The Role of Different Retinal Imaging Modalities in Predicting Progression of Diabetic Retinopathy: A Survey

Recent advances and applications of optical coherence tomography angiography in diabetic retinopathy

Introduction

Optical coherence tomography angiography (OCTA), a noninvasive imaging technique, is increasingly used in managing ophthalmic diseases like diabetic retinopathy (DR). This review examines OCTA's imaging principles, its utility in detecting DR lesions, and its diagnostic advantages over fundus fluorescein angiography (FFA).

Methods

We systematically analyzed 75 articles (2015-2024) from the Web of Science Core Collection, focusing on OCTA's technical principles, clinical applications in DR diagnosis, and its use in diabetes mellitus (DM) without DR and prediabetes. The use of artificial intelligence (AI) in OCTA image analysis for DR severity evaluation was investigated.

Results

OCTA effectively identifies DR lesions and detects early vascular abnormalities in DM and prediabetes, surpassing FFA in noninvasiveness and resolution. AI integration enhances OCTA's capability to diagnose, evaluate, and predict DR progression.

Discussion

OCTA offers significant clinical value in early DR detection and monitoring. Its synergy with AI holds promise for refining diagnostic precision and expanding predictive applications, positioning OCTA as a transformative tool in future ophthalmic practice.

Diabetic Retinopathy-A Review

Diabetic Retinopathy is a vascular microvascular disease also called diabetic eye disease caused by microangiopathy leading to progressive damage of the retina and blindness. The uncontrolled blood glycemic level or sugar level results in diabetic retinopathy. There are two stages of diabetic retinopathy: proliferative diabetic retinopathy and nonproliferative diabetic retinopathy. Symptoms of diabetic retinopathy often have no early warning signs, even muscular edema, which can cause rapid vision loss. Macular edema in which the blood vessels leak can also occur at any stage of diabetic retinopathy. Symptoms are darkened or distorted images and blurred vision that are not the same in both eyes. This review study primarily discusses the pathophysiology, genetics, and ALR, AGEs, VEGF, EPO, and eNOS involved in diabetic retinopathy. The longer a person has diabetes, the higher their risk of developing some ocular problems. During pregnancy, diabetic retinopathy may also be a problem for women with diabetes. NIH are recommends that all pregnant women with diabetes have an overall eye examination. Diagnosis of diabetic retinopathy is made during an eye examination that comprises ophthalmoscopy or fundus photography, and glow-in angiography for Fundus. Here, we present a review of the current insights into pathophysiology in diabetic retinopathy, as well as clinical treatments for diabetic retinopathy patients. Novel laboratory findings and related clinical trials are also analysed.

Gold Nanoparticles for Retinal Molecular Optical Imaging

The incorporation of gold nanoparticles (GNPs) into retinal imaging signifies a notable advancement in ophthalmology, offering improved accuracy in diagnosis and patient outcomes. This review explores the synthesis and unique properties of GNPs, highlighting their adjustable surface plasmon resonance, biocompatibility, and excellent optical absorption and scattering abilities. These features make GNPs advantageous contrast agents, enhancing the precision and quality of various imaging modalities, including photoacoustic imaging, optical coherence tomography, and fluorescence imaging. This paper analyzes the unique properties and corresponding mechanisms based on the morphological features of GNPs, highlighting the potential of GNPs in retinal disease diagnosis and management. Given the limitations currently encountered in clinical applications of GNPs, the approaches and strategies to overcome these limitations are also discussed. These findings suggest that the properties and efficacy of GNPs have innovative applications in retinal disease imaging.

Identification of key biomarkers for early warning of diabetic retinopathy using BP neural network algorithm and hierarchical clustering analysis

Diabetic retinopathy is one of the most common microangiopathy in diabetes, essentially caused by abnormal blood glucose metabolism resulting from insufficient insulin secretion or reduced insulin activity. Epidemiological survey results show that about one third of diabetes patients have signs of diabetic retinopathy, and another third may suffer from serious retinopathy that threatens vision. However, the pathogenesis of diabetic retinopathy is still unclear, and there is no systematic method to detect the onset of the disease and effectively predict its occurrence. In this study, we used medical detection data from diabetic retinopathy patients to determine key biomarkers that induce disease onset through back propagation neural network algorithm and hierarchical clustering analysis, ultimately obtaining early warning signals of the disease. The key markers that induce diabetic retinopathy have been detected, which can also be used to explore the induction mechanism of disease occurrence and deliver strong warning signal before disease occurrence. We found that multiple clinical indicators that form key markers, such as glycated hemoglobin, serum uric acid, alanine aminotransferase are closely related to the occurrence of the disease. They respectively induced disease from the aspects of the individual lipid metabolism, cell oxidation reduction, bone metabolism and bone resorption and cell function of blood coagulation. The key markers that induce diabetic retinopathy complications do not act independently, but form a complete module to coordinate and work together before the onset of the disease, and transmit a strong warning signal. The key markers detected by this algorithm are more sensitive and effective in the early warning of disease. Hence, a new method related to key markers is proposed for the study of diabetic microvascular lesions. In clinical prediction and diagnosis, doctors can use key markers to give early warning of individual diseases and make early intervention.

Effects of CSF1R/p-ERK1/2 signaling pathway on RF/6A cells under high glucose conditions

OBJECTIVE

This study analyzed how high glucose affects CSF1R and p-ERK1/2 expression in RF/6A cells.

METHODS

The cells were cultured as high glucose (HG) and normal control (C) groups, and CSF1R shRNA was introduced. Real time PCR was used to detect the expression of CSF1R and p-ERK1/2 mRNA. Western blot was used to detect the expression of CSF1R and p-ERK1/2 proteins. Cell Counting Kit 8 (CCK-8) method was used to detect cell proliferation, while flow cytometry was used to detect apoptosis in HREC.

RESULTS

Real-time PCR showed significantly raised CSF1R mRNA expression in HG. CSF1R inhibition lowered HG + LV shCSF1R CSF1R mRNA levels. Western blotting revealed higher CSF1R and p-ERK1/2 protein expression in HG than in C. Their expression level dropped after CSF1R inhibition. The number of tube-forming cells was higher in HG than in C, which reduced after CSF1R suppression. Inhibiting CSF1R also decreased cell proliferation and raised apoptosis.

CONCLUSION

Overall, under high glucose, CSF1R and p-ERK1/2 were highly expressed, leading to reduced cellular activity, and CSF1R inhibition helped alleviate this effect.

CSANet: a lightweight channel and spatial attention neural network for grading diabetic retinopathy with optical coherence tomography angiography

Background

Diabetic retinopathy (DR) is one of the most common eye diseases. Convolutional neural networks (CNNs) have proven to be a powerful tool for learning DR features; however, accurate DR grading remains challenging due to the small lesions in optical coherence tomography angiography (OCTA) images and the small number of samples.

Methods

In this article, we developed a novel deep-learning framework to achieve the fine-grained classification of DR; that is, the lightweight channel and spatial attention network (CSANet). Our CSANet comprises two modules: the baseline model, and the hybrid attention module (HAM) based on spatial attention and channel attention. The spatial attention module is used to mine small lesions and obtain a set of spatial position weights to address the problem of small lesions being ignored during the convolution process. The channel attention module uses a set of channel weights to focus on useful features and suppress irrelevant features.

Results

The extensive experimental results for the OCTA-DR and diabetic retinopathy analysis challenge (DRAC) 2022 data sets showed that the CSANet achieved state-of-the-art DR grading results, showing the effectiveness of the proposed model. The CSANet had an accuracy rate of 97.41% for the OCTA-DR data set and 85.71% for the DRAC 2022 data set.

Conclusions

Extensive experiments using the OCTA-DR and DRAC 2022 data sets showed that the proposed model effectively mitigated the problems of mutual confusion between DRs of different severity and small lesions being neglected in the convolution process, and thus improved the accuracy of DR classification.

An AI-based novel system for predicting respiratory support in COVID-19 patients through CT imaging analysis

The proposed AI-based diagnostic system aims to predict the respiratory support required for COVID-19 patients by analyzing the correlation between COVID-19 lesions and the level of respiratory support provided to the patients. Computed tomography (CT) imaging will be used to analyze the three levels of respiratory support received by the patient: Level 0 (minimum support), Level 1 (non-invasive support such as soft oxygen), and Level 2 (invasive support such as mechanical ventilation). The system will begin by segmenting the COVID-19 lesions from the CT images and creating an appearance model for each lesion using a 2D, rotation-invariant, Markov-Gibbs random field (MGRF) model. Three MGRF-based models will be created, one for each level of respiratory support. This suggests that the system will be able to differentiate between different levels of severity in COVID-19 patients. The system will decide for each patient using a neural network-based fusion system, which combines the estimates of the Gibbs energy from the three MGRF-based models. The proposed system were assessed using 307 COVID-19-infected patients, achieving an accuracy of [Formula: see text], a sensitivity of [Formula: see text], and a specificity of [Formula: see text], indicating a high level of prediction accuracy.

Artificial intelligence and hemodynamic studies in optical coherence tomography angiography for diabetic retinopathy evaluation: A review

Diabetic retinopathy (DR) is a rapidly emerging retinal abnormality worldwide, which can cause significant vision loss by disrupting the vascular structure in the retina. Recently, optical coherence tomography angiography (OCTA) has emerged as an effective imaging tool for diagnosing and monitoring DR. OCTA produces high-quality 3-dimensional images and provides deeper visualization of retinal vessel capillaries and plexuses. The clinical relevance of OCTA in detecting, classifying, and planning therapeutic procedures for DR patients has been highlighted in various studies. Quantitative indicators obtained from OCTA, such as blood vessel segmentation of the retina, foveal avascular zone (FAZ) extraction, retinal blood vessel density, blood velocity, flow rate, capillary vessel pressure, and retinal oxygen extraction, have been identified as crucial hemodynamic features for screening DR using computer-aided systems in artificial intelligence (AI). AI has the potential to assist physicians and ophthalmologists in developing new treatment options. In this review, we explore how OCTA has impacted the future of DR screening and early diagnosis. It also focuses on how analysis methods have evolved over time in clinical trials. The future of OCTA imaging and its continued use in AI-assisted analysis is promising and will undoubtedly enhance the clinical management of DR.

Identification of differential immune cells and related diagnostic genes in patients with diabetic retinopathy

BACKGROUND

Diabetic retinopathy (DR) is a frequent microvascular abnormality associated with diabetes mellitus. The loss of retinal immunity is an important underlying mechanism of the DR pathogenesis, including the change in retinal immunosuppressive characteristics and the blood-retinal barrier disturbances. Therefore, this investigation screens immune-associated biomarkers in the retina of DR patients.

METHODS

In this investigation, the differential expression genes (DEGs) were acquired from Gene Expression Omnibus data GSE102485. The relative expression of 22 immune cell types in each sample was calculated by CIBERSORT analysis based on gene expression profile. The core module closely associated with immune infiltration was also screened by weighted gene co-expression network analysis (WGCNA). The overlapping DEGs and module genes were the differentially expressed immune-related genes (DEIRGs). With the help of the genes/proteins (STRING) database and MCODE plug-in, the protein-protein interaction (PPI) network hub genes were screened. Furthermore, the miRNA-hub genes and transcription factor (TF)-hub gene regulatory network were used to explain the possible signal pathways in DR. The hub genes verification was carried out by Polymerase Chain Reaction. Lastly, select CSF1R and its related pathway factor p-ERK1/2 to verify their expression in RF/6A under normal and high glucose environments.

RESULTS

A total of 3583 principle DEGs, that enriched immune-related GO terms and infection-related pathways were identified. CIBERSORT analysis showed that naive B cells, M2 macrophages, eosinophils, and neutrophil infiltration were significantly different. After intersecting 3583 DEGs, 168 DEIRGs and 181 module genes were identified. Furthermore, 15 hub genes, TYROBP, FCGR3A, CD163, FCGR2A, PTPRC, TLR2, CD14, VSIG4, HCK, CSF1R, LILRB2, ITGAM, CTSS, CD86, and LY86, were identified via PPI network. The identified hub genes were up-regulated in DR and showed a high DR diagnostic value. Regulatory networks of the miRNA- and TF-hub genes can help understand the etiology of disease at the genetic level and optimize treatment strategy. CD14, VSIG4, HCK, and CSF1R were verified to be highly expressed in the vitreous of patients with DR. n RF/6A, CSF1R, and p-ERK1/2 were significantly overexpressed under high glucose conditions, with a statistically significant difference.

CONCLUSION

This investigation identified 15 genes (TYROBP, FCGR3A, CD163, FCGR2A, PTPRC, TLR2, CD14, VSIG4, HCK, CSF1R, LILRB2, ITGAM, CTSS, CD86, and LY86) as hub DR genes, which may serve as a new potential point for the diagnosis and treatment of DR. CSF1R/p-ERK1/2 signaling may promotes the development of retinal neovascularization.

Vison transformer adapter-based hyperbolic embeddings for multi-lesion segmentation in diabetic retinopathy

Diabetic Retinopathy (DR) is a major cause of blindness worldwide. Early detection and treatment are crucial to prevent vision loss, making accurate and timely diagnosis critical. Deep learning technology has shown promise in the automated diagnosis of DR, and in particular, multi-lesion segmentation tasks. In this paper, we propose a novel Transformer-based model for DR segmentation that incorporates hyperbolic embeddings and a spatial prior module. The proposed model is primarily built on a traditional Vision Transformer encoder and further enhanced by incorporating a spatial prior module for image convolution and feature continuity, followed by feature interaction processing using the spatial feature injector and extractor. Hyperbolic embeddings are used to classify feature matrices from the model at the pixel level. We evaluated the proposed model's performance on the publicly available datasets and compared it with other widely used DR segmentation models. The results show that our model outperforms these widely used DR segmentation models. The incorporation of hyperbolic embeddings and a spatial prior module into the Vision Transformer-based model significantly improves the accuracy of DR segmentation. The hyperbolic embeddings enable us to better capture the underlying geometric structure of the feature matrices, which is important for accurate segmentation. The spatial prior module improves the continuity of the features and helps to better distinguish between lesions and normal tissues. Overall, our proposed model has potential for clinical use in automated DR diagnosis, improving accuracy and speed of diagnosis. Our study shows that the integration of hyperbolic embeddings and a spatial prior module with a Vision Transformer-based model improves the performance of DR segmentation models. Future research can explore the application of our model to other medical imaging tasks, as well as further optimization and validation in real-world clinical settings.

Enhanced Deep Learning Model for Classification of Retinal Optical Coherence Tomography Images

Retinal optical coherence tomography (OCT) imaging is a valuable tool for assessing the condition of the back part of the eye. The condition has a great effect on the specificity of diagnosis, the monitoring of many physiological and pathological procedures, and the response and evaluation of therapeutic effectiveness in various fields of clinical practices, including primary eye diseases and systemic diseases such as diabetes. Therefore, precise diagnosis, classification, and automated image analysis models are crucial. In this paper, we propose an enhanced optical coherence tomography (EOCT) model to classify retinal OCT based on modified ResNet (50) and random forest algorithms, which are used in the proposed study's training strategy to enhance performance. The Adam optimizer is applied during the training process to increase the efficiency of the ResNet (50) model compared with the common pre-trained models, such as spatial separable convolutions and visual geometry group (VGG) (16). The experimentation results show that the sensitivity, specificity, precision, negative predictive value, false discovery rate, false negative rate accuracy, and Matthew's correlation coefficient are 0.9836, 0.9615, 0.9740, 0.9756, 0.0385, 0.0260, 0.0164, 0.9747, 0.9788, and 0.9474, respectively.

Flavoprotein fluorescence elevation is a marker of mitochondrial oxidative stress in patients with retinal disease

Purpose

Recent studies of glaucoma, age-related macular degeneration, and diabetic retinopathy have demonstrated that flavoprotein fluorescence (FPF) can be utilized non-invasively as an indicator of mitochondrial oxidative stress in the retina. However, a comprehensive assessment of the validity and reliability of FPF in differentiating between healthy and diseased eyes across multiple disease states is lacking. Here, we evaluate the sensitivity and specificity of FPF in discriminating between healthy and diseased eyes in four leading causes of visual impairment worldwide, one of which has not been previously evaluated using FPF. We also evaluate the association between FPF and visual acuity.

Methods

A total of 88 eyes [21 eyes of 21 unaffected controls, 20 eyes from 20 retinal vein occlusion (RVO) patients, 20 eyes from 20 diabetic retinopathy (DR) patients, 17 eyes from 17 chronic exudative age-related macular degeneration (exudative AMD) patients, and 10 eyes from 10 central serous retinopathy (CSR) patients] were included in the present cross-sectional observational study. Eyes were imaged non-invasively using a specially configured fundus camera OcuMet Beacon® (OcuSciences, Ann Arbor, MI). The macula was illuminated using a narrow bandwidth blue light (455 - 470 nm) and fluorescence was recorded using a narrow notch filter to match the peak emission of flavoproteins from 520 to 540 nm. AUROC analysis was used to determine the sensitivity of FPF in discriminating between diseased eyes and healthy eyes. Nonparametric Kruskal-Wallis Tests with post-hoc Mann Whitney U tests with the Holm-Bonferroni correction were performed to assess differences in FPF intensity, FPF heterogeneity, and best corrected visual acuity (BCVA) between the five groups. Spearman rank correlation coefficients were calculated to assess the relationship between FPF and BCVA.

Results

AUROC analysis indicated that FPF intensity is highly sensitive for detecting disease, particularly for exudative AMD subjects (0.989; 95% CI = 0.963 - 1.000, p=3.0 x 107). A significant difference was detected between the FPF intensity, FPF heterogeneity, and BCVA in all four disease states compared to unaffected controls (Kruskal-Wallis Tests, p = 1.06 x 10-8, p = 0.002, p = 5.54 x 10-8, respectively). Compared to healthy controls, FPF intensity values were significantly higher in RVO, DR, exudative AMD, and CSR (p < 0.001, p < 0.001, p < 0.001, and p = 0.001, respectively). Spearman rank correlation coefficient between FPF intensity and BCVA was ρ = 0.595 (p = 9.62 x 10-10).

Conclusions

Despite variations in structural retinal findings, FPF was found to be highly sensitive for detecting retinal disease. Significant FPF elevation were seen in all four disease states, with the exudative AMD patients exhibiting the highest FPF values compared to DR, CSR, and RVO subjects. This is consistent with the hypothesis that there is elevated oxidative stress in all of these conditions as previously demonstrated by blood studies. FPF intensity is moderately correlated with the late-in disease-marker BCVA, which suggests that the degree of FPF elevation can be used as a metabolic indicator of disease severity.

Anatomical and Functional Effects of Oral Administration of Curcuma Longa and Boswellia Serrata Combination in Patients with Treatment-Naïve Diabetic Macular Edema

Anti-vascular endothelial growth factor nowdays represents the standard of care for diabetic macular edema (DME). Nevertheless, the burden of injections worldwide has created tremendous stress on the healthcare system during the COVID-19 pandemic. The aim of this study was to investigate the effects of the oral administration of Curcuma longa and Boswellia serrata (Retimix®) in patients with non-proliferative diabetic retinopathy (DR) and treatment-naïve DME < 400 μm, managed during the COVID-19 pandemic. In this retrospective study, patients were enrolled and divided into two groups, one undergoing observation (Group A, n 12) and one receiving one sachet a day of Retimix® (Group B, n 49). Best-corrected visual acuity (BCVA) and central macular thickness (CMT) measured by spectral-domain optical coherence tomography were performed at baseline, then at one and six months. A mixed-design ANOVA was calculated to determine whether the change in CMT and BCVA over time differed according to the consumption of Retimix®. The interaction between time and treatment was significant, with F (1.032, 102.168) = 14.416; η2 = 0.127; p < 0.001, indicating that the change in terms of CMT and BCVA over time among groups was significantly different. In conclusion, our results show the efficacy of Curcuma longa and Boswellia serrata in patients with non-proliferative DR and treatment-naïve DME in maintaining baseline CMT and BCVA values over time.