Search

Background: Doctors can detect symptoms of diabetic retinopathy (DR) early by using retinal ophthalmoscopy, and they can improve diagnostic efficiency with the assistance of deep learning to select treatments and support personnel workflow. Conventionally, most deep learning methods for DR diagnosis categorize retinal ophthalmoscopy images into training and validation data sets according to the 80/20 rule, and they use the synthetic minority oversampling technique (SMOTE) in data processing (e.g., rotating, scaling, and translating training images) to increase the number of training samples. Oversampling training may lead to overfitting of the training model. Therefore, untrained or unverified images can yield erroneous predictions. Although the accuracy of prediction results is 90%-99%, this overfitting of training data may distort training module variables., Results: This study uses a 2-stage training method to solve the overfitting problem. In the training phase, to build the model, the Learning module 1 used to identify the DR and no-DR. The Learning module 2 on SMOTE synthetic datasets to identify the mild-NPDR, moderate NPDR, severe NPDR and proliferative DR classification. These two modules also used early stopping and data dividing methods to reduce overfitting by oversampling. In the test phase, we use the DIARETDB0, DIARETDB1, eOphtha, MESSIDOR, and DRIVE datasets to evaluate the performance of the training network. The prediction accuracy achieved to 85.38%, 84.27%, 85.75%, 86.73%, and 92.5%., Conclusions: Based on the experiment, a general deep learning model for detecting DR was developed, and it could be used with all DR databases. We provided a simple method of addressing the imbalance of DR databases, and this method can be used with other medical images., (© 2021. The Author(s).)

Background: Diabetic retinopathy (DR) is indicated as a major cause of blindness in the world. Emerging evidence supports the interaction of iron metabolism with diabetes. However, little research is available concerning the relationship between iron metabolism and DR. The intent of this paper is to describe the correlation between serum iron and the occurrence of DR., Methods: A total of 5321 participants who underwent related examinations as part of the National Health and Nutrition Examination Survey (2005-2008) were included. DR was defined by the criteria of the Early Treatment for Diabetic Retinopathy Study based on nonmydriatic fundus photography. The cutoff point of serum iron for DR was explored by the receiver operating characteristics curve. The relationship of serum iron with the occurrence of DR was explored by multivariate logistic regression models., Results: Participants with DR had significantly lower serum iron than the control group. Serum iron was negatively correlated with the occurrence of DR after the adjustment of pertinent variables (an odds ratio (OR) of 0.995 (95% CI: 0.992-0.999)). After dividing serum iron into quartiles, the third quartile was associated with DR with an OR of 0.601 (95% CI: 0.418-0.863). Furthermore, the cutoff point of serum iron had an inverse relationship for the occurrence of DR with an OR of 0.766 (95% CI: 0.597-0.984)., Conclusion: Serum iron has an inverse association with the occurrence of DR in diabetic adults. The assessment of serum iron levels might be a part of follow-up visits with diabetic patients.

Purpose: To improve disease severity classification from fundus images using a hybrid architecture with symptom awareness for diabetic retinopathy (DR)., Methods: We used 26,699 fundus images of 17,834 diabetic patients from three Taiwanese hospitals collected in 2007 to 2018 for DR severity classification. Thirty-seven ophthalmologists verified the images using lesion annotation and severity classification as the ground truth. Two deep learning fusion architectures were proposed: late fusion, which combines lesion and severity classification models in parallel using a postprocessing procedure, and two-stage early fusion, which combines lesion detection and classification models sequentially and mimics the decision-making process of ophthalmologists. Messidor-2 was used with 1748 images to evaluate and benchmark the performance of the architecture. The primary evaluation metrics were classification accuracy, weighted κ statistic, and area under the receiver operating characteristic curve (AUC)., Results: For hospital data, a hybrid architecture achieved a good detection rate, with accuracy and weighted κ of 84.29% and 84.01%, respectively, for five-class DR grading. It also classified the images of early stage DR more accurately than conventional algorithms. The Messidor-2 model achieved an AUC of 97.09% in referral DR detection compared to AUC of 85% to 99% for state-of-the-art algorithms that learned from a larger database., Conclusions: Our hybrid architectures strengthened and extracted characteristics from DR images, while improving the performance of DR grading, thereby increasing the robustness and confidence of the architectures for general use., Translational Relevance: The proposed fusion architectures can enable faster and more accurate diagnosis of various DR pathologies than that obtained in current manual clinical practice., Competing Interests: Disclosure: V.S. Tseng, None; C.-L. Chen, None; C.-M. Liang, None; M.-C. Tai, None; J.-T. Liu, None; P.-Y. Wu, None; M.-S. Deng, None; Y.-W. Lee, None; T.-Y. Huang, None; Y.-H. Chen, None, (Copyright 2020 The Authors.)

It has rarely been studied whether the presence and severity of diabetic retinopathy (DR) could influence the renal disease progression among all chronic kidney disease (CKD) diabetic patients. This study investigates the characteristics of diabetic patients, with different stages of chronic kidney disease (CKD), according to the occurrence of diabetic retinopathy and determines the influence of retinopathy in the deterioration of renal function. We conduct a multicenter, longitudinal cohort study based on the Epidemiology and Risk Factors Surveillance of the CKD project (2008⁻2013) and the National Health Insurance Research Database (NHIRD) (2001⁻2013). A total of 4050 diabetic patients with CKD, 20⁻85 years of age, from 14 hospitals and the community are included in this study. As compared to CKD patients without DR, CKD patients with DR have a lower baseline estimated glomerular filtration rate (eGFR) (39.17 ± 30.36 mL/min per 1.73 m² vs. 54.38 ± 33.67 mL/min per 1.73 m² ); poorer glycemic control (higher glycated hemoglobin (HbA1c) 7.85 ± 4.97 vs. 7.29 ± 4.02, p < 0.01); higher proteinuria (urine protein-to-creatinine ratio (UPCR )1.94 ± 2.96 g/dL vs. 0.91 ± 2.11 g/dL, p < 0.01); more anemia (Hb 11.22 ± 2.43 g/dL vs. 12.39 ± 3.85 g/dL, p < 0.01), and more hypoalbuminemia (3.88 ± 0.95 g/dL vs. 4.16 ± 1.74 g/dL, p < 0.01). Later stage (stage 3b⁻5) CKD patients with DR had significantly higher CKD progression compared with patients without DR (OR (odds ratio) 1.66 (1.36⁻2.02)). Patients with proliferative DR had significantly higher CKD progression events compared to patients with non-proliferative DR (OR 2.18 (1.71⁻2.78)). The presence and severity of DR is a risk factor for CKD progression among our Taiwanese CKD patients with diabetes. Prevention and early detection of DR are important and DR should be routinely screened as early as possible among diabetic CKD patients.

Abstract Background The safety of Laser-assisted in situ keratomileusis (LASIK) in aircrew was unclear, in addition, LASIK was not yet approved for aircrew of Taiwan Air Force. This study was aimed to evaluate visual performance in LASIK eyes in hypoxic and twilight environment. Methods 48 myopic eyes of 24 subjects enrolled in this study were divided into LASIK group and control group. Subjects were exposed in hypoxic (15% O 2) and mesopic (3 cd/m2) environment. Visual performance was evaluated using the Early Treatment of Diabetic Retinopathy Study (ETDRS) visual chart, and Functional Acuity Contrast Test (FACT) before and after the expirement. Physiological parameters of all subjects were measured and recorded throughout the experiment. Results There was no significant difference of the two groups regarding their age, height, weight, and BMI. There is significant difference of preoperative spherical refractive error between the two groups. The results of physiological parameters were similar between two groups. Under normoxic conditions, there were no significant difference regarding distant vision in photopic and mesopic environments, so as for near vision. As a whole, the contrast sensitivity of the LASIK group were lowered than that of the control group about 35%, under whether normoxic or hypoxic conditions; photopic or mesopic circumstances. Under normoxic conditions, the measured accommodation of the LASIK group were 21% lowered than that of the control group and 31% lowered under hypoxic circumstances. Conclusion There was no significant difference of visual acuity between the two groups regarding hypoxic and mesopic environment, but reduced contrast sensitivity was significant in LASIK group as compared to those of the control group. Accommodation was significantly lowered in LASIK group, compared with control group, in hypoxic environment. Whether postoperative visual performance after LASIK in aircrew during flying duty is safe might need further investigation. [ABSTRACT FROM AUTHOR]