Detection Of Age-related Macular Degeneration Research Articles

Early detection of age-related macular degeneration using Vision Transformer-based Architectures – A comparative study with offline metrics and data augmenting

Age-related macular degeneration (AMD) is one of the leading causes of vision loss in elderly adults around the world and is among the main visual impairments in Mexico. The difficulty of diagnosing AMD in its early stages motivates the use of advanced deep-learning methods that offer significant potential to improve diagnostic accuracy in retinal image analysis. In recent years, Transformer architectures for computer vision, such as Vision Transformer (ViT), Swin Transformer and BERT Pre-training of Image Transformers (BEiT) have provided a novel perspective for image analysis. This study presents a comparative analysis of these architectures, applied to AMD detection, focusing on each model's capability to classify the early stages of the disease. Although the small size of medical image datasets represented a challenge, our results suggest that ViT-based architectures and their derivatives achieve significant performance in AMD detection. BEiT is particularly notable for its consistently superior performance.

A deep learning LSTM-based approach for AMD classification using OCT images

Age-related macular degeneration (AMD) is an age-related, persistent, painless eye disease that impairs central vision. The central area (macula) of the retina, located at the back of the eye, sustains damage that is the cause of loss of vision. The early detection of AMD can increase the probability of treatment and prevent vision loss. The AMD can be classified into dry and wet AMD based on the absence of neovascularization. This study introduces a new methodology for the classification of AMD using optical coherence tomography (OCT) retinal images. The proposed methodology is based on three stages. The first stage is the data preparation stage for resizing and normalizing the used images. The second stage is the image processing stage for enhancing the image quality as contrast and resolution these enhancements have been checked by the weighted peak signal-to-noise ratio (WPSNR) methodology. The third stage is the deep feature extraction and classification stage, which consists of two sub-models. The first model is MobileNet V1 which has been used as a deep feature extractor. The second model is LSTM (long short-term memory), fed with deep features to classify the AMD stages. A multi-classification with six separate trials has been employed with the proposed methodology, and compared with other models like DenseNet201 and InceptionV3. The proposed model has been tested on a sample of benchmark data with 4005 grayscale images labeled into three classes. The proposed methodology has achieved an accuracy of 98.85%, a sensitivity of 99.09%, and a specificity of 99.1%. To ensure the effectiveness of the proposed methodology, a comparative analysis has been established with previous approaches in the related field, and the results demonstrated the superiority of the proposed system in AMD multi-classification.

A Comprehensive Review of AI Diagnosis Strategies for Age-Related Macular Degeneration (AMD).

The rapid advancement of computational infrastructure has led to unprecedented growth in machine learning, deep learning, and computer vision, fundamentally transforming the analysis of retinal images. By utilizing a wide array of visual cues extracted from retinal fundus images, sophisticated artificial intelligence models have been developed to diagnose various retinal disorders. This paper concentrates on the detection of Age-Related Macular Degeneration (AMD), a significant retinal condition, by offering an exhaustive examination of recent machine learning and deep learning methodologies. Additionally, it discusses potential obstacles and constraints associated with implementing this technology in the field of ophthalmology. Through a systematic review, this research aims to assess the efficacy of machine learning and deep learning techniques in discerning AMD from different modalities as they have shown promise in the field of AMD and retinal disorders diagnosis. Organized around prevalent datasets and imaging techniques, the paper initially outlines assessment criteria, image preprocessing methodologies, and learning frameworks before conducting a thorough investigation of diverse approaches for AMD detection. Drawing insights from the analysis of more than 30 selected studies, the conclusion underscores current research trajectories, major challenges, and future prospects in AMD diagnosis, providing a valuable resource for both scholars and practitioners in the domain.

Stitched vision transformer for age-related macular degeneration detection using retinal optical coherence tomography images.

Age-related macular degeneration (AMD) is an eye disease that leads to the deterioration of the central vision area of the eye and can gradually result in vision loss in elderly individuals. Early identification of this disease can significantly impact patient treatment outcomes. Furthermore, given the increasing elderly population globally, the importance of automated methods for rapidly monitoring at-risk individuals and accurately diagnosing AMD is growing daily. One standard method for diagnosing AMD is using optical coherence tomography (OCT) images as a non-invasive imaging technology. In recent years, numerous deep neural networks have been proposed for the classification of OCT images. Utilizing pre-trained neural networks can speed up model deployment in related tasks without compromising accuracy. However, most previous methods overlook the feasibility of leveraging pre-existing trained networks to search for an optimal architecture for AMD staging on a new target dataset. In this study, our objective was to achieve an optimal architecture in the efficiency-accuracy trade-off for classifying retinal OCT images. To this end, we employed pre-trained medical vision transformer (MedViT) models. MedViT combines convolutional and transformer neural networks, explicitly designed for medical image classification. Our approach involved pre-training two distinct MedViT models on a source dataset with labels identical to those in the target dataset. This pre-training was conducted in a supervised manner. Subsequently, we evaluated the performance of the pre-trained MedViT models for classifying retinal OCT images from the target Noor Eye Hospital (NEH) dataset into the normal, drusen, and choroidal neovascularization (CNV) classes in zero-shot settings and through five-fold cross-validation. Then, we proposed a stitching approach to search for an optimal model from two MedViT family models. The proposed stitching method is an efficient architecture search algorithm known as stitchable neural networks. Stitchable neural networks create a candidate model in search space for each pair of stitchable layers by inserting a linear layer between them. A pair of stitchable layers consists of layers, each selected from one input model. While stitchable neural networks had previously been tested on more extensive and general datasets, this study demonstrated that stitching networks could also be helpful in smaller medical datasets. The results of this approach indicate that when pre-trained models were available for OCT images from another dataset, it was possible to achieve a model in 100 epochs with an accuracy of over 94.9% in classifying images from the NEH dataset. The results of this study demonstrate the efficacy of stitchable neural networks as a fine-tuning method for OCT image classification. This approach not only leads to higher accuracy but also considers architecture optimization at a reasonable computational cost.

Age-Related Macular Degeneration Detection in Retinal Fundus Images by a Deep Convolutional Neural Network

Computer-based pre-diagnosis of diseases through medical imaging is a task worked on for many years. The so-called fundus images stand out since they do not have uniform illumination and are highly sensitive to noise. One of the diseases that can be pre-diagnosed through fundus images is age-related macular degeneration, which initially manifests as the appearance of lesions called drusen. Several ways of pre-diagnosing macular degeneration have been proposed, methods based entirely on the segmentation of drusen with prior image processing have been designed and applied, and methods based on image pre-processing and subsequent conversion to feature vectors, or patterns, to be classified by a Machine-Learning model have also been developed. Finally, in recent years, the use of Deep-Learning models, particularly Convolutional Networks, has been proposed and used in classification problems where the data are only images. The latter has allowed the so-called transfer learning, which consists of using the learning achieved in the solution of one problem to solve another. In this paper, we propose the use of transfer learning through the Xception Deep Convolutional Neural Network to detect age-related macular degeneration in fundus images. The performance of the Xception model was compared against six other state-of-the-art models with a dataset created from images available in public and private datasets, which were divided into training/validation and test; with the training/validation set, the training was made using 10-fold cross-validation. The results show that the Xception neural network obtained a validation accuracy that surpasses other models, such as the VGG-16 or VGG-19 networks, and had an accuracy higher than 80% in the test set. We consider that the contributions of this work include the use of a Convolutional Neural Network model for the detection of age-related macular degeneration through the classification of fundus images in those affected by AMD (drusen) and the images of healthy patients. The performance of this model is compared against other methods featured in the state-of-the-art approaches, and the best model is tested on a test set outside the training and validation set.

The Association between Diabetic Retinopathy and Macular Degeneration: A Nationwide Population-Based Study.

Age-related macular degeneration (AMD), particularly its exudative form, is a primary cause of vision impairment in older adults. As diabetes becomes increasingly prevalent in aging, it is crucial to explore the potential relationship between diabetic retinopathy (DR) and AMD. This study aimed to assess the risk of developing overall, non-exudative, and exudative AMD in individuals with DR compared to those without retinopathy (non-DR) based on a nationwide population study in Taiwan. A retrospective cohort study was conducted using the Taiwan National Health Insurance Database (NHIRD) (2000-2013). A total of 3413 patients were placed in the study group (DR) and 13,652 in the control group (non-DR) for analysis. Kaplan-Meier analysis and the Cox proportional hazards model were used to calculate the hazard ratios (HRs) and adjusted hazard ratios (aHRs) for the development of AMD, adjusting for confounding factors, such as age, sex, and comorbid conditions. Kaplan-Meier survival analysis indicated a significantly higher cumulative incidence of AMD in the DR group compared to the non-DR group (log-rank test, p < 0.001). Adjusted analyses revealed that individuals with DR faced a greater risk of overall AMD, with an aHR of 3.50 (95% CI = 3.10-3.95). For senile (unspecified) AMD, the aHR was 3.45 (95% CI = 3.04-3.92); for non-exudative senile AMD, it was 2.92 (95% CI = 2.08-4.09); and for exudative AMD, the aHR was 3.92 (95% CI = 2.51-6.14). DR is a significant risk factor for both overall, senile, exudative, and non-exudative AMD, even after adjusting for demographic and comorbid conditions. DR patients tend to have a higher prevalence of vascular comorbidities; however, our findings indicate that the ocular pathologies inherent to DR might have a more significant impact on the progression to AMD. Early detection and appropriate treatment of AMD is critically important among DR patients.

Enhancing Readability and Detection of Age-Related Macular Degeneration Using Optical Coherence Tomography Imaging: An AI Approach.

Artificial intelligence has been used effectively in medical diagnosis. The objective of this project is to examine the application of a collective AI model using weighted fusion of predicted probabilities from different AI architectures to diagnose various retinal conditions based on optical coherence tomography (OCT). A publicly available Noor dataset, comprising 16,822, images from 554 retinal OCT scans of 441 patients, was used to predict a diverse spectrum of age-related macular degeneration (AMD) stages: normal, drusen, or choroidal neovascularization. These predictions were compared with predictions from ResNet, EfficientNet, and Attention models, respectively, using precision, recall, F1 score, and confusion matric and receiver operating characteristics curves. Our collective model demonstrated superior accuracy in classifying AMD compared to individual ResNet, EfficientNet, and Attention models, showcasing the effectiveness of using trainable weights in the ensemble fusion process, where these weights dynamically adapt during training rather than being fixed values. Specifically, our ensemble model achieved an accuracy of 91.88%, precision of 92.54%, recall of 92.01%, and F1 score of 92.03%, outperforming individual models. Our model also highlights the refinement process undertaken through a thorough examination of initially misclassified cases, leading to significant improvements in the model's accuracy rate to 97%. This study also underscores the potential of AI as a valuable tool in ophthalmology. The proposed ensemble model, combining different mechanisms highlights the benefits of model fusion for complex medical image analysis.

Using the Amsler Grid Test for Age-Related Macular Degeneration Screening.

To evaluate the use of the Amsler grid test (AGT) in screening for age-related macular degeneration (AMD), one of the most common causes of blindness, in primary healthcare settings. The AGT was applied to 700 eyes of 355 people aged 50 and over who applied to a family health center in Ankara and had no eye complaints. The test was considered positive if the lines on the AGT card were seen as broken or curved, there was a difference in shape or size between the squares, or a color change or blurring was described in any area. An ophthalmologist was consulted if the AGT was positive in one or both eyes. Patients considered suitable by ophthalmologists were evaluated with optical coherence tomography. AGT results were compared with ophthalmologist examination and tomography findings in terms of AMD detection. The AGT was positive in 97 (13.9%) and negative in 603 (86.1%) out of 700 eyes included in the study. A total of 184 eyes, 79 with a positive AGT and 105 eyes with a negative test, were evaluated by an ophthalmologist. As a result of examinations and tests performed by ophthalmologists, AMD was detected in a total of 67 eyes: 42 of 79 eyes with positive AGT and 25 of 105 eyes with negative AGT but referred to an ophthalmologist for different reasons. In our study, the AGT had 62.7% sensitivity and 68.4% specificity. The AGT is an inexpensive and easily applicable test. Although moderate sensitivity and specificity were found in our study; further studies are needed to evaluate the suitability of its use for AMD screening in primary care with limited facilities.

Interpretable Detection of Diabetic Retinopathy, Retinal Vein Occlusion, Age-Related Macular Degeneration, and Other Fundus Conditions.

Diabetic retinopathy (DR), retinal vein occlusion (RVO), and age-related macular degeneration (AMD) pose significant global health challenges, often resulting in vision impairment and blindness. Automatic detection of these conditions is crucial, particularly in underserved rural areas with limited access to ophthalmic services. Despite remarkable advancements in artificial intelligence, especially convolutional neural networks (CNNs), their complexity can make interpretation difficult. In this study, we curated a dataset consisting of 15,089 color fundus photographs (CFPs) obtained from 8110 patients who underwent fundus fluorescein angiography (FFA) examination. The primary objective was to construct integrated models that merge CNNs with an attention mechanism. These models were designed for a hierarchical multilabel classification task, focusing on the detection of DR, RVO, AMD, and other fundus conditions. Furthermore, our approach extended to the detailed classification of DR, RVO, and AMD according to their respective subclasses. We employed a methodology that entails the translation of diagnostic information obtained from FFA results into CFPs. Our investigation focused on evaluating the models' ability to achieve precise diagnoses solely based on CFPs. Remarkably, our models showcased improvements across diverse fundus conditions, with the ConvNeXt-base + attention model standing out for its exceptional performance. The ConvNeXt-base + attention model achieved remarkable metrics, including an area under the receiver operating characteristic curve (AUC) of 0.943, a referable F1 score of 0.870, and a Cohen's kappa of 0.778 for DR detection. For RVO, it attained an AUC of 0.960, a referable F1 score of 0.854, and a Cohen's kappa of 0.819. Furthermore, in AMD detection, the model achieved an AUC of 0.959, an F1 score of 0.727, and a Cohen's kappa of 0.686. Impressively, the model demonstrated proficiency in subclassifying RVO and AMD, showcasing commendable sensitivity and specificity. Moreover, our models enhanced interpretability by visualizing attention weights on fundus images, aiding in the identification of disease findings. These outcomes underscore the substantial impact of our models in advancing the detection of DR, RVO, and AMD, offering the potential for improved patient outcomes and positively influencing the healthcare landscape.

Survey on age-related macular degeneration detection in OCT image

Age-related Macular Degeneration (AMD) is the most common eye disease that causes visual impairment in elder people. Prevalently, AMD is detected by Spectral Domain Optical Coherence Tomography (SD-OCT) for diagnosis and monitoring purposes. In this work, 50 papers are reviewed to examine various approaches and their performance metrics. This paper reviewed various existing works related to AMD detection using different imaging modalities for quality images with high resolution. The investigation of case studies is analyzed on the basis of data collected from various patients undergoing several treatments and scans obtained from various imaging modalities. Furthermore, the analysis extends to the works that used different AI techniques, such as Deep Learning (DL), Machine Learning (ML), and Unsupervised Framework, for the detection of AMD-related diseases. Also, the analysis of different performance measures is done that shows the variations in terms of performance metrics such as accuracy, sensitivity, specificity, and so on. The outcome of this deep analysis shows that the system with the DL model reaches its utmost performance in AMD detection. Finally, gaps and challenges that are still lagging with this research area are summarized, which motivates the researchers to take away the work in an effective way.

Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5)

Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.

Telehealth improves follow-up and monitoring of age-related macular degeneration during the COVID-19 pandemic.

To prevent vision loss, it is important to monitor patients with age-related macular degeneration (AMD) for the development of choroidal neovascularization. The coronavirus disease 2019 (COVID-19) pandemic caused many patients to miss or delay visits. To offset those gaps in care, providers utilized telehealth (TH) to evaluate patients for symptoms of disease progression and provide health education on the importance of continuous monitoring. This study evaluates the impact of TH encounters on the rate of return for recommended in-person examinations for 1103 patients with non-neovascular (dry) AMD seen in an outpatient ophthalmology clinic in 2019 and due for return evaluation after the outbreak of COVID-19 in 2020. Logistic regression analysis was used to identify demographic, clinical, and sociomedical factors associated with TH utilization and in-person return. 422 patients (38%) utilized TH during the study period. Patients who completed a TH encounter were more likely to return for an in-person examination as compared with those who did not receive TH (OR: 1.8, CI 95%: 1.4-2.3, P < 0.001). Completing a TH visit was associated with the detection of new wet AMD (OR: 3.3, 95% CI 1.04-10.6, P = 0.043), as well as with an earlier return for those patients who were found to have disease progression (62 ± 54days vs. 100 ± 57days, P = 0.049). Completing a TH visit increased the rate at which patients with dry AMD returned for recommended in-person eye examinations. In many cases, this permitted the earlier detection of wet AMD, which is linked with achieving better outcomes.

Automatic detection and differential diagnosis of age-related macular degeneration from color fundus photographs using deep learning with hierarchical vision transformer

Age-related macular degeneration (AMD) is a leading cause of vision loss in the elderly, highlighting the need for early and accurate detection. In this study, we proposed DeepDrAMD, a hierarchical vision transformer-based deep learning model that integrates data augmentation techniques and SwinTransformer, to detect AMD and distinguish between different subtypes using color fundus photographs (CFPs). The DeepDrAMD was trained on the in-house WMUEH training set and achieved high performance in AMD detection with an AUC of 98.76% in the WMUEH testing set and 96.47% in the independent external Ichallenge-AMD cohort. Furthermore, the DeepDrAMD effectively classified dryAMD and wetAMD, achieving AUCs of 93.46% and 91.55%, respectively, in the WMUEH cohort and another independent external ODIR cohort. Notably, DeepDrAMD excelled at distinguishing between wetAMD subtypes, achieving an AUC of 99.36% in the WMUEH cohort. Comparative analysis revealed that the DeepDrAMD outperformed conventional deep-learning models and expert-level diagnosis. The cost-benefit analysis demonstrated that the DeepDrAMD offers substantial cost savings and efficiency improvements compared to manual reading approaches. Overall, the DeepDrAMD represents a significant advancement in AMD detection and differential diagnosis using CFPs, and has the potential to assist healthcare professionals in informed decision-making, early intervention, and treatment optimization.

The Double Layer Sign Is Highly Predictive of Progression to Exudation in Age-Related Macular Degeneration

The presences of a double layer sign (DLS) and a shallow irregular retinal pigment epithelium (RPE) elevation (SIRE) were investigated using spectral domain-OCT (SD-OCT) imaging to determine their ability to predict progression to exudative macular neovascularization (eMNV) in the unaffected fellow eyes (study eye) of participants with age-related macular degeneration (AMD) with newly diagnosed unilateral eMNV. Retrospective, reanalysis of SD-OCT scans of study eyes from the Early Detection of Neovascular AMD (EDNA) study with 3 years follow-up (FU). The EDNA study repository of SD-OCT scans was assessed for inclusion. Cases with incomplete data sets, low quality scans, or exhibiting other pathology were excluded, which resulted in 459 eligible cases. Spectral domain-OCT volume scans of study eyes were graded for irregular elevation of the RPE (IE), with length, and height measurements made on the most affected B-scan. Eyes with heterogeneous reflectivity within the IE were classified as exhibiting the DLS. Eyes with DLS where the length of separation between RPE and Bruch's membrane was ≥ 1000 μm in length and < 100 μm in height were subclassified as SIRE. Hazard of progression to eMNV for DLS and SIRE. Of the 459 eyes, 268 had IE, of which 101 were DLS-like and 51 also fulfilled criteria for SIRE. Over the 3 years FU period, 104 (23%) eyes progressed to eMNV. After an FU of 18 months, a significantly higher proportion of study eyes (P < 0.001) with IE, DLS, and SIRE developed eMNV compared with those without these features (IE: 17% vs. no IE 6.3%; DLS: 23% vs. no DLS 9.9%; SIRE: 22% vs. no SIRE 11%). In the adjusted Cox regression models, a significantly greater hazard of progression (P < 0.001) was associated with the presence of IE (adjusted hazard ratio [HR], 3.01; 95% confidence interval [CI], 1.88-4.82), DLS (adjusted HR, 3.41; 95% CI, 2.26-5.14), or SIRE (adjusted HR, 2.83; 95% CI, 1.68-4.75). The DLS is a highly sensitive predictor of progression to eMNV, and the use of SIRE does not improve predictability. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Deep Learning Approach for Age-related Macular Degeneration Detection Using Retinal Images: Efficacy Evaluation of Different Deep Learning Models

Age-related macular degeneration (AMD) is a typical fundus disease that affects the central vision of elderly people. It causes difficulties in everyday activities such as reading and recognizing faces. AMD can progress slowly or rapidly, and it leads to severe vision loss if left untreated. Therefore, early detection and diagnosis of AMD are crucial to prevent or delay vision impairment in the elderly. To handle this requirement, researchers are exploring deep learning-based models as an AI tool to assist ophthalmologist in AMD diagnosis. However, conducting an appropriate deep learning model for the AMD classification is challenging and cost-intensive. This research aims to evaluate the efficacy of various deep learning models for obtaining the best performance results when identifying AMD disease using retinal images. To meet this objective, the retinal images from the Department of Ophthalmology, the King Chulalongkorn Memorial Hospital, Thailand were collected for transfer learning and other publicly available datasets for testing. Then, seven deep learning models VGG19, Xception, DenseNet201, EfficientNetB7, InceptionV3, NASNetLarge, and ResNet152V2 were chosen to training for the 2-labels (Normal vs. AMD) and the 3-labels (Normal vs. Dry AMD vs. Wet AMD) classifications. From the experimental results, the DenseNet201 model with Dense block in its structure showed the best efficacy in both 2-labels and 3-labels AMD classifications since its performance always include in the Top-3 models accuracy and generalization performance measured by total accuracy and total F1-Score, respectively. Furthermore, the accuracy performance of deep learning models in Top-3 are comparable with the performance of retinal specialist. These results contribute consolidated knowledge to the process of implementation effective deep learning as production that detects AMD automatically in the clinical and enhance the quality of healthcare service.

Detection and diagnosis of age-related macular degeneration using recurrent neural network with cloud architecture and internet of things

Age-Related Macular Degeneration is a progressive, irreversible eye condition that causes vision loss and impairs quality of life. The lost potential of the optic nerve cannot be regained, but a patient with Age-Related Macular Degeneration must have early diagnosis and treatment in order to prevent visual loss. The diagnosis of Age-Related Macular Degeneration is based on visual field loss tests, a patient’s medical history, intraocular pressure, and a physical fundus evaluation. Age-Related Macular Degeneration must be diagnosed early in order to avoid irreparable structural damage and vision loss. The objective of the proposed study is to develop a new optimization-driven strategy-based recurrent neural network using the Internet of Things for the identification of age-related macular degeneration. The Recurrent Neural Network (RNN) classifier is trained using the Particle Swarm Optimization (PSO) technique included into the RNN-IoMT. Initially, the input picture is sent through pre-processing in order to remove noise and artefacts. The generated preprocessed picture is simultaneously sent to optical disc detection and blood vessel detection. In addition, picture level characteristics are extracted from the image that has been preprocessed. Finally, the image-level, optic disc-level, and blood vessel-level features are retrieved and compiled into a feature vector. The acquired feature vector is fed into the RNN classifier, with the suggested PSO used to train the RNN for Age-Related Macular Degeneration detection via the Internet of Medical Things. The suggested PSO+RNN exhibits better performance with enhanced precision of 97.194%, sensitivity of 97.184%, and specificity of 97.2044%, respectively.

Understanding and interpreting CNN's decision in optical coherence tomography-based AMD detection.

Automated assessment of age-related macular degeneration (AMD) using optical coherence tomography (OCT) has gained significant research attention in recent years. Though a list of convolutional neural network (CNN)-based methods has been proposed recently, methods that uncover the decision-making process of CNNs or critically interpret CNNs' decisions in the context are scant. This study aims to bridge this research gap. We independently trained several state-of-the-art CNN models, namely, VGG16, VGG19, Xception, ResNet50, InceptionResNetV2 for AMD detection and applied CNN visualization techniques, namely, Grad-CAM, Grad-CAM++, Score CAM, Faster Score CAM to highlight the regions of interest utilized by the CNNs in the context. Retinal layer segmentation methods were also developed to explore how the CNN regions of interest related to the layers of the retinal structure. Extensive experiments involving 2130 SD-OCT scans collected from Duke University were performed. Experimental analysis shows that Outer Nuclear Layer to Inner Segment Myeloid (ONL-ISM) influences the AMD detection decision heavily as evident from the normalized intersection (NI) scores. For AMD cases the obtained average NI scores were respectively 13.13%, 17.2%, 9.7%, 10.95%, and 11.31% for VGG16, VGG19, ResNet50, Xception, and Inception ResNet V2, whereas, for normal cases, these values were respectively 21.7%, 21.3%, 16.85%, 10.175% and 16%. Critical analysis reveals that the ONL-ISM is the most contributing layer in determining AMD, followed by Nerve Fiber Layer to Inner Plexiform Layer (NFL-IPL).

Deep Learning Applications to Classification and Detection of Age-Related Macular Degeneration on Optical Coherence Tomography Imaging: A Review.

Age-related macular degeneration (AMD) is one of the leading causes of blindness in the elderly, more commonly in developed countries. Optical coherence tomography (OCT) is a non-invasive imaging device widely used for the diagnosis and management of AMD. Deep learning (DL) uses multilayered artificial neural networks (NN) for feature extraction, and is the cutting-edge technique for medical image analysis for diagnostic and prognostication purposes. Application of DL models to OCT image analysis has garnered significant interest in recent years. In this review, we aimed to summarize studies focusing on DL models used in classification and detection of AMD. Additionally, we provide a brief introduction to other DL applications in AMD, such as segmentation, prediction/prognostication, and models trained on multimodal imaging.

Classification Maps: A New Mathematical Tool Supporting the Diagnosis of Age-Related Macular Degeneration.

A new diagnostic graphical tool-classification maps-supporting the detection of Age-Related Macular Degeneration (AMD) has been constructed. The classification maps are constructed using the ordinal regression model. In the ordinal regression model, the ordinal variable (the dependent variable) is the degree of the advancement of AMD. The other variables, such as CRT (Central Retinal Thickness), GCC (Ganglion Cell Complex), MPOD (Macular Pigment Optical Density), ETDRS (Early Treatment Diabetic Retinopathy Study), Snellen and Age have also been used in the analysis and are represented on the axes of the maps. Here, 132 eyes were examined and classified to the AMD advancement level according to the four-point Age-Related Eye Disease Scale (AREDS): AREDS 1, AREDS 2, AREDS 3 and AREDS 4. These data were used for the creation of two-dimensional classification maps for each of the four stages of AMD. The maps allow us to perform the classification of the patient's eyes to particular stages of AMD. The pairs of the variables represented on the axes of the maps can be treated as diagnostic identifiers necessary for the classification to particular stages of AMD.

Synthetic artificial intelligence using generative adversarial network for retinal imaging in detection of age-related macular degeneration.

Age-related macular degeneration (AMD) is one of the leading causes of vision impairment globally and early detection is crucial to prevent vision loss. However, the screening of AMD is resource dependent and demands experienced healthcare providers. Recently, deep learning (DL) systems have shown the potential for effective detection of various eye diseases from retinal fundus images, but the development of such robust systems requires a large amount of datasets, which could be limited by prevalence of the disease and privacy of patient. As in the case of AMD, the advanced phenotype is often scarce for conducting DL analysis, which may be tackled via generating synthetic images using Generative Adversarial Networks (GANs). This study aims to develop GAN-synthesized fundus photos with AMD lesions, and to assess the realness of these images with an objective scale. To build our GAN models, a total of 125,012 fundus photos were used from a real-world non-AMD phenotypical dataset. StyleGAN2 and human-in-the-loop (HITL) method were then applied to synthesize fundus images with AMD features. To objectively assess the quality of the synthesized images, we proposed a novel realness scale based on the frequency of the broken vessels observed in the fundus photos. Four residents conducted two rounds of gradings on 300 images to distinguish real from synthetic images, based on their subjective impression and the objective scale respectively. The introduction of HITL training increased the percentage of synthetic images with AMD lesions, despite the limited number of AMD images in the initial training dataset. Qualitatively, the synthesized images have been proven to be robust in that our residents had limited ability to distinguish real from synthetic ones, as evidenced by an overall accuracy of 0.66 (95% CI: 0.61-0.66) and Cohen's kappa of 0.320. For the non-referable AMD classes (no or early AMD), the accuracy was only 0.51. With the objective scale, the overall accuracy improved to 0.72. In conclusion, GAN models built with HITL training are capable of producing realistic-looking fundus images that could fool human experts, while our objective realness scale based on broken vessels can help identifying the synthetic fundus photos.