance.

Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs

This study aimed to develop an automated computer-based algorithm to estimate axial length and subfoveal choroidal thickness (SFCT) based on color fundus photographs. In the population-based Beijing Eye Study 2011, we took fundus photographs and measured SFCT by optical coherence tomography (OCT) and axial length by optical low-coherence reflectometry. Using 6394 color fundus images taken from 3468 participants, we trained and evaluated a deep-learning-based algorithm for estimation of axial length and SFCT. The algorithm had a mean absolute error (MAE) for estimating axial length and SFCT of 0.56 mm [95% confidence interval (CI): 0.53,0.61] and 49.20 μm (95% CI: 45.83,52.54), respectively. Estimated values and measured data showed coefficients of determination of r 2 = 0.59 (95% CI: 0.50,0.65) for axial length and r 2 = 0.62 (95% CI: 0.57,0.67) for SFCT. Bland-Altman plots revealed a mean difference in axial length and SFCT of -0.16 mm (95% CI: -1.60,1.27 mm) and of -4.40 μm (95% CI, -131.8,122.9 μm), respectively. For the estimation of axial length, heat map analysis showed that signals predominantly from overall of the macular region, the foveal region, and the extrafoveal region were used in the eyes with an axial length of < 22 mm, 22-26 mm, and > 26 mm, respectively. For the estimation of SFCT, the convolutional neural network (CNN) used mostly the central part of the macular region, the fovea or perifovea, independently of the SFCT. Our study shows that deep-learning-based algorithms may be helpful in estimating axial length and SFCT based on conventional color fundus images. They may be a further step in the semiautomatic assessment of the eye.

Comparative study on optic disc features of premature infants and full-term newborns

Background

To study optic disc features of premature infants and compare to that of term infants to explore the pattern and features of newborn optic disc development and provide the basis for the diagnosis of newborn optic disc disease.

Methods

This was a prospective clinical research. Newborns underwent newborn fundus disease screening from January 1st, 2016 to October 31st, 2016 in the neonatal ward of Ruian City Maternal and Child Health Hospital were selected. RetCam 3 Version6.1.25.0 Wide-Field Digital Pediatric Retinal Imaging System developed by Clarity Medical Systems, Inc was adopted to conduct fundus examination on both eyes, 130 degree wide-angle lens was used to film the images centering optic disc.

Results

For both premature infants and full-term newborns, vertical diameter of the optic disc to lateral diameter of the optic disc ratio was > 1, and the shape of the optic disc was a vertical oval. The difference of each optic disc parameter between premature infants and full-term newborns was not statistically significant (P > 0.05). There’s a difference of constitution of sclerotic ring type on optic disc between premature infants and full-term newborns. Among which, the proportion of single ring type and double ring type in premature infants was higher than that in full-term newborns (P < 0.05). The proportion of no ring type in full-term newborns was higher than that in premature infants (P < 0.05). The proportion of mixed type had no significant difference (P > 0.05) between premature infants and full-term newborns.

Conclusions

We found that The proportion of mature types (single ring type and double ring type) in full-term newborns was higher than that in premature infants. While there’s no statistical difference of the proportion of mixed types between premature infants and full-term newborns. Double ring type was a normal stage of the development of optic disc.

Retinopathy of Prematurity: How to Prevent the Third Epidemics in Developing Countries

Retinopathy of prematurity (ROP) is vasoproliferative disease affecting preterm infants and is a leading cause of avoidable childhood blindness worldwide. The world is currently experiencing the third epidemic of ROP, where majority of the cases are from middle-income countries. Over 40% of the world's premature infants were born in India, China, Bangladesh, Pakistan, and Indonesia. Together with other neighboring nations, this region has unique challenges in ROP management. Key aspects of the challenges including heavier and more mature infants developing severe ROP. Current strategies include adoption of national screening guidelines, telemedicine, integrating vision rehabilitation and software innovations in the form of artificial intelligence. This review overviews some of these aspects.

Dehaze of Cataractous Retinal Images Using an Unpaired Generative Adversarial Network

Cataracts are the leading cause of visual impairment worldwide. Examination of the retina through cataracts using a fundus camera is challenging and error-prone due to degraded image quality. We sought to develop an algorithm to dehaze such images to support diagnosis by either ophthalmologists or computer-aided diagnosis systems. Based on the generative adversarial network (GAN) concept, we designed two neural networks: CataractSimGAN and CataractDehazeNet. CataractSimGAN was intended for the synthesis of cataract-like images through unpaired clear retinal images and cataract images. CataractDehazeNet was trained using pairs of synthesized cataract-like images and the corresponding clear images through supervised learning. With two networks trained independently, the number of hyper-parameters was reduced, leading to better performance. We collected 400 retinal images without cataracts and 400 hazy images from cataract patients as the training dataset. Fifty cataract images and the corresponding clear images from the same patients after surgery comprised the test dataset. The clear images after surgery were used for reference to evaluate the performance of our method. CataractDehazeNet was able to enhance the degraded image from cataract patients substantially and to visualize blood vessels and the optic disc, while actively suppressing the artifacts common in application of similar methods. Thus, we developed an algorithm to improve the quality of the retinal images acquired from cataract patients. We achieved high structure similarity and fidelity between processed images and images from the same patients after cataract surgery.

The American Society of Retina Specialists Artificial Intelligence Task Force Report

Artificial intelligence (AI) is a growing area that relies on the heavy use of diagnostic imaging within the field of retina to offer exciting advancements in diagnostic capability to better understand and manage retinal conditions such as diabetic retinopathy, diabetic macular edema, age-related macular degeneration, and retinopathy of prematurity. However, there are discrepancies between the findings of these AI programs and their referral recommendations compared with evidence-based referral patterns, such as Preferred Practice Patterns by the American Academy of Ophthalmology. The overall focus of this task force report is to first describe the work in AI being completed in the management of retinal conditions. This report also discusses the guidelines of the Preferred Practice Pattern and how they can be used in the emerging field of AI.

Artificial Intelligence in Retinopathy of Prematurity Diagnosis

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.