Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images

Analysis of the performance of the CorneAI for iOS in the classification of corneal diseases and cataracts based on journal photographs

CorneAI for iOS is an artificial intelligence (AI) application to classify the condition of the cornea and cataract into nine categories: normal, infectious keratitis, non-infection keratitis, scar, tumor, deposit, acute primary angle closure, lens opacity, and bullous keratopathy. We evaluated its performance to classify multiple conditions of the cornea and cataract of various races in images published in the Cornea journal. The positive predictive value (PPV) of the top classification with the highest predictive score was 0.75, and the PPV for the top three classifications exceeded 0.80. For individual diseases, the highest PPVs were 0.91, 0.73, 0.42, 0.72, 0.77, and 0.55 for infectious keratitis, normal, non-infection keratitis, scar, tumor, and deposit, respectively. CorneAI for iOS achieved an area under the receiver operating characteristic curve of 0.78 (95% confidence interval [CI] 0.5-1.0) for normal, 0.76 (95% CI 0.67-0.85) for infectious keratitis, 0.81 (95% CI 0.64-0.97) for non-infection keratitis, 0.55 (95% CI 0.41-0.69) for scar, 0.62 (95% CI 0.27-0.97) for tumor, and 0.71 (95% CI 0.53-0.89) for deposit. CorneAI performed well in classifying various conditions of the cornea and cataract when used to diagnose journal images, including those with variable imaging conditions, ethnicities, and rare cases.

A systematic review of economic evaluation of artificial intelligence-based screening for eye diseases: From possibility to reality

Artificial Intelligence (AI) has become a focus of research in the rapidly evolving field of ophthalmology. Nevertheless, there is a lack of systematic studies on the health economics of AI in this field. We examine studies from the PubMed, Google Scholar, and Web of Science databases that employed quantitative analysis, retrieved up to July 2023. Most of the studies indicate that AI leads to cost savings and improved efficiency in ophthalmology. On the other hand, some studies suggest that using AI in healthcare may raise costs for patients, especially when taking into account factors such as labor costs, infrastructure, and patient adherence. Future research should cover a wider range of ophthalmic diseases beyond common eye conditions. Moreover, conducting extensive health economic research, designed to collect data relevant to its own context, is imperative.

Development and validation of a deep learning model to predict axial length from ultra-wide field images

BACKGROUND

To validate the feasibility of building a deep learning model to predict axial length (AL) for moderate to high myopic patients from ultra-wide field (UWF) images.

METHODS

This study included 6174 UWF images from 3134 myopic patients during 2014 to 2020 in Eye and ENT Hospital of Fudan University. Of 6174 images, 4939 were used for training, 617 for validation, and 618 for testing. The coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) were used for model performance evaluation.

RESULTS

The model predicted AL with high accuracy. Evaluating performance of R2, MSE and MAE were 0.579, 1.419 and 0.9043, respectively. Prediction bias of 64.88% of the tests was under 1-mm error, 76.90% of tests was within the range of 5% error and 97.57% within 10% error. The prediction bias had a strong negative correlation with true AL values and showed significant difference between male and female (P < 0.001). Generated heatmaps demonstrated that the model focused on posterior atrophy changes in pathological fundus and peri-optic zone in normal fundus. In sex-specific models, R2, MSE, and MAE results of the female AL model were 0.411, 1.357, and 0.911 in female dataset and 0.343, 2.428, and 1.264 in male dataset. The corresponding metrics of male AL models were 0.216, 2.900, and 1.352 in male dataset and 0.083, 2.112, and 1.154 in female dataset.

CONCLUSIONS

It is feasible to utilize deep learning models to predict AL for moderate to high myopic patients with UWF images.

Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images

Purpose

To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images.

Methods

A DLS consisting of two sequential convolutional neural networks (CNNs) to delineate optic disc (OD) and optic cup (OC) boundaries was developed using 800 standard fundus images from the public REFUGE data set. The CNNs were tested on 400 test images from the REFUGE data set and 296 UWF and 300 smartphone-based images from a teleophthalmology clinic. vCDRs derived from the delineated OD/OC boundaries were compared with optometrists' annotations using mean absolute error (MAE). Subgroup analysis was conducted to study the impact of peripapillary atrophy (PPA), and correlation study was performed to investigate potential correlations between sectoral CDR (sCDR) and retinal nerve fiber layer (RNFL) thickness.

Results

The system achieved MAEs of 0.040 (95% CI, 0.037-0.043) in the REFUGE test images, 0.068 (95% CI, 0.061-0.075) in the UWF images, and 0.084 (95% CI, 0.075-0.092) in the smartphone-based images. There was no statistical significance in differences between PPA and non-PPA images. Weak correlation (r = -0.4046, P < 0.05) between sCDR and RNFL thickness was found only in the superior sector.

Conclusions

We developed a deep learning system that estimates vCDR from standard, UWF, and smartphone-based images. We also described anatomic peripapillary adversarial lesion and its potential impact on OD/OC delineation.

Translational Relevance

Artificial intelligence can estimate vCDR from different types of fundus images and may be used as a general and interpretable screening tool to improve community reach for diagnosis and management of glaucoma.

Optic neuropathy in high myopia: Glaucoma or high myopia or both?

Due to the increasing prevalence of high myopia around the world, structural and functional damages to the optic nerve in high myopia has recently attracted much attention. Evidence has shown that high myopia is related to the development of glaucomatous or glaucoma-like optic neuropathy, and that both have many common features. These similarities often pose a diagnostic challenge that will affect the future management of glaucoma suspects in high myopia. In this review, we summarize similarities and differences in optic neuropathy arising from non-pathologic high myopia and glaucoma by considering their respective structural and functional characteristics on fundus photography, optical coherence tomography scanning, and visual field tests. These features may also help to distinguish the underlying mechanisms of the optic neuropathies and to determine management strategies for patients with high myopia and glaucoma.

Deep Learning Detection of Early Retinal Peripheral Degeneration From Ultra-Widefield Fundus Photographs of Asymptomatic Young Adult (17-19 Years) Candidates to Airforce Cadets

Purpose

Artificial intelligence (AI)-assisted ultra-widefield (UWF) fundus photographic interpretation is beneficial to improve the screening of fundus abnormalities. Therefore we constructed an AI machine-learning approach and performed preliminary training and validation.

Methods

We proposed a two-stage deep learning-based framework to detect early retinal peripheral degeneration using UWF images from the Chinese Air Force cadets' medical selection between February 2016 and June 2022. We developed a detection model for the localization of optic disc and macula, which are used to find the peripheral areas. Then we developed six classification models for the screening of various retinal cases. We also compared our proposed framework with two baseline models reported in the literature. The performance of the screening models was evaluated by area under the receiver operating curve (AUC) with 95% confidence interval.

Results

A total of 3911 UWF fundus images were used to develop the deep learning model. The external validation included 760 UWF fundus images. The results of comparison study revealed that our proposed framework achieved competitive performance compared to existing baselines while also demonstrating significantly faster inference time. The developed classification models achieved an average AUC of 0.879 on six different retinal cases in the external validation dataset.

Conclusions

Our two-stage deep learning-based framework improved the machine learning efficiency of the AI model for fundus images with high resolution and many interference factors by maximizing the retention of valid information and compressing the image file size.

Translational Relevance

This machine learning model may become a new paradigm for developing UWF fundus photography AI-assisted diagnosis.

Insights into artificial intelligence in myopia management: from a data perspective

Given the high incidence and prevalence of myopia, the current healthcare system is struggling to handle the task of myopia management, which is worsened by home quarantine during the ongoing COVID-19 pandemic. The utilization of artificial intelligence (AI) in ophthalmology is thriving, yet not enough in myopia. AI can serve as a solution for the myopia pandemic, with application potential in early identification, risk stratification, progression prediction, and timely intervention. The datasets used for developing AI models are the foundation and determine the upper limit of performance. Data generated from clinical practice in managing myopia can be categorized into clinical data and imaging data, and different AI methods can be used for analysis. In this review, we comprehensively review the current application status of AI in myopia with an emphasis on data modalities used for developing AI models. We propose that establishing large public datasets with high quality, enhancing the model's capability of handling multimodal input, and exploring novel data modalities could be of great significance for the further application of AI for myopia.

[Application of artificial intelligence in glaucoma. Part 1. Neural networks and deep learning in glaucoma screening and diagnosis]

This article reviews literature on the use of artificial intelligence (AI) for screening, diagnosis, monitoring and treatment of glaucoma. The first part of the review provides information how AI methods improve the effectiveness of glaucoma screening, presents the technologies using deep learning, including neural networks, for the analysis of big data obtained by methods of ocular imaging (fundus imaging, optical coherence tomography of the anterior and posterior eye segments, digital gonioscopy, ultrasound biomicroscopy, etc.), including a multimodal approach. The results found in the reviewed literature are contradictory, indicating that improvement of the AI models requires further research and a standardized approach. The use of neural networks for timely detection of glaucoma based on multimodal imaging will reduce the risk of blindness associated with glaucoma.

Multimodal and multi-omics-based deep learning model for screening of optic neuropathy

Purpose

To examine the use of multimodal data and multi-omics strategies for optic nerve disease screening.

Methods

This was a single-center retrospective study. A deep learning model was created from fundus photography and infrared reflectance (IR) images of patients with diabetic optic neuropathy, glaucomatous optic neuropathy, and optic neuritis. Patients who were seen at the Ophthalmology Department of First Affiliated Hospital of Nanchang University in Jiangxi Province from November 2019 to April 2023 were included in this study. The data were analyzed in single and multimodal modes following the traditional omics, Resnet101, and fusion models. The accuracy and area-under-the-curve (AUC) of each model were compared.

Results

A total of 312 images fundus and infrared fundus photographs were collected from 156 patients. When multi-modal data was used, the accuracy of the traditional omics mode, Resnet101, and fusion models with the training set were 0.97, 0.98, and 0.99, respectively. The accuracy of the same models with the test sets were 0.72, 0.87, and 0.88, respectively. We compared single- and multi-mode states by applying the data to the different groups in the learning model. In the traditional omics model, the macro-average AUCs of the features extracted from fundus photography, IR images, and multimodal data were 0.94, 0.90, and 0.96, respectively. When the same data were processed in the Resnet101 model, the scores were 0.97 equally. However, when multimodal data was utilized, the macro-average AUCs in the traditional omics, Resnet101, and fusion modesl were 0.96, 0.97, and 0.99, respectively.

Conclusion

The deep learning model based on multimodal data and multi-omics strategies can improve the accuracy of screening and diagnosing diabetic optic neuropathy, glaucomatous optic neuropathy, and optic neuritis.

Deep Learning Performance of Ultra-Widefield Fundus Imaging for Screening Retinal Lesions in Rural Locales

Importance

Retinal diseases are the leading cause of irreversible blindness worldwide, and timely detection contributes to prevention of permanent vision loss, especially for patients in rural areas with limited medical resources. Deep learning systems (DLSs) based on fundus images with a 45° field of view have been extensively applied in population screening, while the feasibility of using ultra-widefield (UWF) fundus image-based DLSs to detect retinal lesions in patients in rural areas warrants exploration.

Objective

To explore the performance of a DLS for multiple retinal lesion screening using UWF fundus images from patients in rural areas.

Design, Setting, and Participants

In this diagnostic study, a previously developed DLS based on UWF fundus images was used to screen for 5 retinal lesions (retinal exudates or drusen, glaucomatous optic neuropathy, retinal hemorrhage, lattice degeneration or retinal breaks, and retinal detachment) in 24 villages of Yangxi County, China, between November 17, 2020, and March 30, 2021.

Interventions

The captured images were analyzed by the DLS and ophthalmologists.

Main Outcomes and Measures

The performance of the DLS in rural screening was compared with that of the internal validation in the previous model development stage. The image quality, lesion proportion, and complexity of lesion composition were compared between the model development stage and the rural screening stage.

Results

A total of 6222 eyes in 3149 participants (1685 women [53.5%]; mean [SD] age, 70.9 [9.1] years) were screened. The DLS achieved a mean (SD) area under the receiver operating characteristic curve (AUC) of 0.918 (0.021) (95% CI, 0.892-0.944) for detecting 5 retinal lesions in the entire data set when applied for patients in rural areas, which was lower than that reported at the model development stage (AUC, 0.998 [0.002] [95% CI, 0.995-1.000]; P < .001). Compared with the fundus images in the model development stage, the fundus images in this rural screening study had an increased frequency of poor quality (13.8% [860 of 6222] vs 0%), increased variation in lesion proportions (0.1% [6 of 6222]-36.5% [2271 of 6222] vs 14.0% [2793 of 19 891]-21.3% [3433 of 16 138]), and an increased complexity of lesion composition.

Conclusions and Relevance

This diagnostic study suggests that the DLS exhibited excellent performance using UWF fundus images as a screening tool for 5 retinal lesions in patients in a rural setting. However, poor image quality, diverse lesion proportions, and a complex set of lesions may have reduced the performance of the DLS; these factors in targeted screening scenarios should be taken into consideration in the model development stage to ensure good performance.

Discriminative-Region Multi-Label Classification of Ultra-Widefield Fundus Images

Ultra-widefield fundus image (UFI) has become a crucial tool for ophthalmologists in diagnosing ocular diseases because of its ability to capture a wide field of the retina. Nevertheless, detecting and classifying multiple diseases within this imaging modality continues to pose a significant challenge for ophthalmologists. An automated disease classification system for UFI can support ophthalmologists in making faster and more precise diagnoses. However, existing works for UFI classification often focus on a single disease or assume each image only contains one disease when tackling multi-disease issues. Furthermore, the distinctive characteristics of each disease are typically not utilized to improve the performance of the classification systems. To address these limitations, we propose a novel approach that leverages disease-specific regions of interest for the multi-label classification of UFI. Our method uses three regions, including the optic disc area, the macula area, and the entire UFI, which serve as the most informative regions for diagnosing one or multiple ocular diseases. Experimental results on a dataset comprising 5930 UFIs with six common ocular diseases showcase that our proposed approach attains exceptional performance, with the area under the receiver operating characteristic curve scores for each class spanning from 95.07% to 99.14%. These results not only surpass existing state-of-the-art methods but also exhibit significant enhancements, with improvements of up to 5.29%. These results demonstrate the potential of our method to provide ophthalmologists with valuable information for early and accurate diagnosis of ocular diseases, ultimately leading to improved patient outcomes.

Artificial intelligence in ophthalmology: The path to the real-world clinic

Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.

Assistive applications of artificial intelligence in ophthalmology

PURPOSE OF REVIEW

Assistive (nonautonomous) artificial intelligence (AI) models designed to support (rather than function independently of) clinicians have received increasing attention in medicine. This review aims to highlight several recent developments in these models over the past year and their ophthalmic implications.

RECENT FINDINGS

Artificial intelligence models with a diverse range of applications in ophthalmology have been reported in the literature over the past year. Many of these systems have reported high performance in detection, classification, prognostication, and/or monitoring of retinal, glaucomatous, anterior segment, and other ocular pathologies.

SUMMARY

Over the past year, developments in AI have been made that have implications affecting ophthalmic surgical training and refractive outcomes after cataract surgery, therapeutic monitoring of disease, disease classification, and prognostication. Many of these recently developed models have obtained encouraging results and have the potential to serve as powerful clinical decision-making tools pending further external validation and evaluation of their generalizability.

Deep Learning for the Detection of Multiple Fundus Diseases Using Ultra-widefield Images

INTRODUCTION

To design and evaluate a deep learning model based on ultra-widefield images (UWFIs) that can detect several common fundus diseases.

METHODS

Based on 4574 UWFIs, a deep learning model was trained and validated that can identify normal fundus and eight common fundus diseases, namely referable diabetic retinopathy, retinal vein occlusion, pathologic myopia, retinal detachment, retinitis pigmentosa, age-related macular degeneration, vitreous opacity, and optic neuropathy. The model was tested on three test sets with data volumes of 465, 979, and 525. The performance of the three deep learning networks, EfficientNet-B7, DenseNet, and ResNet-101, was evaluated on the internal test set. Additionally, we compared the performance of the deep learning model with that of doctors in a tertiary referral hospital.

RESULTS

Compared to the other two deep learning models, EfficientNet-B7 achieved the best performance. The area under the receiver operating characteristic curves of the EfficientNet-B7 model on the internal test set, external test set A and external test set B were 0.9708 (0.8772, 0.9849) to 1.0000 (1.0000, 1.0000), 0.9683 (0.8829, 0.9770) to 1.0000 (0.9975, 1.0000), and 0.8919 (0.7150, 0.9055) to 0.9977 (0.9165, 1.0000), respectively. On a data set of 100 images, the total accuracy of the deep learning model was 93.00%, the average accuracy of three ophthalmologists who had been working for 2 years and three ophthalmologists who had been working in fundus imaging for more than 5 years was 88.00% and 94.00%, respectively.

CONCLUSION

High performance was achieved on all three test sets using our UWFI multidisease classification model with a small sample size and fast model inference. The performance of the artificial intelligence model was comparable to that of a physician with 2-5 years of experience in fundus diseases at a tertiary referral hospital. The model is expected to be used as an effective aid for fundus disease screening.

Applications of Artificial Intelligence and Deep Learning in Glaucoma

Diagnosis and detection of progression of glaucoma remains challenging. Artificial intelligence-based tools have the potential to improve and standardize the assessment of glaucoma but development of these algorithms is difficult given the multimodal and variable nature of the diagnosis. Currently, most algorithms are focused on a single imaging modality, specifically screening and diagnosis based on fundus photos or optical coherence tomography images. Use of anterior segment optical coherence tomography and goniophotographs is limited. The majority of algorithms designed for disease progression prediction are based on visual fields. No studies in our literature search assessed the use of artificial intelligence for treatment response prediction and no studies conducted prospective testing of their algorithms. Additional challenges to the development of artificial intelligence-based tools include scarcity of data and a lack of consensus in diagnostic criteria. Although research in the use of artificial intelligence for glaucoma is promising, additional work is needed to develop clinically usable tools.

LAC-GAN: Lesion attention conditional GAN for Ultra-widefield image synthesis

Automatic detection of retinal diseases based on deep learning technology and Ultra-widefield (UWF) images plays an important role in clinical practices in recent years. However, due to small lesions and limited data samples, it is not easy to train a detection-accurate model with strong generalization ability. In this paper, we propose a lesion attention conditional generative adversarial network (LAC-GAN) to synthesize retinal images with realistic lesion details to improve the training of the disease detection model. Specifically, the generator takes the vessel mask and class label as the conditional inputs, and processes the random Gaussian noise by a series of residual block to generate the synthetic images. To focus on pathological information, we propose a lesion feature attention mechanism based on random forest (RF) method, which constructs its reverse activation network to activate the lesion features. For discriminator, a weight-sharing multi-discriminator is designed to improve the performance of model by affine transformations. Experimental results on multi-center UWF image datasets demonstrate that the proposed method can generate retinal images with reasonable details, which helps to enhance the performance of the disease detection model.

Deep learning for ultra-widefield imaging: a scoping review

PURPOSE

This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-widefield (UWF) imaging. This study provides an overview of the published uses of DL and UWF imaging for the detection of ophthalmic and systemic diseases, generative image synthesis, quality assessment of images, and segmentation and localization of ophthalmic image features.

METHODS

A literature search was performed up to August 31st, 2021 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) deep learning, (2) ultra-widefield imaging. The exclusion criteria were as follows: (1) articles published in any language other than English, (2) articles not peer-reviewed (usually preprints), (3) no full-text availability, (4) articles using machine learning algorithms other than deep learning. No study design was excluded from consideration.

RESULTS

A total of 36 studies were included. Twenty-three studies discussed ophthalmic disease detection and classification, 5 discussed segmentation and localization of ultra-widefield images (UWFIs), 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWF imaging.

CONCLUSION

The application of DL to UWF imaging has demonstrated significant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has also been applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWF imaging, and the future of DL applications in this field.

Comparison between Deep-Learning-Based Ultra-Wide-Field Fundus Imaging and True-Colour Confocal Scanning for Diagnosing Glaucoma

In this retrospective, comparative study, we evaluated and compared the performance of two confocal imaging modalities in detecting glaucoma based on a deep learning (DL) classifier: ultra-wide-field (UWF) fundus imaging and true-colour confocal scanning. A total of 777 eyes, including 273 normal control eyes and 504 glaucomatous eyes, were tested. A convolutional neural network was used for each true-colour confocal scan (Eidon AF™, CenterVue, Padova, Italy) and UWF fundus image (Optomap™, Optos PLC, Dunfermline, UK) to detect glaucoma. The diagnostic model was trained using 545 training and 232 test images. The presence of glaucoma was determined, and the accuracy and area under the receiver operating characteristic curve (AUC) metrics were assessed for diagnostic power comparison. DL-based UWF fundus imaging achieved an AUC of 0.904 (95% confidence interval (CI): 0.861−0.937) and accuracy of 83.62%. In contrast, DL-based true-colour confocal scanning achieved an AUC of 0.868 (95% CI: 0.824−0.912) and accuracy of 81.46%. Both DL-based confocal imaging modalities showed no significant differences in their ability to diagnose glaucoma (p = 0.135) and were comparable to the traditional optical coherence tomography parameter-based methods (all p > 0.005). Therefore, using a DL-based algorithm on true-colour confocal scanning and UWF fundus imaging, we confirmed that both confocal fundus imaging techniques had high value in diagnosing glaucoma.

Performances of Machine Learning in Detecting Glaucoma Using Fundus and Retinal Optical Coherence Tomography Images: A Meta-Analysis

PURPOSE

To evaluate the performance of machine learning (ML) in detecting glaucoma using fundus and retinal optical coherence tomography (OCT) images.

DESIGN

Meta-analysis.

METHODS

PubMed and EMBASE were searched on August 11, 2021. A bivariate random-effects model was used to pool ML's diagnostic sensitivity, specificity, and area under the curve (AUC). Subgroup analyses were performed based on ML classifier categories and dataset types.

RESULTS

One hundred and five studies (3.3%) were retrieved. Seventy-three (69.5%), 30 (28.6%), and 2 (1.9%) studies tested ML using fundus, OCT, and both image types, respectively. Total testing data numbers were 197,174 for fundus and 16,039 for OCT. Overall, ML showed excellent performances for both fundus (pooled sensitivity = 0.92 [95% CI, 0.91-0.93]; specificity = 0.93 [95% CI, 0.91-0.94]; and AUC = 0.97 [95% CI, 0.95-0.98]) and OCT (pooled sensitivity = 0.90 [95% CI, 0.86-0.92]; specificity = 0.91 [95% CI, 0.89-0.92]; and AUC = 0.96 [95% CI, 0.93-0.97]). ML performed similarly using all data and external data for fundus and the external test result of OCT was less robust (AUC = 0.87). When comparing different classifier categories, although support vector machine showed the highest performance (pooled sensitivity, specificity, and AUC ranges, 0.92-0.96, 0.95-0.97, and 0.96-0.99, respectively), results by neural network and others were still good (pooled sensitivity, specificity, and AUC ranges, 0.88-0.93, 0.90-0.93, 0.95-0.97, respectively). When analyzed based on dataset types, ML demonstrated consistent performances on clinical datasets (fundus AUC = 0.98 [95% CI, 0.97-0.99] and OCT AUC = 0.95 [95% 0.93-0.97]).

CONCLUSIONS

Performance of ML in detecting glaucoma compares favorably to that of experts and is promising for clinical application. Future prospective studies are needed to better evaluate its real-world utility.

Artificial intelligence to detect malignant eyelid tumors from photographic images

Malignant eyelid tumors can invade adjacent structures and pose a threat to vision and even life. Early identification of malignant eyelid tumors is crucial to avoiding substantial morbidity and mortality. However, differentiating malignant eyelid tumors from benign ones can be challenging for primary care physicians and even some ophthalmologists. Here, based on 1,417 photographic images from 851 patients across three hospitals, we developed an artificial intelligence system using a faster region-based convolutional neural network and deep learning classification networks to automatically locate eyelid tumors and then distinguish between malignant and benign eyelid tumors. The system performed well in both internal and external test sets (AUCs ranged from 0.899 to 0.955). The performance of the system is comparable to that of a senior ophthalmologist, indicating that this system has the potential to be used at the screening stage for promoting the early detection and treatment of malignant eyelid tumors.

Comparison of deep learning systems and cornea specialists in detecting corneal diseases from low-quality images

The performance of deep learning in disease detection from high-quality clinical images is identical to and even greater than that of human doctors. However, in low-quality images, deep learning performs poorly. Whether human doctors also have poor performance in low-quality images is unknown. Here, we compared the performance of deep learning systems with that of cornea specialists in detecting corneal diseases from low-quality slit lamp images. The results showed that the cornea specialists performed better than our previously established deep learning system (PEDLS) trained on only high-quality images. The performance of the system trained on both high- and low-quality images was superior to that of the PEDLS while inferior to that of a senior corneal specialist. This study highlights that cornea specialists perform better in low-quality images than the system trained on high-quality images. Adding low-quality images with sufficient diagnostic certainty to the training set can reduce this performance gap.

•

Deep learning performs poorly in low-quality images for detecting corneal diseases

•

Corneal specialists perform better than the PEDLS in low-quality images

•

The performance of the NDLS is better than that of the PEDLS in low-quality images

•

Adding low-quality images to the training set can improve the system's performance

Telehealth and Screening Strategies in the Diagnosis and Management of Glaucoma

Telehealth has become a viable option for glaucoma screening and glaucoma monitoring due to advances in technology. The ability to measure intraocular pressure without an anesthetic and to take optic nerve photographs without pharmacologic pupillary dilation using portable equipment have allowed glaucoma screening programs to generate enough data for assessment. At home, patients can perform visual acuity testing, web-based visual field testing, rebound tonometry, and video visits with the physician to monitor for glaucomatous progression. Artificial intelligence will enhance the accuracy of data interpretation and inspire confidence in popularizing telehealth for glaucoma.

Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning

BACKGROUND

Retinal exudates and/or drusen (RED) can be signs of many fundus diseases that can lead to irreversible vision loss. Early detection and treatment of these diseases are critical for improving vision prognosis. However, manual RED screening on a large scale is time-consuming and labour-intensive. Here, we aim to develop and assess a deep learning system for automated detection of RED using ultra-widefield fundus (UWF) images.

METHODS

A total of 26,409 UWF images from 14,994 subjects were used to develop and evaluate the deep learning system. The Zhongshan Ophthalmic Center (ZOC) dataset was selected to compare the performance of the system to that of retina specialists in RED detection. The saliency map visualization technique was used to understand which areas in the UWF image had the most influence on our deep learning system when detecting RED.

RESULTS

The system for RED detection achieved areas under the receiver operating characteristic curve of 0.994 (95% confidence interval [CI]: 0.991-0.996), 0.972 (95% CI: 0.957-0.984), and 0.988 (95% CI: 0.983-0.992) in three independent datasets. The performance of the system in the ZOC dataset was comparable to that of an experienced retina specialist. Regions of RED were highlighted by saliency maps in UWF images.

CONCLUSIONS

Our deep learning system is reliable in the automated detection of RED in UWF images. As a screening tool, our system may promote the early diagnosis and management of RED-related fundus diseases.

Preventing corneal blindness caused by keratitis using artificial intelligence

Keratitis is the main cause of corneal blindness worldwide. Most vision loss caused by keratitis can be avoidable via early detection and treatment. The diagnosis of keratitis often requires skilled ophthalmologists. However, the world is short of ophthalmologists, especially in resource-limited settings, making the early diagnosis of keratitis challenging. Here, we develop a deep learning system for the automated classification of keratitis, other cornea abnormalities, and normal cornea based on 6,567 slit-lamp images. Our system exhibits remarkable performance in cornea images captured by the different types of digital slit lamp cameras and a smartphone with the super macro mode (all AUCs>0.96). The comparable sensitivity and specificity in keratitis detection are observed between the system and experienced cornea specialists. Our system has the potential to be applied to both digital slit lamp cameras and smartphones to promote the early diagnosis and treatment of keratitis, preventing the corneal blindness caused by keratitis.

Health care cost and benefits of artificial intelligence-assisted population-based glaucoma screening for the elderly in remote areas of China: a cost-offset analysis

Background

Population-based screening was essential for glaucoma management. Although various studies have investigated the cost-effectiveness of glaucoma screening, policymakers facing with uncontrollably growing total health expenses were deeply concerned about the potential financial consequences of glaucoma screening. This present study was aimed to explore the impact of glaucoma screening with artificial intelligence (AI) automated diagnosis from a budgetary standpoint in Changjiang county, China.

Methods

A Markov model based on health care system’s perspective was adapted from previously published studies to predict disease progression and healthcare costs. A cohort of 19,395 individuals aged 65 and above were simulated over a 15-year timeframe. Fur illustrative purpose, we only considered primary angle-closure glaucoma (PACG) in this study. Prevalence, disease progression risks between stages, compliance rates were obtained from publish studies. We did a meta-analysis to estimate diagnostic performance of AI automated diagnosis system from fundus image. Screening costs were provided by the Changjiang screening programme, whereas treatment costs were derived from electronic medical records from two county hospitals. Main outcomes included the number of PACG patients and health care costs. Cost-offset analysis was employed to compare projected health outcomes and medical care costs under the screening with what they would have been without screening. One-way sensitivity analysis was conducted to quantify uncertainties around model results.

Results

Among people aged 65 and above in Changjiang county, it was predicted that there were 1940 PACG patients under the AI-assisted screening scenario, compared with 2104 patients without screening in 15 years’ time. Specifically, the screening would reduce patients with primary angle closure suspect by 7.7%, primary angle closure by 8.8%, PACG by 16.7%, and visual blindness by 33.3%. Due to early diagnosis and treatment under the screening, healthcare costs surged dramatically to $107,761.4 dollar in the first year and then were constantly declining over time, while without screening costs grew from $14,759.8 in the second year until peaking at $17,900.9 in the 9th year. However, cost-offset analysis revealed that additional healthcare costs resulted from the screening could not be offset by decreased disease progression. The 5-, 10-, and 15-year accumulated incremental costs of screening versus no screening were estimated to be $396,362.8, $424,907.9, and $434,903.2, respectively. As a result, the incremental cost per PACG of any stages prevented was $1464.3.

Conclusions

This study represented the first attempt to address decision-maker’s budgetary concerns when adopting glaucoma screening by developing a Markov prediction model to project health outcomes and costs. Population screening combined with AI automated diagnosis for PACG in China were able to reduce disease progression risks. However, the excess costs of screening could never be offset by reduction in disease progression. Further studies examining the cost-effectiveness or cost-utility of AI-assisted glaucoma screening were needed.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-021-11097-w.

Polymorphisms of the cytomegalovirus glycoprotein B genotype in patients with Posner-Schlossman syndrome

Aims

The aim of this observational study was to report the distribution of glycoprotein B (gB) genotypes in the eyes of cytomegalovirus (CMV) positive patients with Posner-Schlossman syndrome (PSS), and to investigate their clinical characteristics and outcomes.

Methods

We collected aqueous humour samples from 165 patients clinically diagnosed with PSS between 2017 and 2019. PCR was performed to analyse the CMV DNA and identify the gB genotypes in the samples. Clinical characteristics and responses to antiviral treatment were compared among patients with different gB genotypes.

Results

CMV DNA was detected in 94 (56.97%) of the 165 aqueous humour specimens analysed. Owing to the quantity requirement for CMV gB genotype analysis, results could be obtained from only 14 specimens. CMV gB type 1 was detected in 11 samples (78.6%), whereas CMV gB type 3 was detected in three samples (21.4%). No other gB genotypes or mixed genotypes were detected. Overall, 9.1% (1/11) of the patients in the gB type 1 group and 66.7% (2/3) of the patients in the gB type 3 group had bilateral attacks (p=0.093). The concentration of anti-CMV immunoglobulin G (IgG) in the type 1 group was 0.94±0.79 s/co (ratio of aqueous humour CMV IgG/serum CMV IgG to aqueous humour albumin concentration/serum albumin concentration), whereas that in the type 3 group was 0.67±0.71 s/co.

Conclusion

Genotype 1 was the most prevalent genotype in the aqueous humour of CMV-infected patients with PSS. Bilateral attack was predominant among patients with gB genotype 3. CMV gB gene may be related to the pathogenicity of CMV virus strain in patients with PSS.

Automated Grading of Diabetic Retinopathy with Ultra-Widefield Fluorescein Angiography and Deep Learning

PURPOSE

The objective of this study was to establish diagnostic technology to automatically grade the severity of diabetic retinopathy (DR) according to the ischemic index and leakage index with ultra-widefield fluorescein angiography (UWFA) and the Early Treatment Diabetic Retinopathy Study (ETDRS) 7-standard field (7-SF).

METHODS

This is a cross-sectional study. UWFA samples from 280 diabetic patients and 119 normal patients were used to train and test an artificial intelligence model to differentiate PDR and NPDR based on the ischemic index and leakage index with UWFA. A panel of retinal specialists determined the ground truth for our data set before experimentation. A confusion matrix as a metric was used to measure the precision of our algorithm, and a simple linear regression function was implemented to explore the discrimination of indexes on the DR grades. In addition, the model was tested with simulated 7-SF.

RESULTS

The model classification of DR in the original UWFA images achieved 88.50% accuracy and 73.68% accuracy in the simulated 7-SF images. A simple linear regression function demonstrated that there is a significant relationship between the ischemic index and leakage index and the severity of DR. These two thresholds were set to classify the grade of DR, which achieved 76.8% accuracy.

CONCLUSIONS

The optimization of the cycle generative adversarial network (CycleGAN) and convolutional neural network (CNN) model classifier achieved DR grading based on the ischemic index and leakage index with UWFA and simulated 7-SF and provided accurate inference results. The classification accuracy with UWFA is slightly higher than that of simulated 7-SF.