Fundus Image Analysis Research Articles

Bibliometric analysis of research on the application of deep learning to ophthalmology.

Recently, deep learning has become a popular area of research, and has revolutionized the diagnosis and prediction of ocular diseases, especially fundus diseases. This study aimed to conduct a bibliometric analysis of deep learning in the field of ophthalmology to describe international research trends and examine the current research directions. This cross-sectional bibliometric analysis examined the development of research on deep learning in the field of ophthalmology and its sub-topics from 2015 to 2024. Visualization of similarities (VOS)-viewer was used to analyze and evaluate 3,055 articles. Data from the articles were collected on a specific date (September 11, 2024) and downloaded from the Web of Science Core Collection (WOSCC) in plain-text format. A total of 3,055 relevant articles on the WOSCC published from 2015 to 2024 were included in this analysis. The first article on the application of deep learning to ophthalmology was published in 2015, and the number of articles on the subject has grown significantly since 2019. China was the most productive country (n=1,187), followed by the United States (n=673). Sun Yat-sen University was the institution with the most publications. Cheng and Bogunovic were the most frequently published authors. The following four different clusters were identified based on a co-occurrence cluster analysis of high-frequency keywords: (I) deep learning for the segmentation and feature extraction of ophthalmic images; (II) deep learning for the automatic detection and classification of ophthalmic images; (III) application of deep learning to ophthalmic imaging techniques; and (IV) deep learning for the diagnosis and management of ophthalmic diseases. The analysis of fundus images and the clinical application of deep learning techniques have emerged as prominent research areas in the field of ophthalmology. The substantial increase in publications and citations signifies the expanding impact and global collaboration in the application of deep learning research to ophthalmology. By identifying four distinct clusters representing sub-topics in deep learning ophthalmology research, this study contributes to the understanding of current trends and potential future advancements in the field.

Формирование датасета для нейросетевой модели распознавания офтальмологической патологии на изображениях глазного дна.

Introduction. In ophthalmological practice, the use of digital diagnostic devices has allowed us to accumulate a large database of medical images, and machine learning algorithms make it possible to use this data to create automated solutions that increase the speed, efficiency and quality of screening studies. Materials and methods. In this study, data collection and the formation of a dataset of digital images of the fundus were carried out from open cloud databases for storing and processing data Kaggle, Mendeley Data, Figshare. All images were depersonalized and pseudonymized in accordance with the Federal Law of July 27, 2006 N 152-FZ "On Personal Data" and GOST R 55036-2012 / ISO / TS 25237: 2008. Results. The collected dataset included 1765 digital fundus images measuring 640 × 480 and 2048 × 2048 pixels and was renamed the final dataset "OcuDate". The images were annotated by quality classes and a data preprocessing tool was developed, which will subsequently allow training the neural network model. Conclusions. The obtained data can be integrated into the fundus image analysis and processing system when creating an expert system for supporting clinical decision-making by ophthalmologists.

Development and research status of intelligent ophthalmology in China.

This paper analyzes the current status, technological developments, academic exchange platforms, and future challenges and solutions in the field of intelligent ophthalmology (IO) in China. In terms of technology, significant progress has been made in various areas, including diabetic retinopathy, fundus image analysis, quality assessment of medical artificial intelligence products, clinical research methods, technical evaluation, and industry standards. Researchers continually enhance the safety and standardization of IO technology by formulating a series of clinical application guidelines and standards. The establishment of domestic and international academic exchange platforms provides extensive collaboration opportunities for professionals in various fields, and various academic journals serve as publication platforms for IO research. However, challenges such as technological innovation, data privacy and security, lagging regulations, and talent shortages still pose obstacles to future development. To address these issues, future efforts should focus on strengthening technological research and development, regulatory framework construction, talent cultivation, and increasing patient awareness and acceptance of new technologies. By comprehensively addressing these challenges, IO in China is poised to further lead the industry's development on a global scale, bringing more innovation and convenience to the field of ophthalmic healthcare.

Effective automatic classification methods via deep learning for myopic maculopathy.

Pathologic myopia (PM) associated with myopic maculopathy (MM) is a significant cause of visual impairment, especially in East Asia, where its prevalence has surged. Early detection and accurate classification of myopia-related fundus lesions are critical for managing PM. Traditional clinical analysis of fundus images is time-consuming and dependent on specialist expertise, driving the need for automated, accurate diagnostic tools. This study developed a deep learning-based system for classifying five types of MM using color fundus photographs. Five architectures-ResNet50, EfficientNet-B0, Vision Transformer (ViT), Contrastive Language-Image Pre-Training (CLIP), and RETFound-were utilized. An ensemble learning approach with weighted voting was employed to enhance model performance. The models were trained on a dataset of 2,159 annotated images from Shenzhen Eye Hospital, with performance evaluated using accuracy, sensitivity, specificity, F1-Score, Cohen's Kappa, and area under the receiver operating characteristic curve (AUC). The ensemble model achieved superior performance across all metrics, with an accuracy of 95.4% (95% CI: 93.0-97.0%), sensitivity of 95.4% (95% CI: 86.8-97.5%), specificity of 98.9% (95% CI: 97.1-99.5%), F1-Score of 95.3% (95% CI: 93.2-97.2%), Kappa value of 0.976 (95% CI: 0.957-0.989), and AUC of 0.995 (95% CI: 0.992-0.998). The voting ensemble method demonstrated robustness and high generalization ability in classifying complex lesions, outperforming individual models. The ensemble deep learning system significantly enhances the accuracy and reliability of MM classification. This system holds potential for assisting ophthalmologists in early detection and precise diagnosis, thereby improving patient outcomes. Future work could focus on expanding the dataset, incorporating image quality assessment, and optimizing the ensemble algorithm for better efficiency and broader applicability.

Smartphone Aided Funduscopy in Albino Rabbits

Aims: The methodology, utility and clinical feasibility of using a smartphone camera to obtain images of ocular fundus of albino rabbits with ocular hypertension and normotension were studied. A comparative analysis of fundus images obtained from two popularly used smartphone models, android and iOS device was performed on 36 adult albino rabbits. Study Design: A cross-sectional study involving two cohorts of ocular hypertensive and normotensive albino rabbits. Place and Duration of Study: Department of Veterinary Surgery and Radiology, College of Veterinary and Animal Sciences, Mannuthy for an eight-week period (2023). Methodology: A total of 36 adult albino rabbits (18 males and 18 females; age range 6- 8 months of age) with ocular normotensive eyes and unilateral ocular hypertension-induced models were used. The conscious animals were gently restrained in an acrylic restrainer. Instillation of topical mydriatic solution (tropicamide 0.8% and phenylephrine 5%) facilitated visual examination and enhanced field of view along with auxiliary condensing lenses of 20 and 40 Diopters. A comparison of fundus images obtained from two popularly used smartphone models, android and iOS devices was performed on 36 adult albino rabbits. Results: Fundus images comprising the optic nerve head and peripapillary retina were obtained with adequate spatial resolution and detail. The variation between optic disc of ocular hypertensive eye revealed mild edema and cupping of optic disc. Normal merangiotic retina and optic disc were clearly obtained in normotensive rabbit eyes. The iOS device used in this case yielded better images in resolution and field of view compared to the android version used in this case. Conclusion: Smart phone funduscopy offered good detail in contrast and resolution even in amelanotic eyes of albino rabbits using inbuilt technology without the need for an external adapter or sophisticated additional software. It is an animal-friendly futuristic solution for digital documentation, telemedicine, teaching and clinical prognosis formulation.

Redefining retinal vessel segmentation: empowering advanced fundus image analysis with the potential of GANs.

Retinal vessel segmentation is a critical task in fundus image analysis, providing essential insights for diagnosing various retinal diseases. In recent years, deep learning (DL) techniques, particularly Generative Adversarial Networks (GANs), have garnered significant attention for their potential to enhance medical image analysis. This paper presents a novel approach for retinal vessel segmentation by harnessing the capabilities of GANs. Our method, termed GANVesselNet, employs a specialized GAN architecture tailored to the intricacies of retinal vessel structures. In GANVesselNet, a dual-path network architecture is employed, featuring an Auto Encoder-Decoder (AED) pathway and a UNet-inspired pathway. This unique combination enables the network to efficiently capture multi-scale contextual information, improving the accuracy of vessel segmentation. Through extensive experimentation on publicly available retinal datasets, including STARE and DRIVE, GANVesselNet demonstrates remarkable performance compared to traditional methods and state-of-the-art deep learning approaches. The proposed GANVesselNet exhibits superior sensitivity (0.8174), specificity (0.9862), and accuracy (0.9827) in segmenting retinal vessels on the STARE dataset, and achieves commendable results on the DRIVE dataset with sensitivity (0.7834), specificity (0.9846), and accuracy (0.9709). Notably, GANVesselNet achieves remarkable performance on previously unseen data, underscoring its potential for real-world clinical applications. Furthermore, we present qualitative visualizations of the generated vessel segmentations, illustrating the network's proficiency in accurately delineating retinal vessels. In summary, this paper introduces GANVesselNet, a novel and powerful approach for retinal vessel segmentation. By capitalizing on the advanced capabilities of GANs and incorporating a tailored network architecture, GANVesselNet offers a quantum leap in retinal vessel segmentation accuracy, opening new avenues for enhanced fundus image analysis and improved clinical decision-making.

Looking into Concept Explanation Methods for Diabetic Retinopathy Classification

Diabetic retinopathy is a common complication of diabetes, and monitoring the progression of retinal abnormalities using fundus imaging is crucial. Because the images must be interpreted by a medical expert, it is infeasible to screen all individuals with diabetes for diabetic retinopathy. Deep learning has shown impressive results for automatic analysis and grading of fundus images. One drawback is, however, the lack of interpretability, which hampers the implementation of such systems in the clinic. Explainable artificial intelligence methods can be applied to explain the deep neural networks. Explanations based on concepts have shown to be intuitive for humans to understand, but have not yet been explored in detail for diabetic retinopathy grading. This work investigates and compares two concept-based explanation techniques for explaining deep neural networks developed for automatic diagnosis of diabetic retinopathy: Quantitative Testing with Concept Activation Vectors and Concept Bottleneck Models. We found that both methods have strengths and weaknesses, and choice of method should take the available data and the end user’s preferences into account. Our code is available at <a href='https://github.com/AndreaStoraas/ConceptExplanations_DR_grading'>https://github.com/AndreaStoraas/ConceptExplanations_DR_grading</a>

Retinal Imaging-Based Oculomics: Artificial Intelligence as a Tool in the Diagnosis of Cardiovascular and Metabolic Diseases.

Cardiovascular diseases (CVDs) are a major cause of mortality globally, emphasizing the need for early detection and effective risk assessment to improve patient outcomes. Advances in oculomics, which utilize the relationship between retinal microvascular changes and systemic vascular health, offer a promising non-invasive approach to assessing CVD risk. Retinal fundus imaging and optical coherence tomography/angiography (OCT/OCTA) provides critical information for early diagnosis, with retinal vascular parameters such as vessel caliber, tortuosity, and branching patterns identified as key biomarkers. Given the large volume of data generated during routine eye exams, there is a growing need for automated tools to aid in diagnosis and risk prediction. The study demonstrates that AI-driven analysis of retinal images can accurately predict cardiovascular risk factors, cardiovascular events, and metabolic diseases, surpassing traditional diagnostic methods in some cases. These models achieved area under the curve (AUC) values ranging from 0.71 to 0.87, sensitivity between 71% and 89%, and specificity between 40% and 70%, surpassing traditional diagnostic methods in some cases. This approach highlights the potential of retinal imaging as a key component in personalized medicine, enabling more precise risk assessment and earlier intervention. It not only aids in detecting vascular abnormalities that may precede cardiovascular events but also offers a scalable, non-invasive, and cost-effective solution for widespread screening. However, the article also emphasizes the need for further research to standardize imaging protocols and validate the clinical utility of these biomarkers across different populations. By integrating oculomics into routine clinical practice, healthcare providers could significantly enhance early detection and management of systemic diseases, ultimately improving patient outcomes. Fundus image analysis thus represents a valuable tool in the future of precision medicine and cardiovascular health management.

Artificial intelligence methods in diagnosis of retinoblastoma based on fundus imaging: a systematic review and meta-analysis.

Artificial intelligence (AI) algorithms for the detection of retinoblastoma (RB) by fundus image analysis have been proposed as a potentially effective technique to facilitate diagnosis and screening programs. However, doubts remain about the accuracy of the technique, the best type of AI for this situation, and its feasibility for everyday use. Therefore, we performed a systematic review and meta-analysis to evaluate this issue. Following PRISMA 2020 guidelines, a comprehensive search of MEDLINE, Embase,ClinicalTrials.gov and IEEEX databases identified494studies whose titles and abstracts were screened for eligibility. We included diagnostic studies that evaluated the accuracy of AI in identifying retinoblastoma based on fundus imaging. Univariate and bivariate analysis was performed using the random effects model. The study protocol was registered in PROSPERO under CRD42024499221. Six studies with 9902 fundus images were included, of which 5944 (60%) had confirmed RB. Only one dataset used a semi-supervised machine learning (ML) based method, all other studies used supervised ML, three using architectures requiring high computational power and two using more economical models. The pooled analysis of all models showed a sensitivity of 98.2% (95% CI: 0.947-0.994), a specificity of 98.5% (95% CI: 0.916-0.998) and an AUC of 0.986 (95% CI: 0.970-0.989). Subgroup analyses comparing models with high and low computational power showed no significant difference (p=0.824). AI methods showed a high precision in the diagnosis of RB based on fundus images with no significant difference when comparing high and low computational power models, suggesting a viability of their use. Validation and cost-effectiveness studies are needed in different income countries. Subpopulations should also be analyzed, as AI may be useful as an initial screening tool in populations at high risk for RB, serving as a bridge to the pediatric ophthalmologist or ocular oncologist, who are scarce globally. What isknown Retinoblastoma is the most common intraocular cancer in childhood and diagnostic delay is the main factor leading to a poor prognosis. The application of machine learning techniques proposes reliable methods for screening and diagnosis of retinal diseases. What isnew The meta-analysis of the diagnostic accuracy of artificial intelligence methods for diagnosing retinoblastoma based on fundus images showed a sensitivity of 98.2% (95% CI: 0.947-0.994) and a specificity of 98.5% (95% CI: 0.916-0.998). There was no statistically significant difference in the diagnostic accuracy of high and low computational power models. The overall performance of supervised machine learning was best than unsupervised, although few studies were available on the second type.

Prediction of Cardiovascular Markers and Diseases Using Retinal Fundus Images and Deep Learning: A Systematic Scoping Review

Abstract Background Rapid development in deep learning for image analysis inspired studies to focus on predicting cardiovascular risk using retinal fundus images. This scoping review aimed to identify and describe studies using retinal fundus images and deep learning to predict cardiovascular risk markers and diseases. Methods We searched MEDLINE and Embase on 17/11/2023. Abstracts and relevant full-text articles were independently screened by two reviewers. We included studies that used deep learning for the analysis of retinal fundus images to predict cardiovascular risk markers or cardiovascular diseases and excluded studies only using predefined characteristics of retinal fundus images were not considered. Study characteristics were presented using descriptive statistics. Results We included 24 articles published between 2018 and 2023. Among these, 23 (96%) were cross-sectional studies and eight (33%) were follow-up studies with clinical CVD outcomes. Seven studies included a combination of both designs. Most studies (96%) used convolutional neural networks to process images. We found nine (38%) studies that incorporated clinical risk factors in the prediction and four (17%) that compared the results to commonly used clinical risk scores in a prospective setting. Three of these reported improved discriminative performance. External validation of models was rare (21%). Conclusions There is increasing interest in using retinal fundus images in cardiovascular risk assessment with some studies demonstrating some improvements in prediction. However, more prospective studies, comparisons of results to clinical risk scores, and models augmented with traditional risk factors can strengthen further research in the field.

Evaluating the performance of a non-uniform squash function in Capsule networks for early diabetic retinopathy detection using fundus image analysis

Diabetic retinopathy, known as one of the most crucial neurovascular barriers to diabetes, has affected the retina, leading to a potential risk of blindness. The harm is not isolated to personal health, with negative effects felt at the economic and social level in entire communities. The consequences of vision loss secondary to diabetic retinopathy on quality of life, independent living, and employment can be significant. It is necessary to adopt a comprehensive approach for effective management of underlying diabetes, which includes early detection, timely intervention, supportive care, and management of comorbid conditions. Critical to this is a precise classification of its stages for disease analysis. A manual diagnosis, on the other hand, requires qualified individuals to recognize the subtle nuances of the condition, making it a lengthy process. This study aims to develop a computer-assisted system for analyzing retinal fundus images to identify and classify different stages of diabetic retinopathy. A dataset of eye fundus images was used by the proposed network to classify the presence and severity of blindness and its stages. The proposed model uses a non-uniform squash function in capsule neural networks. The motive behind employing a non-uniform squash function was to encourage the model to allocate greater attention and stability to intricate images throughout the training phase. The proposed model's efficiency is assessed meticulously with pre-trained CNN methods like InceptionV3, VGG16, VGG19, and Xception. The proposed capsule network model has been revamped to address the shortcomings of prior research with care. The method stands out with an impressive 99.84 % training accuracy and 98.68 % validation accuracy. Diabetic retinopathy, though rare in occurrence, poses significant challenges due to the high cost of diagnosis, rendering it inaccessible to rural and remote communities with limited access to tests and check-ups.

A Novel Dual Attention Approach for DNN Based Automated Diabetic Retinopathy Grading

ABSTRACTDiabetic retinopathy (DR) poses a serious threat to vision, emphasising the need for early detection. Manual analysis of fundus images, though common, is error‐prone and time‐intensive. Existing automated diagnostic methods lack precision, particularly in the early stages of DR. This paper introduces the Soft Convolutional Block Attention Module‐based Network (Soft‐CBAMNet), a deep learning network designed for severity detection, which features Soft‐CBAM attention to capture complex features from fundus images. The proposed network integrates both the convolutional block attention module (CBAM) and the soft‐attention components, ensuring simultaneous processing of input features. Following this, attention maps undergo a max‐pooling operation, and refined features are concatenated before passing through a dropout layer with a dropout rate of 50%. Experimental results on the APTOS dataset demonstrate the superior performance of Soft‐CBAMNet, achieving an accuracy of 85.4% in multiclass DR grading. The proposed architecture has shown strong robustness and general feature learning capability, achieving a mean AUC of 0.81 on the IDRID dataset. Soft‐CBAMNet's dynamic feature extraction capability across all classes is further justified by the inspection of intermediate feature maps. The model excels in identifying all stages of DR with increased precision, surpassing contemporary approaches. Soft‐CBAMNet presents a significant advancement in DR diagnosis, offering improved accuracy and efficiency for timely intervention.

Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study

BackgroundCardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown.MethodsThis was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set.ResultsIn an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74–0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86–1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73–1.00).ConclusionsAI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk.Trial registrationThis is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).Graphical

Artificial intelligence in the classification and segmentation of fundus images with choroidal nevi

ObjectiveThe purpose of this study is to summarize the results from 3 experimental studies into the use of artificial intelligence to classify and segment colour fundus images with choroidal nevi. Study DesignThis study is based on a secondary analysis of colour fundus images taken of patients receiving usual clinical care from the Alberta Ocular Brachytherapy Program. MethodsHigh-resolution colour fundus images were labeled by experienced ocular oncologists. In experimental study 1, four pre-trained models (ResNet 50, VGG-19, VGG-16, and AlexNet) were evaluated for their ability to classify images based on the presence of choroidal nevi. In experimental study 2, the performance of 3 patch-based models to classify images based on the presence of choroidal nevi were compared. In experimental study 3, four convolutional neural network models were developed to segment the images. In experimental studies 1 and 2, performance was measured using accuracy, precision, recall, F1 score, and AUC. In experimental study 3, IoU and Dice measures were used to evaluate performance. ResultsA total of 591 labelled colour fundus images were used for analysis. In experimental study 1, VGG-16 showed the best accuracy, AUC, and recall, but lower precision in classifying images. In experimental study 2, the patched approached enhanced with artifact and contrast outperformed the others in classifying images. In experimental study 3, a voting-based Ensemble model excelled in segmenting the part of images with nevi. ConclusionsIt is feasible to train AI models to identify choroidal nevi in colour fundus images.

Sodium-iodate injection can replicate retinal and choroid degeneration in pigmented mice: Using multimodal imaging and label-free quantitative proteomics analysis

Age-related macular degeneration (AMD) is the leading cause of irreversible visual loss in the elderly population. Sodium iodate (NaIO3), a stable oxidizing agent, has been injected to establish a reproducible model of oxidative stress-induced RPE and photoreceptor death. The aim of our study was to evaluate the morphological and molecular changes of retina and retinal pigment epithelium (RPE)-choroid in NaIO3-treated mouse using multimodal fundus imaging and label-free quantitative proteomics analysis. Here, we found that following NaIO3 injection, retinal degeneration was evident. Fundus photographs showed numerous scattered yellow-white speckled deposits. Optical coherence tomography (OCT) images indicated disruption of the retinal layers, damage of the RPE layer and accumulation of hyper-reflective matter in multiple layers of the outer retina. Widespread foci of a high fundus autofluorescence (FAF) signal were noticed. Fundus fluorescein angiography (FFA) revealed diffuse intense transmitted fluorescence mixed with scattered spot-like blocked fluorescence. Indocyanine green angiography (ICGA) presented punctate hyperfluorescence. Due to the atrophy of the RPE and Bruch's membrane and choroidal capillary complex, the larger choroidal vessels become more prominent in ICGA and optical coherence tomography angiography (OCTA). Transmission electron microscope (TEM) illustrated abnormal material accumulation and damaged mitochondria. Bioinformatics analysis of proteomics revealed that the differentially expressed proteins participated in diverse biological processes, encompassing phototransduction, NOD-like receptor signaling pathway, phagosome, necroptosis, and cell adhesion molecules. In conclusion, by multimodal imaging, we described the phenotype of NaIO3-treated mouse model mimicking oxidative stress-induced RPE and photoreceptor death in detail. In addition, proteomics analysis identified differentially expressed proteins and significant enrichment pathways, providing insights for future research, although the exact mechanism of oxidative stress-induced RPE and photoreceptor death remains incompletely understood.

E-LSTM: EfficientNet and Long Short-Term Memory Model for Detection of Glaucoma Diseases

Glaucoma is an eye disease that often has no symptoms until it is advanced. According to the World Health Organization (WHO), after cataracts, glaucoma is the second-leading cause of permanent blindness globally and is expected to affect 111.8 million patients by 2040. Early detection of glaucoma is important to reduce the risk of permanent blindness. Detection is achieved by structural measurement of early thinning of the retinal nerve fiber layer (RNFL). The RNFL is the portion of the retina located outside the optic nerve head (ONH) and can be observed in fundus images of the retina. Analysis of retinal fundus images can be performed with computer assistance using machine learning, especially deep learning. This study proposes a deep learning-based model, a convolutional neural network (CNN) using the EfficientNet architecture combined with long short-term memory (LSTM), for laucoma detection. Using ACRIMA, DRISHTI-GS, and RIM-ONE DL datasets with k-fold cross-validation, the model achieved high performance on the ACRIMA dataset: accuracy 0.9799, loss 0.0596, precision 0.9802, sensitivity 0.9799, specificity 0.9771, and F1score 0.9799. This EfficientNet and LSTM combination (e-LSTM) outperformed previous studies, offering a promising alternative for evaluating retinal fundus images in glaucoma detection.

Deep Learning-Based Vascular Aging Prediction From Retinal Fundus Images.

The purpose of this study was to establish and validate a deep learning model to screen vascular aging using retinal fundus images. Although vascular aging is considered a novel cardiovascular risk factor, the assessment methods are currently limited and often only available in developed regions. We used 8865 retinal fundus images and clinical parameters of 4376 patients from two independent datasets for training a deep learning algorithm. The gold standard for vascular aging was defined as a pulse wave velocity ≥1400 cm/s. The probability of the presence of vascular aging was defined as deep learning retinal vascular aging score, the Reti-aging score. We compared the performance of the deep learning model and clinical parameters by calculating the area under the receiver operating characteristics curve (AUC). We recruited clinical specialists, including ophthalmologists and geriatricians, to assess vascular aging in patients using retinal fundus images, aiming to compare the diagnostic performance between deep learning models and clinical specialists. Finally, the potential of Reti-aging score for identifying new-onset hypertension (NH) and new-onset carotid artery plaque (NCP) in the subsequent three years was examined. The Reti-aging score model achieved an AUC of 0.826 (95% confidence interval [CI] = 0.793-0.855) and 0.779 (95% CI = 0.765-0.794) in the internal and external dataset. It showed better performance in predicting vascular aging compared with the prediction with clinical parameters. The average accuracy of ophthalmologists (66.3%) was lower than that of the Reti-aging score model, whereas geriatricians were unable to make predictions based on retinal fundus images. The Reti-aging score was associated with the risk of NH and NCP (P < 0.05). The Reti-aging score model might serve as a novel method to predict vascular aging through analysis of retinal fundus images. Reti-aging score provides a novel indicator to predict new-onset cardiovascular diseases. Given the robust performance of our model, it provides a new and reliable method for screening vascular aging, especially in undeveloped areas.

Analysis of fundus images based on machine learning

Analysis of fundus images based on machine learning

Automated detection of type 1 ROP, type 2 ROP and A-ROP based on deep learning

PurposeTo provide automatic detection of Type 1 retinopathy of prematurity (ROP), Type 2 ROP, and A-ROP by deep learning-based analysis of fundus images obtained by clinical examination using convolutional neural networks.Material and methodsA total of 634 fundus images of 317 premature infants born at 23–34 weeks of gestation were evaluated. After image pre-processing, we obtained a rectangular region (ROI). RegNetY002 was used for algorithm training, and stratified 10-fold cross-validation was applied during training to evaluate and standardize our model. The model’s performance was reported as accuracy and specificity and described by the receiver operating characteristic (ROC) curve and area under the curve (AUC).ResultsThe model achieved 0.98 accuracy and 0.98 specificity in detecting Type 2 ROP versus Type 1 ROP and A-ROP. On the other hand, as a result of the analysis of ROI regions, the model achieved 0.90 accuracy and 0.95 specificity in detecting Stage 2 ROP versus Stage 3 ROP and 0.91 accuracy and 0.92 specificity in detecting A-ROP versus Type 1 ROP. The AUC scores were 0.98 for Type 2 ROP versus Type 1 ROP and A-ROP, 0.85 for Stage 2 ROP versus Stage 3 ROP, and 0.91 for A-ROP versus Type 1 ROP.ConclusionOur study demonstrated that ROP classification by DL-based analysis of fundus images can be distinguished with high accuracy and specificity. Integrating DL-based artificial intelligence algorithms into clinical practice may reduce the workload of ophthalmologists in the future and provide support in decision-making in the management of ROP.

Glaucoma Detection through a Novel Hyperspectral Imaging Band Selection and Vision Transformer Integration.

Conventional diagnostic methods for glaucoma primarily rely on non-dynamic fundus images and often analyze features such as the optic cup-to-disc ratio and abnormalities in specific retinal locations like the macula and fovea. However, hyperspectral imaging techniques focus on detecting alterations in oxygen saturation within retinal vessels, offering a potentially more comprehensive approach to diagnosis. This study explores the diagnostic potential of hyperspectral imaging for glaucoma by introducing a novel hyperspectral imaging conversion technique. Digital fundus images are transformed into hyperspectral representations, allowing for a detailed analysis of spectral variations. Spectral regions exhibiting differences are identified through spectral analysis, and images are reconstructed from these specific regions. The Vision Transformer (ViT) algorithm is then employed for classification and comparison across selected spectral bands. Fundus images are used to identify differences in lesions, utilizing a dataset of 1291 images. This study evaluates the classification performance of models using various spectral bands, revealing that the 610-780 nm band outperforms others with an accuracy, precision, recall, F1-score, and AUC-ROC all approximately at 0.9007, indicating its superior effectiveness for the task. The RGB model also shows strong performance, while other bands exhibit lower recall and overall metrics. This research highlights the disparities between machine learning algorithms and traditional clinical approaches in fundus image analysis. The findings suggest that hyperspectral imaging, coupled with advanced computational techniques such as the ViT algorithm, could significantly enhance glaucoma diagnosis. This understanding offers insights into the potential transformation of glaucoma diagnostics through the integration of hyperspectral imaging and innovative computational methodologies.