Machine learning applied to retinal image processing for glaucoma detection: review and perspective

Artificial Intelligence in Radiology: What Is Its True Role at Present, and Where Is the Evidence?

The integration of artificial intelligence (AI) in radiology has brought about substantial advancements and transformative potential in diagnostic imaging practices. This study presents an overview of the current research on the application of AI in radiology, highlighting key insights from recent studies and surveys. These recent studies have explored the expected impact of AI, encompassing machine learning and deep learning, on the work volume of diagnostic radiologists. The present and future role of AI in radiology holds great promise for enhancing diagnostic capabilities, improving workflow efficiency, and ultimately, advancing patient care.

A comparative evaluation of deep learning approaches for ophthalmology

There is a growing number of publicly available ophthalmic imaging datasets and open-source code for Machine Learning algorithms. This allows ophthalmic researchers and practitioners to independently perform various deep-learning tasks. With the advancement in artificial intelligence (AI) and in the field of imaging, the choice of the most appropriate AI architecture for different tasks will vary greatly. The best-performing AI-dataset combination will depend on the specific problem that needs to be solved and the type of data available. The article discusses different machine learning models and deep learning architectures currently used for various ophthalmic imaging modalities and for different machine learning tasks. It also proposes the most appropriate models based on accuracy and other important factors such as training time, the ability to deploy the model on clinical devices/smartphones, heatmaps that enhance the self-explanatory nature of classification decisions, and the ability to train/adapt on small image datasets to determine if further data collection is worthwhile. The article extensively reviews the existing state-of-the-art AI methods focused on useful machine-learning applications for ophthalmology. It estimates their performance and viability through training and evaluating architectures with different public and private image datasets of different modalities, such as full-color retinal images, OCT images, and 3D OCT scans. The article is expected to benefit the readers by enriching their knowledge of artificial intelligence applied to ophthalmology.

Robust PCA with Lw,∗ and L2,1 Norms: A Novel Method for Low-Quality Retinal Image Enhancement

Nonmydriatic retinal fundus images often suffer from quality issues and artifacts due to ocular or systemic comorbidities, leading to potential inaccuracies in clinical diagnoses. In recent times, deep learning methods have been widely employed to improve retinal image quality. However, these methods often require large datasets and lack robustness in clinical settings. Conversely, the inherent stability and adaptability of traditional unsupervised learning methods, coupled with their reduced reliance on extensive data, render them more suitable for real-world clinical applications, particularly in the limited data context of high noise levels or a significant presence of artifacts. However, existing unsupervised learning methods encounter challenges such as sensitivity to noise and outliers, reliance on assumptions like cluster shapes, and difficulties with scalability and interpretability, particularly when utilized for retinal image enhancement. To tackle these challenges, we propose a novel robust PCA (RPCA) method with low-rank sparse decomposition that also integrates affine transformations τi, weighted nuclear norm, and the L2,1 norms, aiming to overcome existing method limitations and to achieve image quality improvement unseen by these methods. We employ the weighted nuclear norm (Lw,∗) to assign weights to singular values to each retinal images and utilize the L2,1 norm to eliminate correlated samples and outliers in the retinal images. Moreover, τi is employed to enhance retinal image alignment, making the new method more robust to variations, outliers, noise, and image blurring. The Alternating Direction Method of Multipliers (ADMM) method is used to optimally determine parameters, including τi, by solving an optimization problem. Each parameter is addressed separately, harnessing the benefits of ADMM. Our method introduces a novel parameter update approach and significantly improves retinal image quality, detecting cataracts, and diabetic retinopathy. Simulation results confirm our method's superiority over existing state-of-the-art methods across various datasets.

Enhancing Medical Image Classification with an Advanced Feature Selection Algorithm: A Novel Approach to Improving the Cuckoo Search Algorithm by Incorporating Caputo Fractional Order

Glaucoma is a chronic eye condition that seriously impairs vision and requires early diagnosis and treatment. Automated detection techniques are essential for obtaining a timely diagnosis. In this paper, we propose a novel method for feature selection that integrates the cuckoo search algorithm with Caputo fractional order (CFO-CS) to enhance the performance of glaucoma classification. However, when using the infinite series, the Caputo definition has memory length truncation issues. Therefore, we suggest a fixed memory step and an adjustable term count for optimization. We conducted experiments integrating various feature extraction techniques, including histograms of oriented gradients (HOGs), local binary patterns (LBPs), and deep features from MobileNet and VGG19, to create a unified vector. We evaluate the informative features selected from the proposed method using the k-nearest neighbor. Furthermore, we use data augmentation to enhance the diversity and quantity of the training set. The proposed method enhances convergence speed and the attainment of optimal solutions during training. The results demonstrate superior performance on the test set, achieving 92.62% accuracy, 94.70% precision, 93.52% F1-Score, 92.98% specificity, 92.36% sensitivity, and 85.00% Matthew's correlation coefficient. The results confirm the efficiency of the proposed method, rendering it a generalizable and applicable technique in ophthalmology.

Assessing the efficacy of 2D and 3D CNN algorithms in OCT-based glaucoma detection

Glaucoma is a progressive neurodegenerative disease characterized by the gradual degeneration of retinal ganglion cells, leading to irreversible blindness worldwide. Therefore, timely and accurate diagnosis of glaucoma is crucial, enabling early intervention and facilitating effective disease management to mitigate further vision deterioration. The advent of optical coherence tomography (OCT) has marked a transformative era in ophthalmology, offering detailed visualization of the macula and optic nerve head (ONH) regions. In recent years, both 2D and 3D convolutional neural network (CNN) algorithms have been applied to OCT image analysis. While 2D CNNs rely on post-prediction aggregation of all B-scans within OCT volumes, 3D CNNs allow for direct glaucoma prediction from the OCT data. However, in the absence of extensively pre-trained 3D models, the comparative efficacy of 2D and 3D-CNN algorithms in detecting glaucoma from volumetric OCT images remains unclear. Therefore, this study explores the efficacy of glaucoma detection through volumetric OCT images using select state-of-the-art (SOTA) 2D-CNN models, 3D adaptations of these 2D-CNN models with specific weight transfer techniques, and a custom 5-layer 3D-CNN-Encoder algorithm. The performance across two distinct datasets is evaluated, each focusing on the macula and the ONH, to provide a comprehensive understanding of the models' capabilities in identifying glaucoma. Our findings demonstrate that the 2D-CNN algorithm consistently provided robust results compared to their 3D counterparts tested in this study for glaucoma detection, achieving AUC values of 0.960 and 0.943 for the macular and ONH OCT test images, respectively. Given the scarcity of pre-trained 3D models trained on extensive datasets, this comparative analysis underscores the overall utility of 2D and 3D-CNN algorithms in advancing glaucoma diagnostic systems in ophthalmology and highlights the potential of 2D algorithms for volumetric OCT image-based glaucoma detection.

Multimodal Deep Learning Classifier for Primary Open Angle Glaucoma Diagnosis Using Wide-Field Optic Nerve Head Cube Scans in Eyes With and Without High Myopia

PRCIS

An optical coherence tomography (OCT)-based multimodal deep learning (DL) classification model, including texture information, is introduced that outperforms single-modal models and multimodal models without texture information for glaucoma diagnosis in eyes with and without high myopia.

BACKGROUND/AIMS

To evaluate the diagnostic accuracy of a multimodal DL classifier using wide OCT optic nerve head cube scans in eyes with and without axial high myopia.

MATERIALS AND METHODS

Three hundred seventy-one primary open angle glaucoma (POAG) eyes and 86 healthy eyes, all without axial high myopia [axial length (AL) ≤ 26 mm] and 92 POAG eyes and 44 healthy eyes, all with axial high myopia (AL > 26 mm) were included. The multimodal DL classifier combined features of 3 individual VGG-16 models: (1) texture-based en face image, (2) retinal nerve fiber layer (RNFL) thickness map image, and (3) confocal scanning laser ophthalmoscope (cSLO) image. Age, AL, and disc area adjusted area under the receiver operating curves were used to compare model accuracy.

RESULTS

Adjusted area under the receiver operating curve for the multimodal DL model was 0.91 (95% CI = 0.87, 0.95). This value was significantly higher than the values of individual models [0.83 (0.79, 0.86) for texture-based en face image; 0.84 (0.81, 0.87) for RNFL thickness map; and 0.68 (0.61, 0.74) for cSLO image; all P ≤ 0.05]. Using only highly myopic eyes, the multimodal DL model showed significantly higher diagnostic accuracy [0.89 (0.86, 0.92)] compared with texture en face image [0.83 (0.78, 0.85)], RNFL [0.85 (0.81, 0.86)] and cSLO image models [0.69 (0.63, 0.76)] (all P ≤ 0.05).

CONCLUSIONS

Combining OCT-based RNFL thickness maps with texture-based en face images showed a better ability to discriminate between healthy and POAG than thickness maps alone, particularly in high axial myopic eyes.

Developments in Image Processing Using Deep Learning and Reinforcement Learning

The growth in the volume of data generated, consumed, and stored, which is estimated to exceed 180 zettabytes in 2025, represents a major challenge both for organizations and for society in general. In addition to being larger, datasets are increasingly complex, bringing new theoretical and computational challenges. Alongside this evolution, data science tools have exploded in popularity over the past two decades due to their myriad of applications when dealing with complex data, their high accuracy, flexible customization, and excellent adaptability. When it comes to images, data analysis presents additional challenges because as the quality of an image increases, which is desirable, so does the volume of data to be processed. Although classic machine learning (ML) techniques are still widely used in different research fields and industries, there has been great interest from the scientific community in the development of new artificial intelligence (AI) techniques. The resurgence of neural networks has boosted remarkable advances in areas such as the understanding and processing of images. In this study, we conducted a comprehensive survey regarding advances in AI design and the optimization solutions proposed to deal with image processing challenges. Despite the good results that have been achieved, there are still many challenges to face in this field of study. In this work, we discuss the main and more recent improvements, applications, and developments when targeting image processing applications, and we propose future research directions in this field of constant and fast evolution.

Donut: Augmentation Technique for Enhancing The Efficacy of Glaucoma Suspect Screening

Glaucoma is the second most common cause of blindness. A glaucoma suspect has risk factors that increase the possibility of developing glaucoma. Evaluating a patient with suspected glaucoma is challenging. The "donut method" was developed in this study as an augmentation technique for obtaining high-quality fundus images for training ConvNeXt-Small model. Fundus images from GlauCUTU-DATA, labelled by randomizing at least 3 well-trained ophthalmologists (4 well-trained ophthalmologists in case of no majority agreement) with a unanimous agreement (3/3) and majority agreement (2/3), were used in the experiment. The experimental results from the proposed method showed the training model with the "donut method" increased the sensitivity of glaucoma suspects from 52.94% to 70.59% for the 3/3 data and increased the sensitivity of glaucoma suspects from 37.78% to 42.22% for the 2/3 data. This method enhanced the efficacy of classifying glaucoma suspects in both equalizing sensitivity and specificity sufficiently. Furthermore, three well-trained ophthalmologists agreed that the GradCAM++ heatmaps obtained from the training model using the proposed method highlighted the clinical criteria.Clinical relevance- The donut method for augmentation fundus images focuses on the optic nerve head region for enhancing efficacy of glaucoma suspect screening, and uses Grad-CAM++ to highlight the clinical criteria.

Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP

Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a "black box" that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model's predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment.

Real-time closed-loop tissue-specific laser osteotomy using deep-learning-assisted optical coherence tomography

This article presents a real-time noninvasive method for detecting bone and bone marrow in laser osteotomy. This is the first optical coherence tomography (OCT) implementation as an online feedback system for laser osteotomy. A deep-learning model has been trained to identify tissue types during laser ablation with a test accuracy of 96.28 %. For the hole ablation experiments, the average maximum depth of perforation and volume loss was 0.216 mm and 0.077 mm³, respectively. The contactless nature of OCT with the reported performance shows that it is becoming more feasible to utilize it as a real-time feedback system for laser osteotomy.

Wavelet image scattering based glaucoma detection

BACKGROUND

The ever-growing need for cheap, simple, fast, and accurate healthcare solutions spurred a lot of research activities which are aimed at the reliable deployment of artificial intelligence in the medical fields. However, this has proved to be a daunting task especially when looking to make automated diagnoses using biomedical image data. Biomedical image data have complex patterns which human experts find very hard to comprehend. Against this backdrop, we applied a representation or feature learning algorithm: Invariant Scattering Convolution Network or Wavelet scattering Network to retinal fundus images and studied the the efficacy of the automatically extracted features therefrom for glaucoma diagnosis/detection. The influence of wavelet scattering network parameter settings as well as 2-D channel image type on the detection correctness is also examined. Our work is a distinct departure from the usual method where wavelet transform is applied to pre-processed retinal fundus images and handcrafted features are extracted from the decomposition results. Here, the RIM-ONE DL image dataset was fed into a wavelet scattering network developed in the Matlab environment to achieve a stage-wise decomposition process called wavelet scattering of the retinal fundus images thereby, automatically learning features from the images. These features were then used to build simple and computationally cheap classification algorithms.

RESULTS

Maximum detection correctness of 98% was achieved on the held-out test set. Detection correctness is highly sensitive to scattering network parameter setting and 2-D channel image type.

CONCLUSION

A superficial comparison of the classification results obtained from our work and those obtained using a convolutional neural network underscores the potentiality of the proposed method for glaucoma detection.

Luminosity rectified blind Richardson-Lucy deconvolution for single retinal image restoration

BACKGROUND AND OBJECTIVE

Due to imperfect imaging conditions, retinal images can be degraded by uneven/insufficient illumination, blurriness caused by optical aberrations and unintentional motions. Degraded images reduce the effectiveness of diagnosis by an ophthalmologist. To restore the image quality, in this research we propose the luminosity rectified Richardson-Lucy (LRRL) blind deconvolution framework for single retinal image restoration.

METHODS

We established an image formation model based on the double-pass fundus reflection feature and developed a differentiable non-convex cost function that jointly achieves illumination correction and blind deconvolution. To solve this non-convex optimization problem, we derived the closed-form expression of the gradients and used gradient descent with Nesterov-accelerated adaptive momentum estimation to accelerate the optimization, which is more efficient than the traditional half quadratic splitting method.

RESULTS

The LRRL was tested on 1719 images from three public databases. Four image quality matrixes including image definition, image sharpness, image entropy, and image multiscale contrast were used for objective assessments. The LRRL was compared against the state-of-the-art retinal image blind deconvolution methods.

CONCLUSIONS

Our LRRL corrects the problematic illumination and improves the clarity of the retinal image simultaneously, showing its superiority in terms of restoration quality and implementation efficiency. The MATLAB code is available on Github.

Glaucoma Detection and Classification Using Improved U-Net Deep Learning Model

Glaucoma is prominent in a variety of nations, with the United States and Europe being two of the most famous. Glaucoma now affects around 78 million people throughout the world (2020). By the year 2040, it is expected that there will be 111.8 million cases of glaucoma worldwide. In countries that are still building enough healthcare infrastructure to cope with glaucoma, the ailment is misdiagnosed nine times out of ten. To aid in the early diagnosis of glaucoma, the creation of a detection system is necessary. In this work, the researchers propose using a technology known as deep learning to identify and predict glaucoma before symptoms appear. The glaucoma dataset is used in this deep learning algorithm that has been proposed for analyzing glaucoma images. To get the required results when using deep learning principles for the job of segmenting the optic cup, pretrained transfer learning models are integrated with the U-Net architecture. For feature extraction, the DenseNet-201 deep convolution neural network (DCNN) is used. The DCNN approach is used to determine whether a person has glaucoma. The fundamental goal of this line of research is to recognize glaucoma in retinal fundus images, which will aid in assessing whether a patient has the condition. Because glaucoma can affect the model in both positive and negative ways, the model's outcome might be either positive or negative. Accuracy, precision, recall, specificity, the F-measure, and the F-score are some of the metrics used in the model evaluation process. An extra comparison study is performed as part of the process of establishing whether the suggested model is accurate. The findings are compared to convolution neural network classification methods based on deep learning. When used for training, the suggested model has an accuracy of 98.82 percent and an accuracy of 96.90 percent when used for testing. All assessments show that the new paradigm that has been proposed is more successful than the one that is currently in use.

Digital Advancements in Retinal Models of Care in the Post-COVID-19 Lockdown Era

The coronavirus disease-2019 (COVID-19) pandemic introduced unique barriers to retinal care including limited access to imaging modalities, ophthalmic clinicians, and direct medical interventions. These unprecedented barriers were met with the robust implementation of digital advances to aid in monitoring and efficiency of retinal care while taking into the account of public safety. Many of these innovations have been successful in maintaining efficiency and patient satisfaction and are likely to stay to help preserve vision in the future. In this article we highlight these advances implemented during the pandemic including telescreening triage, virtual retinal imaging clinics, at-home optical coherence tomography, mobile phone self-monitoring, and virtual reality monitoring technology. We also discuss advancing innovations including Internet of Things and Blockchain technology that will be critical for further implementation and security of these digital advancements.

Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation - A Review

Background

Globally, glaucoma is the second leading cause of blindness. Detecting glaucoma in the early stages is essential to avoid disease complications, which lead to blindness. Thus, computer-aided diagnosis systems are powerful tools to overcome the shortage of glaucoma screening programs.

Methods

A systematic search of public databases, including PubMed, Google Scholar, and other sources, was performed to identify relevant studies to overview the publicly available fundus image datasets used to train, validate, and test machine learning and deep learning methods. Additionally, existing machine learning and deep learning methods for optic cup and disc segmentation were surveyed and critically reviewed.

Results

Eight fundus images datasets were publicly available with 15,445 images labeled with glaucoma or non-glaucoma, and manually annotated optic disc and cup boundaries were found. Five metrics were identified for evaluating the developed models. Finally, three main deep learning architectural designs were commonly used for optic disc and optic cup segmentation.

Conclusion

We provided future research directions to formulate robust optic cup and disc segmentation systems. Deep learning can be utilized in clinical settings for this task. However, many challenges need to be addressed before using this strategy in clinical trials. Finally, two deep learning architectural designs have been widely adopted, such as U-net and its variants.

Segmentation and Classification of Glaucoma Using U-Net with Deep Learning Model

Glaucoma is the second most common cause for blindness around the world and the third most common in Europe and the USA. Around 78 million people are presently living with glaucoma (2020). It is expected that 111.8 million people will have glaucoma by the year 2040. 90% of glaucoma is undetected in developing nations. It is essential to develop a glaucoma detection system for early diagnosis. In this research, early prediction of glaucoma using deep learning technique is proposed. In this proposed deep learning model, the ORIGA dataset is used for the evaluation of glaucoma images. The U-Net architecture based on deep learning algorithm is implemented for optic cup segmentation and a pretrained transfer learning model; DenseNet-201 is used for feature extraction along with deep convolution neural network (DCNN). The DCNN approach is used for the classification, where the final results will be representing whether the glaucoma infected or not. The primary objective of this research is to detect the glaucoma using the retinal fundus images, which can be useful to determine if the patient was affected by glaucoma or not. The result of this model can be positive or negative based on the outcome detected as infected by glaucoma or not. The model is evaluated using parameters such as accuracy, precision, recall, specificity, and F-measure. Also, a comparative analysis is conducted for the validation of the model proposed. The output is compared to other current deep learning models used for CNN classification, such as VGG-19, Inception ResNet, ResNet 152v2, and DenseNet-169. The proposed model achieved 98.82% accuracy in training and 96.90% in testing. Overall, the performance of the proposed model is better in all the analysis.

Evaluations of Deep Learning Approaches for Glaucoma Screening Using Retinal Images from Mobile Device

Glaucoma is a silent disease that leads to vision loss or irreversible blindness. Current deep learning methods can help glaucoma screening by extending it to larger populations using retinal images. Low-cost lenses attached to mobile devices can increase the frequency of screening and alert patients earlier for a more thorough evaluation. This work explored and compared the performance of classification and segmentation methods for glaucoma screening with retinal images acquired by both retinography and mobile devices. The goal was to verify the results of these methods and see if similar results could be achieved using images captured by mobile devices. The used classification methods were the Xception, ResNet152 V2 and the Inception ResNet V2 models. The models’ activation maps were produced and analysed to support glaucoma classifier predictions. In clinical practice, glaucoma assessment is commonly based on the cup-to-disc ratio (CDR) criterion, a frequent indicator used by specialists. For this reason, additionally, the U-Net architecture was used with the Inception ResNet V2 and Inception V3 models as the backbone to segment and estimate CDR. For both tasks, the performance of the models reached close to that of state-of-the-art methods, and the classification method applied to a low-quality private dataset illustrates the advantage of using cheaper lenses.

Multithreshold Image Segmentation Technique Using Remora Optimization Algorithm for Diabetic Retinopathy Detection from Fundus Images

One of the most common complications of diabetes mellitus is diabetic retinopathy (DR), which produces lesions on the retina. A novel framework for DR detection and classification was proposed in this study. The proposed work includes four stages: pre-processing, segmentation, feature extraction, and classification. Initially, the image pre-processing is performed and after that, the Multi threshold-based Remora Optimization (MTRO) algorithm performs the vessel segmentation. The feature extraction and classification process are done by using a Region-based Convolution Neural Network (R-CNN) with Wild Geese Algorithm (WGA). Finally, the proposed R-CNN with WGA effectively classifies the different stages of DR including Non-DR, Proliferative DR, Severe, Moderate DR, Mild DR. The experimental images were collected from the DRIVE database, and the proposed framework exhibited superior DR detection performance. Compared to other existing methods like fully convolutional deep neural network (FCDNN), genetic-search feature selection (GSFS), Convolutional Neural Networks (CNN), and deep learning (DL) techniques, the proposed R-CNN with WGA provided 95.42% accuracy, 93.10% specificity, 93.20% sensitivity, and 98.28% F-score results.

Review of Machine Learning Applications Using Retinal Fundus Images

Automating screening and diagnosis in the medical field saves time and reduces the chances of misdiagnosis while saving on labor and cost for physicians. With the feasibility and development of deep learning methods, machines are now able to interpret complex features in medical data, which leads to rapid advancements in automation. Such efforts have been made in ophthalmology to analyze retinal images and build frameworks based on analysis for the identification of retinopathy and the assessment of its severity. This paper reviews recent state-of-the-art works utilizing the color fundus image taken from one of the imaging modalities used in ophthalmology. Specifically, the deep learning methods of automated screening and diagnosis for diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma are investigated. In addition, the machine learning techniques applied to the retinal vasculature extraction from the fundus image are covered. The challenges in developing these systems are also discussed.

Accuracy of Using Generative Adversarial Networks for Glaucoma Detection During the COVID-19 Pandemic: A Systematic Review and Bibliometric Analysis

Background

Glaucoma leads to irreversible blindness. Globally, it is the second most common retinal disease that leads to blindness, slightly less common than cataracts. Therefore, there is a great need to avoid the silent growth of this disease using recently developed generative adversarial networks (GANs).

Objective

This paper aims to introduce a GAN technology for the diagnosis of eye disorders, particularly glaucoma. This paper illustrates deep adversarial learning as a potential diagnostic tool and the challenges involved in its implementation. This study describes and analyzes many of the pitfalls and problems that researchers will need to overcome to implement this kind of technology.

Methods

To organize this review comprehensively, articles and reviews were collected using the following keywords: (“Glaucoma,” “optic disc,” “blood vessels”) and (“receptive field,” “loss function,” “GAN,” “Generative Adversarial Network,” “Deep learning,” “CNN,” “convolutional neural network” OR encoder). The records were identified from 5 highly reputed databases: IEEE Xplore, Web of Science, Scopus, ScienceDirect, and PubMed. These libraries broadly cover the technical and medical literature. Publications within the last 5 years, specifically 2015-2020, were included because the target GAN technique was invented only in 2014 and the publishing date of the collected papers was not earlier than 2016. Duplicate records were removed, and irrelevant titles and abstracts were excluded. In addition, we excluded papers that used optical coherence tomography and visual field images, except for those with 2D images. A large-scale systematic analysis was performed, and then a summarized taxonomy was generated. Furthermore, the results of the collected articles were summarized and a visual representation of the results was presented on a T-shaped matrix diagram. This study was conducted between March 2020 and November 2020.

Results

We found 59 articles after conducting a comprehensive survey of the literature. Among the 59 articles, 30 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences. The other 29 articles discuss the recent advances in GANs, do practical experiments, and contain analytical studies of retinal disease.

Conclusions

Recent deep learning techniques, namely GANs, have shown encouraging performance in retinal disease detection. Although this methodology involves an extensive computing budget and optimization process, it saturates the greedy nature of deep learning techniques by synthesizing images and solves major medical issues. This paper contributes to this research field by offering a thorough analysis of existing works, highlighting current limitations, and suggesting alternatives to support other researchers and participants in further improving and strengthening future work. Finally, new directions for this research have been identified.

Explainable Machine Learning Model for Glaucoma Diagnosis and Its Interpretation

The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination including an intraocular pressure (IOP) measurement, and fundus photography were provided for the feature selection process. Five selected features (variables) were used to develop a machine learning prediction model. The support vector machine, C5.0, random forest, and XGboost algorithms were tested for the prediction model. The performance of the prediction models was tested with 10-fold cross-validation. Statistical charts, such as gauge, radar, and Shapley Additive Explanations (SHAP), were used to explain the prediction case. All four models achieved similarly high diagnostic performance, with accuracy values ranging from 0.903 to 0.947. The XGboost model is the best model with an accuracy of 0.947, sensitivity of 0.941, specificity of 0.950, and AUC of 0.945. Three statistical charts were established to explain the prediction based on the characteristics of the XGboost model. Higher diagnostic performance was achieved with the XGboost model. These three statistical charts can help us understand why the machine learning model produces a specific prediction result. This may be the first attempt to apply "explainable artificial intelligence" to eye disease diagnosis.