RESUMO
AIM: To develop a deep learning-based model for automatic retinal vascular segmentation, analyzing and comparing parameters under diverse glucose metabolic status (normal, prediabetes, diabetes) and to assess the potential of artificial intelligence (AI) in image segmentation and retinal vascular parameters for predicting prediabetes and diabetes. METHODS: Retinal fundus photos from 200 normal individuals, 200 prediabetic patients, and 200 diabetic patients (600 eyes in total) were used. The U-Net network served as the foundational architecture for retinal artery-vein segmentation. An automatic segmentation and evaluation system for retinal vascular parameters was trained, encompassing 26 parameters. RESULTS: Significant differences were found in retinal vascular parameters across normal, prediabetes, and diabetes groups, including artery diameter (P=0.008), fractal dimension (P=0.000), vein curvature (P=0.003), C-zone artery branching vessel count (P=0.049), C-zone vein branching vessel count (P=0.041), artery branching angle (P=0.005), vein branching angle (P=0.001), artery angle asymmetry degree (P=0.003), vessel length density (P=0.000), and vessel area density (P=0.000), totaling 10 parameters. CONCLUSION: The deep learning-based model facilitates retinal vascular parameter identification and quantification, revealing significant differences. These parameters exhibit potential as biomarkers for prediabetes and diabetes.
RESUMO
AIM: To investigate the impact of hsa_circ_0007482 on the proliferation and apoptosis of human pterygium fibroblasts (HPFs) and its correlation with the severity grades of pterygium. METHODS: Pterygium and normal conjunctival tissues were collected from the superior area of the same patient's eye (n=33). The correlation between pterygium severity and hsa_circ_0007482 expression using quantitative reverse-transcription polymerase chain reaction (RT-qPCR) were analyzed. Three distinct siRNA sequences targeting hsa_circ_0007482, along with a negative control sequence, were transfected into HPFs. Cell proliferation was assessed using the cell counting kit-8. Expression levels of Ki67, proliferating cell nuclear antigen (PCNA), Cyclin D1, Bax, B-cell lymphoma-2 (Bcl-2), and Caspase-3 were measured via RT-qPCR. Immunofluorescence staining was employed to detect Ki67 and vimentin expressions. Apoptosis was evaluated using flow cytometry. RESULTS: Hsa_circ_0007482 expression was significantly higher in pterygium tissues compared to normal conjunctival tissues (P<0.001). Positive correlations were observed between hsa_circ_0007482 expression and pterygium severity, thickness, and vascular density. Knockdown of hsa_circ_0007482 inhibited cell proliferation, reducing the mRNA expression of Ki67, PCNA, and Cyclin D1 in HPFs. Hsa_circ_0007482 knockdown induced apoptosis, increasing mRNA expression levels of Bax and Caspase-3, while decreasing Bcl-2 expression in HPFs. Additionally, hsa_circ_0007482 knockdown attenuated vimentin expression in HPFs. CONCLUSION: The downregulation of hsa_circ_0007482 effectively hampers cell proliferation and triggers apoptosis in HPFs. There are discernible positive correlations detected between the expression of hsa_circ_0007482 and the severity of pterygium.
RESUMO
AIM: To evaluate the application of an intelligent diagnostic model for pterygium. METHODS: For intelligent diagnosis of pterygium, the attention mechanisms-SENet, ECANet, CBAM, and Self-Attention-were fused with the lightweight MobileNetV2 model structure to construct a tri-classification model. The study used 1220 images of three types of anterior ocular segments of the pterygium provided by the Eye Hospital of Nanjing Medical University. Conventional classification models-VGG16, ResNet50, MobileNetV2, and EfficientNetB7-were trained on the same dataset for comparison. To evaluate model performance in terms of accuracy, Kappa value, test time, sensitivity, specificity, the area under curve (AUC), and visual heat map, 470 test images of the anterior segment of the pterygium were used. RESULTS: The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%, and the Kappa value of the model was 88.92%. The testing time using the model was 9ms/image in the server and 138ms/image in the local computer. The sensitivity, specificity, and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%, 100%, and 100%, respectively; using anterior segment images in the observation period were 88.30%, 95.32%, and 96.70%, respectively; and using the anterior segment images in the surgery period were 88.18%, 94.44%, and 97.30%, respectively. CONCLUSION: The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.