Diagnosis Of Ocular Diseases Research Articles

Ophthalmic examination findings in healthy white storks (Ciconia Ciconia)

In birds, vision plays an essential role in vital functions such as feeding and reproduction. In this study, it was aimed to determine the ophthalmic examination findings in healthy storks. A total of eleven healthy white storks were included in the study. Schirmer tear test 1 (STT-I), intraocular pressure (IOP) and ocular biometry were performed on both eyes of each stork. The mean STT-I values were 12±3.4 (right eye) and 11.9±3.14 mm/min (left eye), and the IOP values were 19±0.97 (right eye) and 18.85±0.73 mmHg (left eye). The mean ocular biometric values were as follows: anterior chamber depth, 2.30±0.18 and 2.29±0.13 mm, lens thickness 5.18±0.1 and 5.19±0.13 mm, vitreous body 11.72±0.25 and 11.82±0.34 mm, and pecten 7.94±0.34 and 7.9±0.37 mm of the right and left eyes, respectively. Knowledge of the normal value ranges in healthy white storks is necessary for the diagnosis of ocular diseases in this species. To the authors’ knowledge, this is the first study in which normal ophthalmic value ranges in healthy storks are described.

Diagnosis of ophthalmologic diseases in canines based on images using neural networks for image segmentation

The primary challenge in diagnosing ocular diseases in canines based on images lies in developing an accurate and reliable machine learning method capable of effectively segmenting and diagnosing these conditions through image analysis. Addressing this challenge, the study focuses on developing and rigorously evaluating a machine learning model for diagnosing ocular diseases in canines, employing the U-Net neural network architecture as a foundational element of this investigation.Through this extensive evaluation, the authors identified a model that exhibited good reliability, achieving prediction scores with an Intersection over Union (IoU) exceeding 80 %, as measured by the Jaccard index. The research methodology encompassed a systematic exploration of various neural network backbones (VGG, ResNet, Inception, EfficientNet) and the U-Net model, combined with an extensive model selection process and an in-depth analysis of a custom training dataset consisting of historical images of different medical symptoms and diseases in dog eyes.The results indicate a fairly high degree of accuracy in the segmentation and diagnosis of ocular diseases in canines, demonstrating the model's effectiveness in real-world applications. In conclusion, this potentially makes a significant contribution to the field by utilizing advanced machine-learning techniques to develop image-based diagnostic routines in veterinary ophthalmology. This model's successful development and validation offer a promising new tool for veterinarians and pet owners, enhancing early disease detection and improving health outcomes for canine patients.

Advances in Extracellular-Vesicles-Based Diagnostic and Therapeutic Approaches for Ocular Diseases.

Extracellular vesicles (EVs) are nanoscale membrane vesicles of various sizes that can be secreted by most cells. EVs contain a diverse array of cargo, including RNAs, lipids, proteins, and other molecules with functions of intercellular communication, immune modulation, and regulation of physiological and pathological processes. The biofluids in the eye, including tears, aqueous humor, and vitreous humor, are important sources for EV-based diagnosis of ocular disease. Because the molecular cargos may reflect the biology of their parental cells, EVs in these biofluids, as well as in the blood, have been recognized as promising candidates as biomarkers for early diagnosis of ocular disease. Moreover, EVs have also been used as therapeutics and targeted drug delivery nanocarriers in many ocular disorders because of their low immunogenicity and superior biocompatibility in nature. In this review, we provide an overview of the recent advances in the field of EV-based studies on the diagnosis and therapeutics of ocular disease. We summarized the origins of EVs applied in ocular disease, assessed different methods for EV isolation from ocular biofluid samples, highlighted bioengineering strategies of EVs as drug delivery systems, introduced the latest applications in the diagnosis and treatment of ocular disease, and presented their potential in the current clinical trials. Finally, we briefly discussed the challenges of EV-based studies in ocular disease and some issues of concern for better focusing on clinical translational studies of EVs in the future.

Enhancing the ophthalmic AI assessment with a fundus image quality classifier using local and global attention mechanisms.

The assessment of image quality (IQA) plays a pivotal role in the realm of image-based computer-aided diagnosis techniques, with fundus imaging standing as the primary method for the screening and diagnosis of ophthalmic diseases. Conventional studies on fundus IQA tend to rely on simplistic datasets for evaluation, predominantly focusing on either local or global information, rather than a synthesis of both. Moreover, the interpretability of these studies often lacks compelling evidence. In order to address these issues, this study introduces the Local and Global Attention Aggregated Deep Neural Network (LGAANet), an innovative approach that integrates both local and global information for enhanced analysis. The LGAANet was developed and validated using a Multi-Source Heterogeneous Fundus (MSHF) database, encompassing a diverse collection of images. This dataset includes 802 color fundus photography (CFP) images (302 from portable cameras), and 500 ultrawide-field (UWF) images from 904 patients with diabetic retinopathy (DR) and glaucoma, as well as healthy individuals. The assessment of image quality was meticulously carried out by a trio of ophthalmologists, leveraging the human visual system as a benchmark. Furthermore, the model employs attention mechanisms and saliency maps to bolster its interpretability. In testing with the CFP dataset, LGAANet demonstrated remarkable accuracy in three critical dimensions of image quality (illumination, clarity and contrast based on the characteristics of human visual system, and indicates the potential aspects to improve the image quality), recording scores of 0.947, 0.924, and 0.947, respectively. Similarly, when applied to the UWF dataset, the model achieved accuracies of 0.889, 0.913, and 0.923, respectively. These results underscore the efficacy of LGAANet in distinguishing between varying degrees of image quality with high precision. To our knowledge, LGAANet represents the inaugural algorithm trained on an MSHF dataset specifically for fundus IQA, marking a significant milestone in the advancement of computer-aided diagnosis in ophthalmology. This research significantly contributes to the field, offering a novel methodology for the assessment and interpretation of fundus images in the detection and diagnosis of ocular diseases.

Advances in the diagnosis of ocular diseases: an innovative approach through an expert system

In the context of ophthalmic care, where early diagnosis of eye disorders plays a crucial role in patients' quality of life, this study focused on the development and evaluation of an expert system based on SWI Prolog. The main objective of this research was to provide an effective method for the preliminary diagnosis of ocular disorders, including cataract, trachoma, uveitis, glaucoma, and presbyopia. For the evaluation of the system, a confusion matrix was implemented and accuracy, sensitivity and specificity were calculated using a sample of 30 cases, of which 20 were positive and 10 negatives. The findings revealed an outstanding accuracy of 95%, with a sensitivity and specificity of 90%. This highlights the potential of the tool as an effective means of early detection of visual problems. In conclusion, this expert system represents a significant advance in ophthalmologic diagnosis, with important implications for clinical care and patients' quality of life, although expansion and validation of the tool in further clinical studies is suggested for its wider and more successful implementation in the field of ophthalmology.

Compact Linear Flow Phantom Model for Retinal Blood-Flow Evaluation.

Impaired retinal blood flow is associated with ocular diseases such as glaucoma, macular degeneration, and diabetic retinopathy. Among several ocular imaging techniques developed to measure retinal blood flow both invasively and non-invasively, adaptive optics (AO)-enabled scanning laser ophthalmoscopy (AO-SLO) resolves individual red blood cells and provides a high resolution with which to measure flow across retinal microvasculature. However, cross-validation of flow measures remains a challenge owing to instrument and patient-specific variability in each imaging technique. Hence, there is a critical need for a well-controlled clinical flow phantom for standardization and to establish blood-flow measures as clinical biomarkers for early diagnosis. Here, we present the design and validation of a simple, compact, portable, linear flow phantom based on a direct current motor and a conveyor-belt system that provides linear velocity tuning within the retinal microvasculature range (0.5-7 mm/s). The model was evaluated using a sensitive AO-SLO line-scan technique, which showed a <6% standard deviation from the true velocity. Further, a clinical SLO instrument showed a linear correlation with the phantom's true velocity (r2 > 0.997). This model has great potential to calibrate, evaluate, and improve the accuracy of existing clinical imaging systems for retinal blood flow and aid in the diagnosis of ocular diseases with abnormal blood flow.

A Method for Ocular Disease Diagnosis through Visual Prediction Explainability

Ocular diseases can range in severity, with some being more serious than others. As a matter of fact, there are several common and severe eye diseases, for instance, glaucoma, i.e., a group of eye conditions that damage the optic nerve, often associated with elevated intraocular pressure. Effective management and prevention strategies require a multifaceted approach, involving healthcare providers, public health officials and community education. Regular screenings and early interventions are crucial in reducing the impact of eye diseases on individuals and populations. In this paper, we propose a method aimed to detect the presence of ocular disease from the automatic analysis of eye fundus photographs. We consider deep learning; in detail, we adopt several convolutional neural networks aimed to train several models to be able to discriminate between different eye diseases. Furthermore, to boost the application of deep learning in real-world everyday medical practice, we adopt a method to understand which areas of the images are of interest from the model’s point of view; this allows us to detect disease by providing in this way disease localization by explainability. In the experimental analysis, we provide a set of four different experiments: in the first one, we propose a model to discern between age-related macular degenerations and normal fundus (obtaining an accuracy of 0.91); in the second one, the model is able to discriminate between cataract and normal fundus (obtaining an accuracy of 0.92); the third experiment is related to a model aimed to discriminate between glaucoma and normal ocular fundus (obtaining an accuracy of 0.88); and the last experiment is related to a model aimed to discern between pathological myopia and normal ocular fundus (obtaining an accuracy of 0.95). Thus, the experimental analysis confirms the effectiveness of the proposed method from a quantitative point of view (analysis aimed at understanding whether the model is able to correctly identify the disease) but also from a qualitative one, with a detailed and reasoned analysis aimed at understanding whether the model is able to correctly localize the disease.

Automated eyeball volume measurement based on CT images using neural network-based segmentation and simple estimation

With the increase in the dependency on digital devices, the incidence of myopia, a precursor of various ocular diseases, has risen significantly. Because myopia and eyeball volume are related, myopia progression can be monitored through eyeball volume estimation. However, existing methods are limited because the eyeball shape is disregarded during estimation. We propose an automated eyeball volume estimation method from computed tomography images that incorporates prior knowledge of the actual eyeball shape. This study involves data preprocessing, image segmentation, and volume estimation steps, which include the truncated cone formula and integral equation. We obtained eyeball image masks using U-Net, HFCN, DeepLab v3 +, SegNet, and HardNet-MSEG. Data from 200 subjects were used for volume estimation, and manually extracted eyeball volumes were used for validation. U-Net outperformed among the segmentation models, and the proposed volume estimation method outperformed comparative methods on all evaluation metrics, with a correlation coefficient of 0.819, mean absolute error of 0.640, and mean squared error of 0.554. The proposed method surpasses existing methods, provides an accurate eyeball volume estimation for monitoring the progression of myopia, and could potentially aid in the diagnosis of ocular diseases. It could be extended to volume estimation of other ocular structures.

Tensor Ring Decomposition Guided Dictionary Learning for OCT Image Denoising.

Optical coherence tomography (OCT) is a non-invasive and effective tool for the imaging of retinal tissue. However, the heavy speckle noise, resulting from multiple scattering of the light waves, obscures important morphological structures and impairs the clinical diagnosis of ocular diseases. In this paper, we propose a novel and powerful model known as tensor ring decomposition-guided dictionary learning (TRGDL) for OCT image denoising, which can simultaneously utilize two useful complementary priors, i.e., three-dimensional low-rank and sparsity priors, under a unified framework. Specifically, to effectively use the strong correlation between nearby OCT frames, we construct the OCT group tensors by extracting cubic patches from OCT images and clustering similar patches. Then, since each created OCT group tensor has a low-rank structure, to exploit spatial, non-local, and its temporal correlations in a balanced way, we enforce the TR decomposition model on each OCT group tensor. Next, to use the beneficial three-dimensional inter-group sparsity, we learn shared dictionaries in both spatial and temporal dimensions from all of the stacked OCT group tensors. Furthermore, we develop an effective algorithm to solve the resulting optimization problem by using two efficient optimization approaches, including proximal alternating minimization and the alternative direction method of multipliers. Finally, extensive experiments on OCT datasets from various imaging devices are conducted to prove the generality and usefulness of the proposed TRGDL model. Experimental simulation results show that the suggested TRGDL model outperforms state-of-the-art approaches for OCT image denoising both qualitatively and quantitatively.

A transfer learning enabled approach for ocular disease detection and classification.

Ocular diseases pose significant challenges in timely diagnosis and effective treatment. Deep learning has emerged as a promising technique in medical image analysis, offering potential solutions for accurately detecting and classifying ocular diseases. In this research, we propose Ocular Net, a novel deep learning model for detecting and classifying ocular diseases, including Cataracts, Diabetic, Uveitis, and Glaucoma, using a large dataset of ocular images. The study utilized an image dataset comprising 6200 images of both eyes of patients. Specifically, 70% of these images (4000 images) were allocated for model training, while the remaining 30% (2200 images) were designated for testing purposes. The dataset contains images of five categories that include four diseases, and one normal category. The proposed model uses transfer learning, average pooling layers, Clipped Relu, Leaky Relu and various other layers to accurately detect the ocular diseases from images. Our approach involves training a novel Ocular Net model on diverse ocular images and evaluating its accuracy and performance metrics for disease detection. We also employ data augmentation techniques to improve model performance and mitigate overfitting. The proposed model is tested on different training and testing ratios with varied parameters. Additionally, we compare the performance of the Ocular Net with previous methods based on various evaluation parameters, assessing its potential for enhancing the accuracy and efficiency of ocular disease diagnosis. The results demonstrate that Ocular Net achieves 98.89% accuracy and 0.12% loss value in detecting and classifying ocular diseases by outperforming existing methods.

Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment.

Automatic retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis of ocular diseases. Currently, automatic retinal layer segmentation works well with normal OCT images. However, pigment epithelial detachment (PED) dramatically alters the retinal structure, causing blurred boundaries and partial disappearance of the Bruch's Membrane (BM), thus posing challenges to the segmentation. To tackle these problems, we propose a novel dual-path U-shaped network for simultaneous layer segmentation and boundary regression. This network first designs a feature interaction fusion (FIF) module to strengthen the boundary shape constraints in the layer path. To address the challenge posed by partial BM disappearance and boundary-blurring, we propose a layer boundary repair (LBR) module. This module aims to use contrastive loss to enhance the confidence of blurred boundary regions and refine the segmentation of layer boundaries through the re-prediction head. In addition, we introduce a novel bilateral threshold distance map (BTDM) designed for the boundary path. The BTDM serves to emphasize information within boundary regions. This map, combined with the updated probability map, culminates in topology-guaranteed segmentation results achieved through a topology correction (TC) module. We investigated the proposed network on two severely deformed datasets (i.e., OCTA-500 and Aier-PED) and one slightly deformed dataset (i.e., DUKE). The proposed method achieves an average Dice score of 94.26% on the OCTA-500 dataset, which was 1.5% higher than BAU-Net and outperformed other methods. In the DUKE and Aier-PED datasets, the proposed method achieved average Dice scores of 91.65% and 95.75%, respectively.

Advancements and turning point of artificial intelligence in ophthalmology: A comprehensive analysis of research trends and collaborative networks.

Artificial intelligence (AI) has emerged as a transformative force with great potential in various fields, including healthcare. In recent years, AI has garnered significant attention due to its potential to revolutionise ophthalmology, leading to advancements in patient care such as disease detection, diagnosis, treatment and monitoring of disease progression. This study presents a comprehensive analysis of the research trends and collaborative networks at the intersection of AI and ophthalmology. In this study, we conducted an extensive search of the Web of Science Core Collection to identify articles related to 'artificial intelligence' in ophthalmology published from 1968 to 2023. We performed co-occurrence keywords and co-authorship network analyses using VOSviewer software to explore the relationships between keywords and country collaboration. We found a remarkable surge in articles applying AI in ophthalmology after 2017, marking a turning point in the integration of AI within the medical field. The primary application of AI shifted towards the diagnosis of ocular disease, which was particularly evident through keywords such as glaucoma, diabetic retinopathy and age-related macular degeneration. Analysis of the collaboration networks of countries revealed a global expansion of ophthalmology-related AI research. This study provides valuable insights into the evolving landscape of AI integration in ophthalmology, indicating its growing potential for enhancing disease detection, diagnosis, treatment planning and monitoring of disease progression. In order to translate AI technologies into clinical practice effectively, it is imperative to comprehend the evolving research trends and advancements at the intersection of AI and ophthalmology.

Advanced nanomaterials for imaging of eye diseases.

Vision impairment and blindness present significant global challenges, with common causes including age-related macular degeneration, diabetes, retinitis pigmentosa, and glaucoma. Advanced imaging tools, such as optical coherence tomography, fundus photography, photoacoustic microscopy, and fluorescence imaging, play a crucial role in improving therapeutic interventions and diagnostic methods. Contrast agents are often employed with these tools to enhance image clarity and signal detection. This review aims to explore the commonly used contrast agents in ocular disease imaging. The first section of the review delves into advanced ophthalmic imaging techniques, outlining their importance in addressing vision-related issues. The emphasis is on the efficacy of therapeutic interventions and diagnostic methods, establishing a foundation for the subsequent exploration of contrast agents. This review focuses on the role of contrast agents, with a specific emphasis on gold nanoparticles, particularly gold nanorods. The discussion highlights how these contrast agents optimize imaging in ocular disease diagnosis and monitoring, emphasizing their unique properties that enhance signal detection and imaging precision. The final section, we explores both organic and inorganic contrast agents and their applications in specific conditions such as choroidal neovascularization, retinal neovascularization, and stem cell tracking. The review concludes by addressing the limitations of current contrast agent usage and discussing potential future clinical applications. This comprehensive exploration contributes to advancing our understanding of contrast agents in ocular disease imaging and sets the stage for further research and development in the field.

Parallel Multi-Path Network for Ocular Disease Detection Inspired by Visual Cognition Mechanism.

Various ocular diseases such as cataracts, glaucoma, and diabetic retinopathy have become several major factors causing non-congenital visual impairment, which seriously threatens people's vision health. The shortage of ophthalmic medical resources has brought huge obstacles to large-scale ocular disease screening. Therefore, it is necessary to use computer-aided diagnosis (CAD) technology to achieve large-scale screening and diagnosis of ocular diseases. In this work, inspired by the human visual cognition mechanism, we propose a parallel multi-path network for multiple ocular diseases detection, called PMP-OD, which integrates the detection of multiple common ocular diseases, including cataracts, glaucoma, diabetic retinopathy, and pathological myopia. The bottom-up features of the fundus image are extracted by a common convolutional module, the Low-level Feature Extraction module, which simulates the non-selective pathway. Simultaneously, the top-down vessel and other lesion features are extracted by the High-level Feature Extraction module that simulates the selective pathway. The retinal vessel and lesion features can be regarded as task-driven high-level semantic information in the physician's disease diagnosis process. Then, the features are fused by a feature fusion module based on the attention mechanism. Finally, the disease classifier gives prediction results according to the integrated multi-features. The experimental results indicate that our PMP-OD model outperforms other state-of-the-art (SOTA) models on an ocular disease dataset reconstructed from ODIR-5K, APTOS-2019, ORIGA-light, and Kaggle.

The role of deep learning in the diagnosis of ocular diseases

Deep Learning (DL) revolutionized a wide variety of research fields and applications of Artificial Intelligence (AI) in the last years. Computer vision is among those fields that witnessed a stronger impact, especially in some tasks like image equalization, classification and segmentation, that have several applications in medical imaging. Such applications often focus on microscopy images, but they can be successfully extended to other fields, like the detection of diseases involving the ocular surface and the cornea.One of the reasons of the success of deep learning applied to image processing relies in the end‐to‐end data‐driven approach. This means that the whole image processing and classification/segmentation pipeline can be adapted to the data being processed. This is particularly powerful when dealing with medical images, whose processing is often based on the detection of low‐ and mid‐level patterns that might be difficult to define in a formal manner. This means that deep learning has the chance to select and consider some image elements that would be nearly impossible to define using standard computer vision techniques. However, this becomes possible if large amounts of data are available for training the network, which became reality in the last years thanks to the wide digitalization of medical systems, including ophthalmology equipment.Based on a substantial amount of literature that has rapidly grown in the last years, this talk will focus on the new perspectives of eye disease diagnosis that were opened by the advent of deep learning. At the same time, the limitations and risks that must be considered in the development of DL‐based medical systems, like overfitting and lack of generalization, will be highlighted and discussed. Keeping track of such limitations is crucial in order not to consider DL as a sort of magic box, but rather, as powerful image analysis and processing tool.The talk will also provide a qualitative and quantitative evaluation of the diagnosis systems currently available that exploit DL and AI systems. The current and future impact of automatic image processing systems dedicated to ophthalmology will also be discussed. When automatic medical image analysis will be widely available, the patterns of medical diagnosis will need to change, taking advantage of the possibility to perform larger screenings that will be automatically processed.

Molecular and cellular imaging of the eye.

The application of molecular and cellular imaging in ophthalmology has numerous benefits. It can enable the early detection and diagnosis of ocular diseases, facilitating timely intervention and improved patient outcomes. Molecular imaging techniques can help identify disease biomarkers, monitor disease progression, and evaluate treatment responses. Furthermore, these techniques allow researchers to gain insights into the pathogenesis of ocular diseases and develop novel therapeutic strategies. Molecular and cellular imaging can also allow basic research to elucidate the normal physiological processes occurring within the eye, such as cell signaling, tissue remodeling, and immune responses. By providing detailed visualization at the molecular and cellular level, these imaging techniques contribute to a comprehensive understanding of ocular biology. Current clinically available imaging often relies on confocal microscopy, multi-photon microscopy, PET (positron emission tomography) or SPECT (single-photon emission computed tomography) techniques, optical coherence tomography (OCT), and fluorescence imaging. Preclinical research focuses on the identification of novel molecular targets for various diseases. The aim is to discover specific biomarkers or molecular pathways associated with diseases, allowing for targeted imaging and precise disease characterization. In parallel, efforts are being made to develop sophisticated and multifunctional contrast agents that can selectively bind to these identified molecular targets. These contrast agents can enhance the imaging signal and improve the sensitivity and specificity of molecular imaging by carrying various imaging labels, including radionuclides for PET or SPECT, fluorescent dyes for optical imaging, or nanoparticles for multimodal imaging. Furthermore, advancements in technology and instrumentation are being pursued to enable multimodality molecular imaging. Integrating different imaging modalities, such as PET/MRI (magnetic resonance imaging) or PET/CT (computed tomography), allows for the complementary strengths of each modality to be combined, providing comprehensive molecular and anatomical information in a single examination. Recently, photoacoustic microscopy (PAM) has been explored as a novel imaging technology for visualization of different retinal diseases. PAM is a non-invasive, non-ionizing radiation, and hybrid imaging modality that combines the optical excitation of contrast agents with ultrasound detection. It offers a unique approach to imaging by providing both anatomical and functional information. Its ability to utilize molecularly targeted contrast agents holds great promise for molecular imaging applications in ophthalmology. In this review, we will summarize the application of multimodality molecular imaging for tracking chorioretinal angiogenesis along with the migration of stem cells after subretinal transplantation in vivo.

Exploring the Associations between Diabetes Mellitus and Diabetic Retinopathy: Prevention and Management by focus on Machine Learning Technique

Introduction: diabetes Mellitus, a disorder impacting insulin production and utilization, led to elevated blood sugar levels. Immune system assaults on insulin-producing pancreas cells caused Type 1 Diabetes Mellitus, while Type 2 Diabetes Mellitus affected glucose processing, predominantly in adults but also observed in children. Unmanaged diabetes resulted in varied health issues including heart disease, kidney damage, nerve impairment, and diabetic retinopathy, a major cause of adult blindness.Objective: to prevent diabetic retinopathy through glycemic control, achieved via management, lifestyle choices, screenings, treatments, education, and awareness. Machine learning techniques like transfer learning, ensemble learning, CNN-MNIST, and multiscale approaches showed promise in detection and diagnosis. Monitoring blood sugar and eye exams were vital for early retinopathy treatment.Result: DR risk is elevated in those with positive complications like nephropathy, heart disease, cerebrovascular disease, foot ulcers and HbA1C levels ≥6,8 %. Retinal imaging aids diagnosis and monitoring of ocular diseases like DR, utilizing processed monochrome images for structural analysis.Method: involved observing NPDR, MPDR via eye exams, measuring glucose, visual acuity, and retinal thickness. Retinal imaging aided ocular disease diagnosis, utilizing processed images for analysis.Conclusion: diabetes prevalence rose globally, projected to affect 800 million adults by 2050. High India rates emphasized healthcare need, especially in remote areas, addressing diabetic retinopathy and early symptom awareness

Profiling miRNAs in tear extracellular vesicles: a pilot study with implications for diagnosis of ocular diseases.

To estimate the roles of extracellular vesicles (EVs) in tears and to determine whether their profiles are associated with the type of ocular disease. Cross-sectional study. Tear EVs were extracted from 14 healthy participants and from 21 patients with retinal diseases (age-related macular degeneration [AMD] or diabetic macular edema [DME]). The surface marker expression of tear EVs was examined, and microRNAs (miRNAs) were extracted and profiled by use of real-time PCR array. The stability of the expression of the miRNAs was determined, and their functions were assessed by network analyses. Classification accuracy was evaluated by use of a random forest classifier and k-fold cross-validation. The miRNAs that were highly expressed in tear EVs were miR-323-3p, miR-548a-3p, and miR-516a-5p. The most stably expressed miRNAs independent of diseases were miR-520h and miR-146b-3p. The primary networks of the highly stably expressed endogenous miRNAs were annotated as regulation of organismal injury and abnormalities. The highly expressed miRNAs for severe retinal disease were miR-151-5p for AMD and miR-422a for DME, suggesting potential roles of tear EVs in liquid biopsy. Nine miRNAs (miR-25, miR-30d, miR-125b, miR-132, miR-150, miR-184, miR-342-3p, miR-378, and miR-518b) were identified as distinguishing individuals with AMD from healthy individuals with a classification accuracy of 91.9%. The finding that tear EVs contain characteristic miRNA species indicates that they may help in maintaining homeostasis and serve as a potential tool for disease diagnosis.

Classification of Retinal Vascular Diseases Using Ensemble Decision Tree in Thermal Images

In the field of medicine, thermal image processing and analysis play a significant role in the diagnosis, monitoring, and treatment of diseases. For example, during the last decade, several studies have been performed based on thermal image processing for ocular disease diagnosis. This research proposes a unique approach for the classification of subgroups of two retinal vascular diseases, namely diabetic eye disease and age-related macular degeneration (AMD). The class imbalance problem is a well-known issue when working with medical data, where one class is significantly less represented than another class in the dataset. To deal with the class imbalance issue, an ensemble decision tree classifier with a random under-sampling and adaptive boosting (RUSBoost) technique is proposed. The performance of the proposed classifier is compared with various traditional machine learning-based classifiers. Experimental results show that the proposed ensemble tree outperforms other classifiers through high accuracy, [Formula: see text]-score, and Mathews correlation coefficient (MCC) values in classifying diabetic eye diseases and AMD diseases. The proposed ensemble decision tree distinguishes dry AMD and wet AMD over healthy controls with 95% average accuracy. Also, it classifies diabetic retinopathy (DR) with diabetic macular edema (DME) and DR without DME with 94% average accuracy. The classifier could distinguish dry and wet AMD which did not work around in temperature analysis on the manual temperature measurement. The performance of the automated classification model is on par with the performance of the temperature analysis of OST for DME and DR without DME.

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

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