Ocular Disease Detection with Deep Learning (Fine-Grained Image Categorization) Applied to Ocular B-Scan Ultrasound Images.

INTRODUCTION: The aim of this work is to develop a deep learning (DL) system for rapidly and accurately screening for intraocular tumor (IOT), retinal detachment (RD), vitreous hemorrhage (VH), and posterior scleral staphyloma (PSS) using ocular B-scan ultrasound images. METHODS: Ultrasound images from five clinically confirmed categories, including vitreous hemorrhage, retinal detachment, intraocular tumor, posterior scleral staphyloma, and normal eyes, were used to develop and evaluate a fine-grained classification system (the Dual-Path Lesion Attention Network, DPLA-Net). Images were derived from five centers scanned by different sonographers and divided into training, validation, and test sets in a ratio of 7:1:2. Two senior ophthalmologists and four junior ophthalmologists were recruited to evaluate the system's performance. RESULTS: This multi-center cross-sectional study was conducted in six hospitals in China. A total of 6054 ultrasound images were collected; 4758 images were used for the training and validation of the system, and 1296 images were used as a testing set. DPLA-Net achieved a mean accuracy of 0.943 in the testing set, and the area under the curve was 0.988 for IOT, 0.997 for RD, 0.994 for PSS, 0.988 for VH, and 0.993 for normal. With the help of DPLA-Net, the accuracy of the four junior ophthalmologists improved from 0.696 (95% confidence interval [CI] 0.684-0.707) to 0.919 (95% CI 0.912-0.926, p < 0.001), and the time used for classifying each image reduced from 16.84 ± 2.34 s to 10.09 ± 1.79 s. CONCLUSIONS: The proposed DPLA-Net showed high accuracy for screening and classifying multiple ophthalmic diseases using B-scan ultrasound images across mutiple centers. Moreover, the system can promote the efficiency of classification by ophthalmologists.

Lesion detection with fine-grained image categorization for myopic traction maculopathy (MTM) using optical coherence tomography.

BACKGROUND: Myopic traction maculopathy (MTM) are retinal disorder caused by traction force on the macula, which can lead to varying degrees of vision loss in eyes with high myopia. Optical coherence tomography (OCT) is an effective imaging technique for diagnosing, detecting and classifying retinopathy. MTM has been classified into different patterns by OCT, corresponding to different clinical strategies. PURPOSE: We aimed to engineer a deep learning model that can automatically identify MTM in highly myopic (HM) eyes using OCT images. METHODS: A five-class classification model was developed using 2837 OCT images from 958 HM patients. We adopted a ResNet-34 architecture to train the model to identify MTM: no MTM (class 0), extra-foveal maculoschisis (class 1), inner lamellar macular hole (class 2), outer foveoschisis (class 3), and discontinuity or detachment of foveal outer hyperreflective layers (class 4). An independent test set of 604 images from 173 HM patients was used to evaluate the model's performance. Classification performance was assessed according to the area under the curve (AUC), accuracy, sensitivity, specificity. RESULTS: Our model exhibited a high training performance for classification (F1-score of 0.953; AUCs of 0.961 to 0.998). In test set, it achieved sensitivities (91.67%-97.78 %) and specificities (98.33%-99.17%) as good as, or better than, those of experienced clinicians. Heatmaps were generated to provide visual explanations. CONCLUSIONS: We established a deep learning model for MTM classification using OCT images. This model performed equally well or better than retinal specialists and is suitable for large-scale screening and identifying MTM in HM eyes.

Artificial Intelligence-Based Quantification of Central Macular Fluid Volume and VA Prediction for Diabetic Macular Edema Using OCT Images.

INTRODUCTION: We studied the correlation of central macular fluid volume (CMFV) and central subfield thickness (CST) with best-corrected visual acuity (BCVA) in treatment-naïve eyes with diabetic macular edema (DME) 1 month after anti-vascular endothelial growth factor (VEGF) therapy. METHODS: This retrospective cohort study investigated eyes that received anti-VEGF therapy. All participants underwent comprehensive examinations and optical coherence tomography (OCT) volume scans at baseline (M0) and 1 month after the first treatment (M1). Two deep learning models were separately developed to automatically measure the CMFV and the CST. Correlations were analyzed between the CMFV and the logMAR BCVA at M0 and logMAR BCVA at M1. The area under the receiver operating characteristic curve (AUROC) of CMFV and CST for predicting eyes with BCVA [Formula: see text] 20/40 at M1 was analyzed. RESULTS: This study included 156 DME eyes from 89 patients. The median CMFV decreased from 0.272 (0.061-0.568) at M0 to 0.096 (0.018-0.307) mm3 at M1. The CST decreased from 414 (293-575) to 322 (252-430) µm. The logMAR BCVA decreased from 0.523 (0.301-0.817) to 0.398 (0.222-0.699). Multivariate analysis demonstrated that the CMFV was the only significant factor for logMAR BCVA at both M0 (ß = 0.199, p = 0.047) and M1 (ß = 0.279, p = 0.004). The AUROC of CMFV for predicting eyes with BCVA [Formula: see text] 20/40 at M1 was 0.72, and the AUROC of CST was 0.69. CONCLUSIONS: Anti-VEGF therapy is an effective treatment for DME. Automated measured CMFV is a more accurate prognostic factor than CST for the initial anti-VEGF treatment outcome of DME.

Quantitative evaluation of dissociated optic nerve fibre layer (DONFL) following idiopathic macular hole surgery.

OBJECTIVES: To quantitatively evaluate concentric macular dark spots (CMDS) on spectral-domain optical coherence tomography (SD-OCT) to determine the morphological characteristics of dissociated optic nerve fibre layer (DONFL) following the performance of internal limiting membrane (ILM) peeling in patients with full-thickness idiopathic macular hole (IMH) closure. METHODS: Retrospective study on patients who underwent a vitrectomy with ILM peeling procedure. BCVA, cross-sectional OCT scans, and three-dimensional reconstructions of en face OCT scans were analysed preoperatively, at 2, 6, 12 months post-operatively. A novel image analysis technique was used to automatically measure DONFL logical properties through the radius, area, the nerve fibre layer dissociation index (NFLDI), and depth of the CMDS. RESULTS: 53 eyes of 51 patients were included, and the mean follow-up was 11.53 ± 6.26 months. CMDS was found in 46 (86.79%) eyes within 2 months after ILM peeling and 50 (94.34%) eyes within 6 months after ILM peeling. CMDS concentrated on the temporal side of the macula in all 50 eyes (100%) at first detection. The area, NFLDI, and depth of CMDS in four quadrants developed significantly during the postoperative 6 months (p < 0.05), and then these changes slowed down and remained unchanged 12 months post-operatively. The morphological changes in the temporal quadrant were significantly greater than those in other quadrants at 2, 6, 12 months (all p < 0.05) post-operatively. CONCLUSIONS: CMDS mostly appeared and concentrated on the temporal side of the macula in IMHs within two months after ILM peeling and progressed within 6 months and remained unchanged after 12 months.

Analysis of Retinal Microstructure in Eyes with Dissociated Optic Nerve Fiber Layer (DONFL) Appearance following Idiopathic Macular Hole Surgery: An Optical Coherence Tomography Study.

(1) Purpose: This study aimed to evaluate morphological changes of the retina in eyes with dissociated optic nerve fiber layer (DONFL) appearance following internal limiting membrane (ILM) peeling for full-thickness idiopathic macular hole (IMH) on spectral-domain optical coherence tomography (SD-OCT). (2) Methods: We retrospectively analyzed 39 eyes of 39 patients with type 1 macular hole closure after a vitrectomy with ILM peeling procedure at a six-month minimum postoperative follow-up. The retinal thickness maps and cross-sectional OCT images were obtained from a clinical OCT device. The cross-sectional area of the retinal nerve fiber layer (RNFL) on cross-sectional OCT images was manually measured by ImageJ software. (3) Results: The inner retinal layers (IRLs) thickness thinned down much more in the temporal quadrant than in nasal quadrants at 2 and 6 months postoperatively (p < 0.001). However, the cross-sectional area of the RNFL did not change significantly at 2 and 6 months postoperatively (p > 0.05) when compared to preoperative data. In addition, the thinning of the IRL did not correlate with the best-corrected visual acuity (BCVA) at 6 months postoperatively. (4) Conclusions: The thickness of the IRL decreased in eyes with a DONFL appearance after ILM peeling for IMH. The thickness of the IRL decreased more in the temporal retina than in the nasal retina, but the change did not affect BCVA during the 6 months after surgery.

OIMHS: An Optical Coherence Tomography Image Dataset Based on Macular Hole Manual Segmentation.

Macular holes, one of the most common macular diseases, require timely treatment. The morphological changes on optical coherence tomography (OCT) images provided an opportunity for direct observation of the disease, and accurate segmentation was needed to identify and quantify the lesions. Developments of such algorithms had been obstructed by a lack of high-quality datasets (the OCT images and the corresponding gold standard macular hole segmentation labels), especially for supervised learning-based segmentation algorithms. In such context, we established a large OCT image macular hole segmentation (OIMHS) dataset with 3859 B-scan images of 119 patients, and each image provided four segmentation labels: retina, macular hole, intraretinal cysts, and choroid. This dataset offered an excellent opportunity for investigating the accuracy and reliability of different segmentation algorithms for macular holes and a new research insight into the further development of clinical research for macular diseases, which included the retina, lesions, and choroid in quantitative analyses.

Association of sex with the global burden of vision impairment caused by neonatal preterm birth: An analysis from the global burden of disease study 2019.

Aims: To investigate the sex-specific global burden of neonatal preterm birth (NPB) vision impairment by year, age, and socioeconomic status using years lived with disability (YLDs). Methods: The global, regional, and national sex-specific YLD numbers, crude YLD rates, and age-standardized YLD rates of NPB-related moderate and severe vision loss and blindness were obtained from the Global Burden of Disease Study 2019. The Wilcoxon test and linear regression were used to investigate the relationship between sex difference in age-standardized YLD rates and the Human Development Index (HDI). Results: Between 1990 and 2019, the gender disparity in age-standardized YLD rates for NPB-related vision impairment remained stable, increasing from 10.2 [95% uncertainty interval (UI) 6.7-14.6] to 10.4 (95% UI 6.9-15.0) for men and 10.3 (95% UI 6.8-14.7) to 10.7 (95% UI 7.2-15.1) for women, with women consistently having higher age-standardized YLD rates. Between the ages of 25 and 75, women had higher YLD rates than males, with the biggest disparity in the 60-64 age group. In 2019, sex difference in age-standardized YLD rates across 195 nations was statistically significant. Women had higher age-standardized YLD rates than men in both low (Z = -3.53, p < 0.001) and very high HDI countries (Z = -4.75, p < 0.001). Additionally, age-standardized YLD rates were found to be adversely associated with HDI (male: Standardized ß = -0.435, female: Standardized ß = -0.440; p < 0.001). Conclusion: Despite advancements in worldwide NPB health care, sexual differences in NPB-related vision impairment burden showed little change. Female had higher burden than male, particularly in low and very high socioeconomic status countries.

Automatic Screening and Identifying Myopic Maculopathy on Optical Coherence Tomography Images Using Deep Learning.

Purpose: The purpose of this study was to engineer deep learning (DL) models that can identify myopic maculopathy in patients with high myopia based on optical coherence tomography (OCT) images. Methods: An artificial intelligence (AI) system was developed using 2342 qualified OCT macular images from 1041 patients with pathologic myopia admitted to the Affiliated Eye Hospital of Wenzhou Medical University (WMU). We adopted an ResNeSt101 architecture to train five independent models to identify the following five myopic maculopathies: macular choroidal thinning, macular Bruch membrane (BM) defects, subretinal hyper-reflective material (SHRM), myopic traction maculopathy (MTM), and dome-shaped macula (DSM). We tested the models with an independent test dataset that included 450 images obtained from 297 patients with high myopia. Focal loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index. The performance was quantified using the area under the receiver operating characteristic (AUC), sensitivity, specificity, and confusion matrix. Results: For the identification of myopic maculopathy, the AUCs of receiver operating characteristic (ROC) curves were 0.927 to 0.974 for 5 myopic maculopathies. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists (56.16-99.73%). The diagnosis of it is also interpretable that we provide visual explanations clearly via heatmaps. Conclusions: We developed a convolutional neural network (CNN)-based DL AI system for detection and classification of myopic maculopathy in patients with high myopia using OCT macular images. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists. Translational Relevance: This AI system can be widely applied in sophisticated situations in large-scale high myopia screening.

Winemaking Characteristics of Red-Fleshed Dragon Fruit from Three Locations in Guizhou Province, China.

The aim of this study was to identify the locations and harvest months in Guizhou province, China, producing the most suitable red dragon fruit (Hylocereus polyrhizus) for winemaking. Fruit from Guanling, Luodian and Zhenfeng counties was harvested separately from successive fruit cycles in August, September and October, respectively. The key traits measured were fruit weight, pulp yield, soluble solids content, and titratable acid. Wine characteristics measured were alcohol content, total carbohydrates, titratable acidity, volatile acidity, and betacyanin content. The overall suitability of fruit from each location for winemaking was evaluated using a multi-factor, unweighted, scorecard. On that basis, fruit from Guanling county harvested in August was the most suitable. Fruit from Luodian, and Zhenfeng was most suitable when harvested in August and September, and September, respectively. These results provide a preliminary guide for the sourcing of red dragon fruit from Guizhou for wine production.

Total glucosides of paeony (TGP) alleviates Sjogren's syndrome through inhibiting inflammatory responses in mice.

BACKGROUND: Sjogren's syndrome (SS) is an inflammatory autoimmune disease whose etiology is complicated. Total glucosides of paeony (TGP) has a variety of pharmacological effects. PURPOSE: To evaluate the therapeutic effects of TGP on SS in mice and anti-inflammatory mechanism. STUDY DESIGN: SS animal model was developed from C57BL/6J mice through immunological induction (SS mice) and NOD/ShiltJNju (NOD) mice. Inflammatory cytokines and other related indicators were measured. METHODS: TGP (720, 360, 180 mg/kg) was intragastrically administered for 6 or 16 weeks for SS mice and NOD mice, respectively. Average food and water intake, average body weight, saliva flow, submandibular gland (SMG) and spleen index, and SMG pathology were measured. ELISA was used to evaluate serum inflammatory cytokines in SS mice and autoantigens in NOD mice. Real-time PCR, Western blot and Luminex liquid suspension chip assay were applied to analyze SMG inflammatory cytokines mRNA and protein expression of NOD mice. RESULTS: Compared with SS mice, TGP treatment improved SMG pathological damage. TGP (720 mg/kg) treatment increased saliva flow, and reduced organ indexes and serum IL-6 and IFN-γ concentration. TGP (360 mg/kg) treatment decreased serum IFN-γ concentration. TGP (180 mg/kg) treatment for 6 weeks decreased average body weight. Compared with NOD mice, TGP treatment increased saliva flow from 9 to 15 weeks, decreased body weight, and alleviated pathological damage of SMG after 2 and 16 weeks. After 2 weeks of administration, TGP treatment inhibited serum concentration of SSB/La, SSA/Ro and α-fodrin, decreased TNF-α, IL-1ß and IFN-γ in SMG, and down-regulated protein expressions of BAFF and IL-17A and mRNA expressions of BAFF, TNF-α, IL-17A, CXCL9 and CXCL13 in SMG. After 8 weeks of administration, TGP treatment decreased the concentration of α-fodrin in serum, TNF-α and IL-6 in SMG, and down-regulated mRNA expressions of IL-17A, TNF-α, CXCL9, CXCL13 and BAFF and protein expressions of IL-17A and BAFF in SMG. After 16 weeks of administration, TGP treatment reduced serum SSA/Ro, SSB/La and α-fodrin concentration, and decreased BAFF protein expression and TNF-α, CXCL9, CXCL13, IL-17A, and BAFF mRNA expressions. CONCLUSION: TGP has a certain therapeutic effect on SS mice and NOD mice through inhibiting inflammatory responses.