Retinal images benchmark for the detection of diabetic retinopathy and clinically significant macular edema (CSME)

VEGF promotes diabetic retinopathy by upregulating the PKC/ET/NF-κB/ICAM-1 signaling pathway

Diabetic retinopathy (DR) is a common microvascular complication in patients with diabetes mellitus. DR is caused by chronic hyperglycemia and is characterized by progressive loss of vision because of damage to the retinal microvasculature. In this study, we investigated the regulatory role and clinical significance of the vascular endothelial growth factor (VEGF)/protein kinase C (PKC)/endothelin (ET)/nuclear factor-κB (NF-κB)/intercellular adhesion molecule 1 (ICAM-1) signaling pathway in DR using a rat model. Intraperitoneal injections of the VEGF agonist, streptozotocin (STZ) were used to generate the DR model rats. DR rats treated with the VEGF inhibitor (DR+VEGF inhibitor) were used to study the specific effects of VEGF on DR pathology and the underlying mechanisms. DR and DR+VEGF agonist rats were injected with the PKCβ2 inhibitor, GF109203X to determine the therapeutic potential of blocking the VEGF/PKC/ET/NF-κB/ICAM-1 signaling pathway. The body weights and blood glucose levels of the rats in all groups were evaluated at 16 weeks. DR-related retinal histopathology was analyzed by hematoxylin and eosin staining. ELISA assay was used to estimate the PKC activity in the retinal tissues. Western blotting and RT-qPCR assays were used to analyze the expression levels of PKC-β2, VEGF, ETs, NF-κB, and ICAM-1 in the retinal tissues. Immunohistochemistry was used to analyze VEGF and ICAM-1 expression in the rat retinal tissues. Our results showed that VEGF, ICAM-1, PKCβ2, ET, and NF-κB expression levels as well as PKC activity were significantly increased in the retinal tissues of the DR and DR+VEGF agonist rat groups compared to the control and DR+VEGF inhibitor rat groups. DR and DR+VEGF agonist rats showed significantly lower body weight and significantly higher retinal histopathology scores and blood glucose levels compared to the control and DR+VEGF inhibitor group rats. However, treatment of DR and DR+VEGF agonist rats with GF109203X partially alleviated DR pathology by inhibiting the VEGF/ PKC/ET/NF-κB/ICAM-1 signaling pathway. In summary, our data demonstrated that inhibition of the VEGF/ PKC/ET/NF-κB/ICAM-1 signaling pathway significantly alleviated DR-related pathology in the rat model. Therefore, VEGF/PKC/ET/NF-κB/ICAM-1 signaling axis is a promising therapeutic target for DR.

A critical review on diagnosis of diabetic retinopathy using machine learning and deep learning

Diabetic Retinopathy (DR) is a health condition caused due to Diabetes Mellitus (DM). It causes vision problems and blindness due to disfigurement of human retina. According to statistics, 80% of diabetes patients battling from long diabetic period of 15 to 20 years, suffer from DR. Hence, it has become a dangerous threat to the health and life of people. To overcome DR, manual diagnosis of the disease is feasible but overwhelming and cumbersome at the same time and hence requires a revolutionary method. Thus, such a health condition necessitates primary recognition and diagnosis to prevent DR from developing into severe stages and prevent blindness. Innumerable Machine Learning (ML) models are proposed by researchers across the globe, to achieve this purpose. Various feature extraction techniques are proposed for extraction of DR features for early detection. However, traditional ML models have shown either meagre generalization throughout feature extraction and classification for deploying smaller datasets or consumes more of training time causing inefficiency in prediction while using larger datasets. Hence Deep Learning (DL), a new domain of ML, is introduced. DL models can handle a smaller dataset with help of efficient data processing techniques. However, they generally incorporate larger datasets for their deep architectures to enhance performance in feature extraction and image classification. This paper gives a detailed review on DR, its features, causes, ML models, state-of-the-art DL models, challenges, comparisons and future directions, for early detection of DR.

Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world. In the past few years, artificial intelligence (AI) based approaches have been used to detect and grade DR. Early detection enables appropriate treatment and thus prevents vision loss. For this purpose, both fundus and optical coherence tomography (OCT) images are used to image the retina. Next, Deep-learning (DL)-/machine-learning (ML)-based approaches make it possible to extract features from the images and to detect the presence of DR, grade its severity and segment associated lesions. This review covers the literature dealing with AI approaches to DR such as ML and DL in classification and segmentation that have been published in the open literature within six years (2016-2021). In addition, a comprehensive list of available DR datasets is reported. This list was constructed using both the PICO (P-Patient, I-Intervention, C-Control, O-Outcome) and Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) 2009 search strategies. We summarize a total of 114 published articles which conformed to the scope of the review. In addition, a list of 43 major datasets is presented.

Numerical Computational Study of Photoacoustic Signals from Eye Models to Detect Diabetic Retinopathy

Introduction:

Detection of Diabetic Retinopathy (DR) is essential in clinical ophthalmology as it may prevent sight degradation. In this paper, a complete Photoacoustic (PA) analysis is implemented to detect DR in three different eye models representing a healthy eye as well as two abnormal eyes exhibiting Non-Proliferative Retinopathy (NPDR), and Proliferative Retinopathy (PDR)

Methods & Materials:

Monte Carlo method was used to simulate the interaction of a 0.8 ns duration laser pulse with eye tissues at 750 nm wavelength. Thermal, structural and acoustical analyses were performed using the Finite Element Method (FEM).

Results:

The results showed that there is a significant change in the amplitude of the detected PA signal for abnormal eye tissues in the retina (P < 0.05) as compared to healthy eye tissues. The maximum amplitude of the received PA signal in the NPDR and the PDR eye models is 5% and 33%, respectively, which are greater than those observed in the healthy eye.

Conclusion:

These results may provide insights into using PA imaging to detect DR.