Digital ray: enhancing cataractous fundus images using style transfer generative adversarial networks to improve retinopathy detection.

BACKGROUND/AIMS: The aim of this study was to develop and evaluate digital ray, based on preoperative and postoperative image pairs using style transfer generative adversarial networks (GANs), to enhance cataractous fundus images for improved retinopathy detection. METHODS: For eligible cataract patients, preoperative and postoperative colour fundus photographs (CFP) and ultra-wide field (UWF) images were captured. Then, both the original CycleGAN and a modified CycleGAN (C2ycleGAN) framework were adopted for image generation and quantitatively compared using Frechet Inception Distance (FID) and Kernel Inception Distance (KID). Additionally, CFP and UWF images from another cataract cohort were used to test model performances. Different panels of ophthalmologists evaluated the quality, authenticity and diagnostic efficacy of the generated images. RESULTS: A total of 959 CFP and 1009 UWF image pairs were included in model development. FID and KID indicated that images generated by C2ycleGAN presented significantly improved quality. Based on ophthalmologists' average ratings, the percentages of inadequate-quality images decreased from 32% to 18.8% for CFP, and from 18.7% to 14.7% for UWF. Only 24.8% and 13.8% of generated CFP and UWF images could be recognised as synthetic. The accuracy of retinopathy detection significantly increased from 78% to 91% for CFP and from 91% to 93% for UWF. For retinopathy subtype diagnosis, the accuracies also increased from 87%-94% to 91%-100% for CFP and from 87%-95% to 93%-97% for UWF. CONCLUSION: Digital ray could generate realistic postoperative CFP and UWF images with enhanced quality and accuracy for overall detection and subtype diagnosis of retinopathies, especially for CFP.\ TRIAL REGISTRATION NUMBER: This study was registered with ClinicalTrials.gov (NCT05491798).

Quantitative assessment of retinochoroidal microvasculature in patients with carotid artery stenosis using OCT angiography.

PURPOSE: To investigate the alterations in retinochoroidal parameters measured by optical coherence tomography (OCT) and OCT angiography (OCTA) in patients with carotid artery stenosis (CAS) and assess their associations with digital subtraction angiography (DSA) data. METHOD: This study enrolled patients diagnosed with CAS and age-matched healthy controls. Both groups underwent OCT and OCTA examinations. DSA and assessment of carotid artery stenosis were performed only in the CAS group. The study evaluated various retinochoroidal parameters from OCT and OCTA, including linear vessel density (LVD), foveal avascular zone (FAZ), choroidal thickness (ChT), and retinal nerve fiber layer (RNFL) thickness. DSA-derived measures included cervical segment (C1) diameter, cavernous segment (C4) diameter, stenosis percentage, ophthalmic artery (OA) filling time, C1-OA filling time, and residual stenosis. RESULTS: A total of 42 eyes from 30 CAS patients and 60 eyes from 30 healthy controls were included. Patients with CAS displayed significantly decreased LVD compared to controls (p < 0.001). Additionally, the CAS group had thinner choroid and RNFL (p = 0.047 and p < 0.001, respectively). Macular LVD negatively correlated with both stenosis percentage and C1-OA filling time (p = 0.010 and p = 0.014, respectively). In patients who underwent carotid artery stenting, preoperative ChT significantly correlated with residual stenosis (Pearson r = -0.480, p = 0.020). CONCLUSION: OCT and OCTA provide a quantitative assessment of retinochoroidal microstructural changes associated with CAS, suggesting potential for noninvasive evaluation of the disease. This might contribute to the prevention of irreversible ocular complications and early detection of CAS. Furthermore, ChT may not only aid in diagnosing CAS more reliably but also offer prognostic information.

Deep Learning Performance of Ultra-Widefield Fundus Imaging for Screening Retinal Lesions in Rural Locales.

Importance: Retinal diseases are the leading cause of irreversible blindness worldwide, and timely detection contributes to prevention of permanent vision loss, especially for patients in rural areas with limited medical resources. Deep learning systems (DLSs) based on fundus images with a 45° field of view have been extensively applied in population screening, while the feasibility of using ultra-widefield (UWF) fundus image-based DLSs to detect retinal lesions in patients in rural areas warrants exploration. Objective: To explore the performance of a DLS for multiple retinal lesion screening using UWF fundus images from patients in rural areas. Design, Setting, and Participants: In this diagnostic study, a previously developed DLS based on UWF fundus images was used to screen for 5 retinal lesions (retinal exudates or drusen, glaucomatous optic neuropathy, retinal hemorrhage, lattice degeneration or retinal breaks, and retinal detachment) in 24 villages of Yangxi County, China, between November 17, 2020, and March 30, 2021. Interventions: The captured images were analyzed by the DLS and ophthalmologists. Main Outcomes and Measures: The performance of the DLS in rural screening was compared with that of the internal validation in the previous model development stage. The image quality, lesion proportion, and complexity of lesion composition were compared between the model development stage and the rural screening stage. Results: A total of 6222 eyes in 3149 participants (1685 women [53.5%]; mean [SD] age, 70.9 [9.1] years) were screened. The DLS achieved a mean (SD) area under the receiver operating characteristic curve (AUC) of 0.918 (0.021) (95% CI, 0.892-0.944) for detecting 5 retinal lesions in the entire data set when applied for patients in rural areas, which was lower than that reported at the model development stage (AUC, 0.998 [0.002] [95% CI, 0.995-1.000]; P < .001). Compared with the fundus images in the model development stage, the fundus images in this rural screening study had an increased frequency of poor quality (13.8% [860 of 6222] vs 0%), increased variation in lesion proportions (0.1% [6 of 6222]-36.5% [2271 of 6222] vs 14.0% [2793 of 19 891]-21.3% [3433 of 16 138]), and an increased complexity of lesion composition. Conclusions and Relevance: This diagnostic study suggests that the DLS exhibited excellent performance using UWF fundus images as a screening tool for 5 retinal lesions in patients in a rural setting. However, poor image quality, diverse lesion proportions, and a complex set of lesions may have reduced the performance of the DLS; these factors in targeted screening scenarios should be taken into consideration in the model development stage to ensure good performance.

DeepQuality improves infant retinopathy screening.

Image quality variation is a prominent cause of performance degradation for intelligent disease diagnostic models in clinical applications. Image quality issues are particularly prominent in infantile fundus photography due to poor patient cooperation, which poses a high risk of misdiagnosis. Here, we developed a deep learning-based image quality assessment and enhancement system (DeepQuality) for infantile fundus images to improve infant retinopathy screening. DeepQuality can accurately detect various quality defects concerning integrity, illumination, and clarity with area under the curve (AUC) values ranging from 0.933 to 0.995. It can also comprehensively score the overall quality of each fundus photograph. By analyzing 2,015,758 infantile fundus photographs from real-world settings using DeepQuality, we found that 58.3% of them had varying degrees of quality defects, and large variations were observed among different regions and categories of hospitals. Additionally, DeepQuality provides quality enhancement based on the results of quality assessment. After quality enhancement, the performance of retinopathy of prematurity (ROP) diagnosis of clinicians was significantly improved. Moreover, the integration of DeepQuality and AI diagnostic models can effectively improve the model performance for detecting ROP. This study may be an important reference for the future development of other image-based intelligent disease screening systems.

Prediction of OCT images of short-term response to anti-VEGF treatment for diabetic macular edema using different generative adversarial networks.

PURPOSE: This study sought to assess the predictive performance of optical coherence tomography (OCT) images for the response of diabetic macular edema (DME) patients to anti-vascular endothelial growth factor (VEGF) therapy generated from baseline images using generative adversarial networks (GANs). METHODS: Patient information, including clinical and imaging data, was obtained from inpatients at the Ophthalmology Department of Qilu Hospital. 715 and 103 pairs of pre-and post-treatment OCT images of DME patients were included in the training and validation sets, respectively. The post-treatment OCT images were used to assess the validity of the generated images. Six different GAN models (CycleGAN, PairGAN, Pix2pixHD, RegGAN, SPADE, UNIT) were applied to predict the efficacy of anti-VEGF treatment by generating OCT images. Independent screening and evaluation experiments were conducted to validate the quality and comparability of images generated by different GAN models. RESULTS: OCT images generated f GAN models exhibited high comparability to the real images, especially for edema absorption. RegGAN exhibited the highest prediction accuracy over the CycleGAN, PairGAN, Pix2pixHD, SPADE, and UNIT models. Further analyses were conducted based on the RegGAN. Most post-therapeutic OCT images (95/103) were difficult to differentiate from the real OCT images by retinal specialists. A mean absolute error of 26.74 ± 21.28 µm was observed for central macular thickness (CMT) between the synthetic and real OCT images. CONCLUSION: Different generative adversarial networks have different prognostic efficacy for DME, and RegGAN yielded the best performance in our study. Different GAN models yielded good accuracy in predicting the OCT-based response to anti-VEGF treatment at one month. Overall, the application of GAN models can assist clinicians in prognosis prediction of patients with DME to design better treatment strategies and follow-up schedules.

DeepFundus: A flow-cytometry-like image quality classifier for boosting the whole life cycle of medical artificial intelligence.

Medical artificial intelligence (AI) has been moving from the research phase to clinical implementation. However, most AI-based models are mainly built using high-quality images preprocessed in the laboratory, which is not representative of real-world settings. This dataset bias proves a major driver of AI system dysfunction. Inspired by the design of flow cytometry, DeepFundus, a deep-learning-based fundus image classifier, is developed to provide automated and multidimensional image sorting to address this data quality gap. DeepFundus achieves areas under the receiver operating characteristic curves (AUCs) over 0.9 in image classification concerning overall quality, clinical quality factors, and structural quality analysis on both the internal test and national validation datasets. Additionally, DeepFundus can be integrated into both model development and clinical application of AI diagnostics to significantly enhance model performance for detecting multiple retinopathies. DeepFundus can be used to construct a data-driven paradigm for improving the entire life cycle of medical AI practice.

Predicting OCT images of short-term response to anti-VEGF treatment for retinal vein occlusion using generative adversarial network.

To generate and evaluate post-therapeutic optical coherence tomography (OCT) images based on pre-therapeutic images with generative adversarial network (GAN) to predict the short-term response of patients with retinal vein occlusion (RVO) to anti-vascular endothelial growth factor (anti-VEGF) therapy. Real-world imaging data were retrospectively collected from 1 May 2017, to 1 June 2021. A total of 515 pairs of pre-and post-therapeutic OCT images of patients with RVO were included in the training set, while 68 pre-and post-therapeutic OCT images were included in the validation set. A pix2pixHD method was adopted to predict post-therapeutic OCT images in RVO patients after anti-VEGF therapy. The quality and similarity of synthetic OCT images were evaluated by screening and evaluation experiments. We quantitatively and qualitatively assessed the prognostic accuracy of the synthetic post-therapeutic OCT images. The post-therapeutic OCT images generated by the pix2pixHD algorithm were comparable to the actual images in edema resorption response. Retinal specialists found most synthetic images (62/68) difficult to differentiate from the real ones. The mean absolute error (MAE) of the central macular thickness (CMT) between the synthetic and real OCT images was 26.33 ± 15.81 µm. There was no statistical difference in CMT between the synthetic and the real images. In this retrospective study, the application of the pix2pixHD algorithm objectively predicted the short-term response of each patient to anti-VEGF therapy based on OCT images with high accuracy, suggestive of its clinical value, especially for screening patients with relatively poor prognosis and potentially guiding clinical treatment. Importantly, our artificial intelligence-based prediction approach's non-invasiveness, repeatability, and cost-effectiveness can improve compliance and follow-up management of this patient population.

Comparison of functional changes of retina after subthreshold and threshold pan-retinal photocoagulation in severe non-proliferative diabetic retinopathy.

PURPOSE: To find a new approach of pan-retinal photocoagulation (PRP) with less damage to the retina in the treatment of severe non-proliferative diabetic retinopathy (NPDR), this study compared functional changes in the retina after subthreshold and threshold PRP treatment in severe NPDR eyes. METHODS: Post hoc analysis of a randomized clinical trial was conducted in this study. Seventy eyes of 35 patients with bilateral, symmetric, severe NPDR were enrolled. Two eyes from the same patient were randomized into two groups, one eye received subthreshold PRP (S-PRP) and the other eye received threshold PRP (T-PRP). Comprehensive ophthalmological evaluations were performed on the baseline and every 3 months for 1 year. Visual field (VF) and full-field electroretinography (ERG) were performed on the baseline and repeated at month 12. RESULTS: During the 12-month follow-up, 4 eyes (11.4%) in the S-PRP group and 3 eyes (8.6%) in the T-PRP group progressed to proliferative diabetic retinopathy (PDR) stage, and there was no statistical difference in PDR progression rate between the two groups (P = 0.69). In addition, the changes in best-corrected visual acuity (BCVA) from baseline to month 12 between the two groups had no statistical difference (P = 0.30). From baseline to month 12, changes in central VF between the two groups had no statistical difference (P = 0.25), but changes in total score points of peripheral VF in the S-PRP group (- 242.1 ± 210.8 dB) and the T-PRP group (- 308.9 ± 209.7 dB) were statistically significant (P = 0.03). At month 12, ERG records showed that the amplitude of dark-adapted 0.01 ERG, dark-adapted 3.0 ERG, oscillatory potentials, light-adapted 3.0 ERG, and 30 Hz flicker ERG of both groups were significantly decreased from the baseline (P < 0.05). In addition, the amplitude of each ERG record in the S-PRP group decreased significantly less than those in the T-PRP group (P < 0.05). CONCLUSIONS: Subthreshold PRP is as effective as threshold PRP for preventing severe NPDR progress to PDR within 1 year with less damage to periphery VF and retinal function. CLINICALTRIALS: gov Identifier: NCT01759121.

Retinal Microvascular Signs in Pre- and Early-Stage Diabetic Retinopathy Detected Using Wide-Field Swept-Source Optical Coherence Tomographic Angiography.

Purpose Using a wide-field, high-resolution swept-source optical coherence tomographic angiography (OCTA), this study investigated microvascular abnormalities in patients with pre- and early-stage diabetic retinopathy. Methods 38 eyes of 20 people with diabetes mellitus (DM) type 2 without diabetic retinopathy (DR) and 39 eyes of 21 people with DR were enrolled in this observational and cross-sectional cohort study, and a refractive error-matched group consisting of 42 eyes of 21 non-diabetic subjects of similar age were set as the control. Each participant underwent a wide-field swept-source OCTA. On OCTA scans (1.2 × 1.2 cm), the mean central macular thickness (CMT), the vessel density of the inner retina, superficial capillary plexus (SCP), and deep capillary plexus (DCP) were independently measured in the whole area (1.2 cm diameter) via concentric rings with varying radii (0-0.3, 0.3-0.6, 0.6-0.9, and 0.9-1.2 cm). Results Patients whose eyes had pre-and early-stage DR showed significantly decreased vessel density in the inner retina, SCP, DCP and CMT (early-stage DR) compared with the control. In addition, compared with the average values upon wide-field OCTA, the decreases were even more pronounced for concentric rings with a radius of 0.9-1.2 cm in terms of the inner retina, SCP, DCP and CMT. Conclusions Widefield OCTA allows for a more thorough assessment of retinal changes in patients with pre- and early-stage DR.; retinal microvascular abnormalities were observed in both groups. In addition, the decreases in retinal vessel density were more significant in the peripheral concentric ring with a radius of 0.9-1.2 cm. The application of novel and wide-field OCTA could potentially help to detect earlier diabetic microvascular abnormalities.

Prediction of the Short-Term Therapeutic Effect of Anti-VEGF Therapy for Diabetic Macular Edema Using a Generative Adversarial Network with OCT Images.

PURPOSE: To generate and evaluate individualized post-therapeutic optical coherence tomography (OCT) images that could predict the short-term response of anti-vascular endothelial growth factor (VEGF) therapy for diabetic macular edema (DME) based on pre-therapeutic images using generative adversarial network (GAN). METHODS: Real-world imaging data were collected at the Department of Ophthalmology, Qilu Hospital. A total of 561 pairs of pre-therapeutic and post-therapeutic OCT images of patients with DME were retrospectively included in the training set, 71 pre-therapeutic OCT images were included in the validation set, and their corresponding post-therapeutic OCT images were used to evaluate the synthetic images. A pix2pixHD method was adopted to predict post-therapeutic OCT images in DME patients that received anti-VEGF therapy. The quality and similarity of synthetic OCT images were evaluated independently by a screening experiment and an evaluation experiment. RESULTS: The post-therapeutic OCT images generated by the GAN model based on big data were comparable to the actual images, and the response of edema resorption was also close to the ground truth. Most synthetic images (65/71) were difficult to differentiate from the actual OCT images by retinal specialists. The mean absolute error (MAE) of the central macular thickness (CMT) between the synthetic OCT images and the actual images was 24.51 ± 18.56 µm. CONCLUSIONS: The application of GAN can objectively demonstrate the individual short-term response of anti-VEGF therapy one month in advance based on OCT images with high accuracy, which could potentially help to improve treatment compliance of DME patients, identify patients who are not responding well to treatment and optimize the treatment program.

Prediction of Visual Acuity after anti-VEGF Therapy in Diabetic Macular Edema by Machine Learning.

Purpose: To predict visual acuity (VA) 1 month after anti-vascular endothelial growth factor (VEGF) therapy in patients with diabetic macular edema (DME) by using machine learning. Methods: This retrospective study included 281 eyes with DME receiving intravitreal anti-VEGF treatment from January 1, 2019, to April 1, 2021. Eighteen features from electronic medical records and measurements data from OCT images were extracted. The data obtained from January 1, 2019, to November 1, 2020, were used as the training set; the data obtained from November 1, 2020, to April 1, 2021, were used as the validation set. Six different machine learning algorithms were used to predict VA in patients after anti-VEGF therapy. After the initial detailed investigation, we designed an optimization model for convenient application. The VA predicted by machine learning was compared with the ground truth. Results: The ensemble algorithm (linear regression + random forest regressor) performed best in VA and VA variance predictions. In the validation set, the mean absolute errors (MAEs) of VA predictions were 0.137-0.153 logMAR (within 7-8 letters), and the mean square errors (MSEs) were 0.033-0.045 logMAR (within 2-3 letters) for the 1-month VA predictions, respectively. For the prediction of VA variance at 1 month, the MAEs were 0.164-0.169 logMAR (within 9 letters), and the MSEs were 0.056-0.059 logMAR (within 3 letters), respectively. Conclusions: Our machine learning models could accurately predict VA and VA variance in DME patients receiving anti-VEGF therapy 1 month after, which would be much valuable to guide precise individualized interventions and manage expectations in clinical practice.

The Fundus Structural and Functional Predictions of DME Patients After Anti-VEGF Treatments.

Diabetic retinopathy (DR) is an important complication with a high incidence of 34.6% in the diabetic populations. DR could finally lead to vision impairment without effective interventions, during which, diabetic macular edema (DME) is a key phase causing visual loss. Up to date, antivascular endothelial growth factor (anti-VEGF) therapy is the first-line treatment for DME which has achieved relatively better clinical outcomes than traditional treatments. However, there are several kinds of anti-VEGF medicines, and patients are sensitive to different anti-VEGF treatments. In addition, its effectiveness is unstable. Considering the patients' need to accept continual anti-VEGF treatments and its price is comparatively high, it is clinically important to predict the prognosis after different anti-VEGF treatments. In our research, we used the demographic and clinical data of 254 DME patients and 2,763 optical coherence tomography (OCT) images from three countries to predict the fundus structural and functional parameters and treatment plan in 6 months after different anti-VEGF treatments. Eight baseline features combined with 11 models were applied to conduct seven prediction tasks. Accuracy (ACC), the area under curve (AUC), mean absolute error (MAE), and mean square error (MSE) were respectively used to evaluate the classification and regression tasks. The ACC and AUC of structural predictions of retinal pigment epithelial detachment were close to 1.000. The MAE and MSE of visual acuity predictions were nearly 0.3 to 0.4 logMAR. The ACC of treatment plan regarding continuous injection was approaching 70%. Our research has achieved great performance in the predictions of fundus structural and functional parameters as well as treatment plan, which can help ophthalmologists improve the treatment compliance of DME patients.

Automated detection of retinal exudates and drusen in ultra-widefield fundus images based on deep learning.

BACKGROUND: Retinal exudates and/or drusen (RED) can be signs of many fundus diseases that can lead to irreversible vision loss. Early detection and treatment of these diseases are critical for improving vision prognosis. However, manual RED screening on a large scale is time-consuming and labour-intensive. Here, we aim to develop and assess a deep learning system for automated detection of RED using ultra-widefield fundus (UWF) images. METHODS: A total of 26,409 UWF images from 14,994 subjects were used to develop and evaluate the deep learning system. The Zhongshan Ophthalmic Center (ZOC) dataset was selected to compare the performance of the system to that of retina specialists in RED detection. The saliency map visualization technique was used to understand which areas in the UWF image had the most influence on our deep learning system when detecting RED. RESULTS: The system for RED detection achieved areas under the receiver operating characteristic curve of 0.994 (95% confidence interval [CI]: 0.991-0.996), 0.972 (95% CI: 0.957-0.984), and 0.988 (95% CI: 0.983-0.992) in three independent datasets. The performance of the system in the ZOC dataset was comparable to that of an experienced retina specialist. Regions of RED were highlighted by saliency maps in UWF images. CONCLUSIONS: Our deep learning system is reliable in the automated detection of RED in UWF images. As a screening tool, our system may promote the early diagnosis and management of RED-related fundus diseases.

Assessment of choroidal structural changes in patients with pre- and early-stage clinical diabetic retinopathy using wide-field SS-OCTA.

Purpose: To investigate the micro-vascular changes in choroidal structures in patients with pre- and early-stage clinical diabetic retinopathy (DR) using wide-field Swept-Source Optical Coherence Tomography Angiography (SS-OCTA). Method: This observational cross-sectional study included 131 eyes of 68 subjects that were divided into healthy controls (group 1, n = 46), pre-DR (group 2, n = 43), early-stage DR (group 3, n = 42) cohorts. All participants that underwent SS-OCTA examination were inpatients in the department of Ophthalmology and the department of Endocrinology, Qilu Hospital, Shandong University, and Department of Ophthalmology, Aier Eye Hospital, Jinan, from July 11, 2021 to March 17, 2022. The choroidal vascularity index (CVI), choroidal thickness (ChT) and central macular thickness (CMT) in the whole area (diameter of 12 mm) and concentric rings with different ranges (0-3, 3-6, 6-9, and 9-12 mm) were recorded and analyzed from the OCTA image. Result: Compared with healthy eyes, decreases in CVI and ChT were found in the eyes of patients with pre-or early-stage DR. The changes were more significant in the peripheral choroid, with the most prominent abnormalities in the 9-12mm area (P < 0.001). However, there was no obvious difference in the average CMT value. Furthermore, CVI and ChT were significantly correlated with the duration of diabetes in the range of 6-9 and 9-12 mm (Ps < 0.05; Correlation coefficient = -0.549, -0.395, respectively), with the strongest correlation (Ps < 0.01; Correlation coefficient = -0.597, -0.413, respectively) observed at 9-12 mm. Conclusion: The CVI and ChT values of diabetic patients are significantly lower than in healthy controls, especially in patients with early-stage DR. In addition, the peripheral choroidal capillaries are more susceptible to early DM-induced injury than in the central area.

Predicting Central Serous Chorioretinopathy Recurrence Using Machine Learning.

Purpose: To predict central serous chorioretinopathy (CSC) recurrence 3 and 6 months after laser treatment by using machine learning. Methods: Clinical and imaging features of 461 patients (480 eyes) with CSC were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The ZOC data (416 eyes of 401 patients) were used as the training dataset and the internal test dataset, while the XEC data (64 eyes of 60 patients) were used as the external test dataset. Six different machine learning algorithms and an ensemble model were trained to predict recurrence in patients with CSC. After completing the initial detailed investigation, we designed a simplified model using only clinical data and OCT features. Results: The ensemble model exhibited the best performance among the six algorithms, with accuracies of 0.941 (internal test dataset) and 0.970 (external test dataset) at 3 months and 0.903 (internal test dataset) and 1.000 (external test dataset) at 6 months. The simplified model showed a comparable level of predictive power. Conclusion: Machine learning achieves high accuracies in predicting the recurrence of CSC patients. The application of an intelligent recurrence prediction model for patients with CSC can potentially facilitate recurrence factor identification and precise individualized interventions.

Predicting Post-Therapeutic Visual Acuity and OCT Images in Patients With Central Serous Chorioretinopathy by Artificial Intelligence.

To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, and 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical and imaging data were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The data obtained from ZOC (416 eyes of 401 patients) were used as the training set; the data obtained from XEC (64 eyes of 60 patients) were used as the test set. Six different machine learning algorithms and a blending algorithm were used to predict VA, and a pix2pixHD method was adopted to predict post-therapeutic OCT images in patients after laser treatment. The data for VA predictions included clinical features obtained from electronic medical records (20 features) and measured features obtained from fundus fluorescein angiography, indocyanine green angiography, and OCT (145 features). The data for OCT predictions included 480 pairs of pre- and post-therapeutic OCT images. The VA and OCT images predicted by AI were compared with the ground truth. In the VA predictions of XEC dataset, the mean absolute errors (MAEs) were 0.074-0.098 logMAR (within four to five letters), and the root mean square errors were 0.096-0.127 logMAR (within five to seven letters) for the 1-, 3-, and 6-month predictions, respectively; in the post-therapeutic OCT predictions, only about 5.15% (5 of 97) of synthetic OCT images could be accurately identified as synthetic images. The MAEs of central macular thickness of synthetic OCT images were 30.15 ± 13.28 µm and 22.46 ± 9.71 µm for the 1- and 3-month predictions, respectively. This is the first study to apply AI to predict VA and post-therapeutic OCT of patients with CSC. This work establishes a reliable method of predicting prognosis 6 months in advance; the application of AI has the potential to help reduce patient anxiety and serve as a reference for ophthalmologists when choosing optimal laser treatments.

Deep Learning for Detecting Subretinal Fluid and Discerning Macular Status by Fundus Images in Central Serous Chorioretinopathy.

Subretinal fluid (SRF) can lead to irreversible visual loss in patients with central serous chorioretinopathy (CSC) if not absorbed in time. Early detection and intervention of SRF can help improve visual prognosis and reduce irreversible damage to the retina. As fundus image is the most commonly used and easily obtained examination for patients with CSC, the purpose of our research is to investigate whether and to what extent SRF depicted on fundus images can be assessed using deep learning technology. In this study, we developed a cascaded deep learning system based on fundus image for automated SRF detection and macula-on/off serous retinal detachment discerning. The performance of our system is reliable, and its accuracy of SRF detection is higher than that of experienced retinal specialists. In addition, the system can automatically indicate whether the SRF progression involves the macula to provide guidance of urgency for patients. The implementation of our deep learning system could effectively reduce the extent of vision impairment resulting from SRF in patients with CSC by providing timely identification and referral.

Intravitreal injection of triptolide attenuates subretinal fibrosis in laser-induced murine model.

BACKGROUND: Choroidal neovascularization (CNV) is a common cause of irreversible blindness in elderly patients in developed countries, and subretinal fibrosis is an advanced stage of CNV. Currently, there is no effective clinical treatment for subretinal fibrosis. PURPOSE: To investigate whether intravitreal injection of triptolide (TP) could attenuate subretinal fibrosis and determine its underlying mechanisms. METHODS: CNV was induced by laser photocoagulation in C57BL/6J mice. Immediately after laser photocoagulation, 1 µl of free TP (10 µg), TP-nanolip-PEG (TP-loaded PEGylated nanoliposomes containing 10 µg TP), or the same volume of phosphate-buffered saline (PBS) was intravitreally administered to each respective group. Areas and ratios of subretinal fibrosis were calculated seven days after laser injury. Additionally, expression levels of M2 macrophage-related markers, molecules of the transforming growth factor (TGF)-ß1/Smad signaling pathway, and markers for epithelial-mesenchymal transition (EMT) and endothelial-to-mesenchymal transition (EndoMT) were detected both in vitro and in vivo. RESULTS: The areas of subretinal fibrosis were significantly reduced in both the free TP (10993.87 ± 2416.90 µm2) and TP-nanolip-PEG (7695.32 ± 2121.91 µm2) groups when compared with the PBS group (15971.97 ± 3203.10 µm2) (p < 0.05, n = 6). The ratio of subretinal fibrosis in the free TP monomer (20.8 ± 4.2%) and TP-nanolip-PEG (12.5 ± 4.0%) groups was lower than that in the PBS control group (41.7 ± 5.3%) (p < 0.01, n = 6). Moreover, both TP and TP-nanolip-PEG suppressed the polarization of M2 macrophages and downregulated gene expressions of TGF-ß1, Smad 2, Smad 3, α-SMA, and collagen I (p < 0.05), but upregulated the gene expression of E-cadherin (p < 0.05), thus reversing TGF-ß1 induced EMT/EndoMT and attenuating subretinal fibrosis. CONCLUSIONS: TP could attenuate subretinal fibrosis by suppressing the polarization of M2 macrophages and TGF-ß1 induced EMT/EndoMT. TP-nanolip-PEG enhanced the inhibitory effects of TP on subretinal fibrosis, suggesting its therapeutic potential for CNV-related subretinal fibrosis.

Application of Surgical Decision Model for Patients With Childhood Cataract: A Study Based on Real World Data.

Reliable validated methods are necessary to verify the performance of diagnosis and therapy-assisted models in clinical practice. However, some validated results have research bias and may not reflect the results of real-world application. In addition, the conduct of clinical trials has executive risks for the indeterminate effectiveness of models and it is challenging to finish validated clinical trials of rare diseases. Real world data (RWD) can probably solve this problem. In our study, we collected RWD from 251 patients with a rare disease, childhood cataract (CC) and conducted a retrospective study to validate the CC surgical decision model. The consistency of the real surgical type and recommended surgical type was 94.16%. In the cataract extraction (CE) group, the model recommended the same surgical type for 84.48% of eyes, but the model advised conducting cataract extraction and primary intraocular lens implantation (CE + IOL) surgery in 15.52% of eyes, which was different from the real-world choices. In the CE + IOL group, the model recommended the same surgical type for 100% of eyes. The real-recommended matched rates were 94.22% in the eyes of bilateral patients and 90.38% in the eyes of unilateral patients. Our study is the first to apply RWD to complete a retrospective study evaluating a clinical model, and the results indicate the availability and feasibility of applying RWD in model validation and serve guidance for intelligent model evaluation for rare diseases.

Subthreshold Micropulse Laser vs. Conventional Laser for Central Serous Chorioretinopathy: A Randomized Controlled Clinical Trial.

Purpose: To investigate the effectiveness and safety of 577-nm subthreshold micropulse laser (SML) on acute central serous chorioretinopathy (CSC). Methods: One hundred and ten patients with acute CSC were randomized to receive SML or 577-nm conventional laser (CL) treatment. Optical coherence tomography and best-corrected visual acuity (BCVA) were performed before and after treatment. Results: At 3 months, the complete resolution of subretinal fluid (SRF) in 577-nm SML group (72.7%) was lower than that in CL group (89.1%) (Unadjusted RR, 0.82; P = 0.029), but it was 85.5 vs. 92.7% at 6 months (unadjusted RR, 0.92; P = 0.221). The mean LogMAR BCVA significantly improved, and the mean central foveal thickness (CFT) significantly decreased in the SML group and CL group (all P < 0.001) at 6 months. But there was no statistical difference between the two groups (all P > 0.05). In the SML group, obvious retinal pigment epithelium (RPE) damage was shown only in 3.64% at 1 month but 92.7% in the CL group (P < 0.001). Conclusions: Although 577-nm SML has a lower complete absorption of SRF compared with 577-nm CL for acute CSC at 3 months, it is similarly effective as 577-nm CL on improving retinal anatomy and function at 6 months. Importantly, 577-nm SML causes less damage to the retina.