Intelligent diagnosis of retinal vein occlusion based on color fundus photographs

AIM:To develop an artificial intelligence(AI)diagnosis model based on deep learning(DL)algorithm to diagnose different types of retinal vein occlusion(RVO)by recognizing color fundus photographs(CFPs).METHODS:Totally 914 CFPs of healthy people and patients with RVO were collected as experimental data sets,and used to train,verify and test the diagnostic model of RVO.All the images were divided into four categories[normal,central retinal vein occlusion(CRVO),branch retinal vein occlusion(BRVO),and macular retinal vein occlusion(MRVO)]by three fundus disease experts.Swin Transformer was used to build the RVO diagnosis model,and different types of RVO diagnosis experiments were conducted.The model’s performance was compared to that of the experts.RESULTS:The accuracy of the model in the diagnosis of normal,CRVO,BRVO,and MRVO reached 1.000,0.978,0.957,and 0.978;the specificity reached 1.000,0.986,0.982,and 0.976;the sensitivity reached 1.000,0.955,0.917,and 1.000;the F1-Sore reached 1.000,0.9550.943,and 0.887 respectively.In addition,the area under curve of normal,CRVO,BRVO,and MRVO diagnosed by the diagnostic model were 1.000,0.900,0.959 and 0.970,respectively.The diagnostic results were highly consistent with those of fundus disease experts,and the diagnostic performance was superior.CONCLUSION:The diagnostic model developed in this study can well diagnose different types of RVO,effectively relieve the work pressure of clinicians,and provide help for the follow-up clinical diagnosis and treatment of RVO patients.

Diabetic retinopathy identification based on multi-sourcefree domain adaptation

AIM:To address the challenges of data labeling difficulties,data privacy,and necessary large amount of labeled data for deep learning methods in diabetic retinopathy(DR)identification,the aim of this study is to develop a source-free domain adaptation(SFDA)method for efficient and effective DR identification from unlabeled data.METHODS:A multi-SFDA method was proposed for DR identification.This method integrates multiple source models,which are trained from the same source domain,to generate synthetic pseudo labels for the unlabeled target domain.Besides,a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances.Validation is performed using three color fundus photograph datasets(APTOS2019,DDR,and EyePACS).RESULTS:The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks.It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains.CONCLUSION:The multi-SFDA method provides an effective approach to overcome the challenges in DR identification.The method not only addresses difficulties in data labeling and privacy issues,but also reduces the need for large amounts of labeled data required by deep learning methods,making it a practical tool for early detection and preservation of vision in diabetic patients.

Artificial intelligence applications in ophthalmic optical coherence tomography:a 12-year bibliometric analysis

AIM:To explore the current application and research frontiers of global ophthalmic optical coherence tomography(OCT)imaging artificial intelligence(AI)research.METHODS:The citation data were downloaded from the Web of Science Core Collection database(WoSCC)to evaluate the articles in application of AI in ophthalmic OCT published from January 1,2012 to December 31,2023.This information was analyzed using CiteSpace 6.2.R2 Advanced software,and high-impact articles were analyzed.RESULTS:In general,877 articles from 65 countries were studied and analyzed,of which 261 were published by the United States and 252 by China.The centrality of the United States is 0.33,the H index is 38,and the H index of two institutions in England reaches 20.Ophthalmology,computer science,and AI are the main disciplines involved.

Acute primary angle closure during the Omicron outbreak

AIM:To investigate Omicron’s impact on clinical presentation of acute primary angle closure(APAC)in China.METHODS:A consecutive case series with historical controls was conducted at Shenzhen Eye Hospital,the largest specialized hospital in Shenzhen,China.Medical records from a two-month period during the Omicron pandemic(December 1,2022,to January 31,2023)were compared with records from two control groups(12/2018–1/2019 and 12/2021–1/2022)before pandemic.Patients with APAC were included,and the prevalence of APAC and demographic characteristics in Omicron-infected and noninfected patients were compared.RESULTS:Seventy-one(23.43%)out of 303 patients were diagnosed with APAC in the pandemic cohort,which was 2.98 and 2.61 times higher than that in control cohorts(7.87%in 2019,8.96%in 2022,P<0.001).The pandemic cohort has significantly higher Omicron-infected rate(78.87%vs 0 vs 0;P<0.001),lower proportion of glaucoma history(16.90%vs 42.86%vs 41.67%,P=0.005),higher surgical rate(95.77%vs 83.33%vs 78.57%,P=0.024),higher total medical costs and larger pupil diameter(5.63±0.15 vs 4.68±0.15 vs 4.69±0.22 mm,P<0.01).In 83%Omicron-infected patients,ocular symptoms appeared within 3d after systemic symptoms onset.In multivariate analysis,Omicron infection(P<0.001)was the only independent predictor of pupil diameter.CONCLUSION:In the Omicron epidemic in China,there is an increase of prevalence and severity of APAC,particularly focusing on the first 3d following infection.

Development and research status of intelligent ophthalmology in China

This paper analyzes the current status,technological developments,academic exchange platforms,and future challenges and solutions in the field of intelligent ophthalmology(IO)in China.In terms of technology,significant progress has been made in various areas,including diabetic retinopathy,fundus image analysis,quality assessment of medical artificial intelligence products,clinical research methods,technical evaluation,and industry standards.Researchers continually enhance the safety and standardization of IO technology by formulating a series of clinical application guidelines and standards.The establishment of domestic and international academic exchange platforms provides extensive collaboration opportunities for professionals in various fields,and various academic journals serve as publication platforms for IO research.However,challenges such as technological innovation,data privacy and security,lagging regulations,and talent shortages still pose obstacles to future development.To address these issues,future efforts should focus on strengthening technological research and development,regulatory framework construction,talent cultivation,and increasing patient awareness and acceptance of new technologies.By comprehensively addressing these challenges,IO in China is poised to further lead the industry’s development on a global scale,bringing more innovation and convenience to the field of ophthalmic healthcare.

Bibliometric analysis of hotspots and trends of global myopia research

AIM:To gain insights into the global research hotspots and trends of myopia.METHODS:Articles were downloaded from January 1,2013 to December 31,2022 from the Science Core Database website and were mainly statistically analyzed by bibliometrics software.RESULTS:A total of 444 institutions in 87 countries published 4124 articles.Between 2013 and 2022,China had the highest number of publications(n=1865)and the highest H-index(61).Sun Yat-sen University had the highest number of publications(n=229)and the highest H-index(33).Ophthalmology is the main category in related journals.Citations from 2020 to 2022 highlight keywords of options and reference,child health(pediatrics),myopic traction mechanism,public health,and machine learning,which represent research frontiers.CONCLUSION:Myopia has become a hot research field.China and Chinese institutions have the strongest academic influence in the field from 2013 to 2022.The main driver of myopic research is still medical or ophthalmologists.This study highlights the importance of public health in addressing the global rise in myopia,especially its impact on children’s health.At present,a unified theoretical system is still needed.Accurate surgical and therapeutic solutions must be proposed for people with different characteristics to manage and intervene refractive errors.In addition,the benefits of artificial intelligence(AI)models are also reflected in disease monitoring and prediction.

Microvascular changes after conbercept therapy in central retinal vein occlusion analyzed by optical coherence tomography angiography

AIM: To investigate microvascular changes in eyes with central retinal vein occlusion(CRVO) complicated by macular edema before and after intravitreal conbercept injection and evaluate correlations between these changes and best-corrected visual acuity(BCVA) and retinal thickness. METHODS: Twenty-eight eyes of 28 patients with macular edema caused by CRVO were included in this retrospective study. All patients received a single intravitreal conbercept injection to treat macular edema. BCVA and the results of optical coherence tomography angiography(OCTA) automatic measurements of the vessel density in the superficial(SCP) and deep retinal capillary plexus(DCP), the foveal avascular zone(FAZ) area, the FAZ perimeter(PERIM), the vessel density within a 300-μm wide ring surrounding the FAZ(FD-300), the acircularity index(AI), the choriocapillaris flow area, and retinal thickness were recorded before and at one month after treatment and compared with the results observed in age-and sexmatched healthy subjects. RESULTS: The vessel density in the SCP and DCP, the FD-300, and the flow area of the choriocapillaris were allsignificantly lower in CRVO eyes than in healthy eyes, while the AI and retinal thickness were significantly higher(all P<0.05). After treatment, retinal thickness was significantly decreased, and the mean BCVA had markedly improved from 20/167 to 20/65(P=0.0092). The flow area of the choriocapillaris was also significantly improved, which may result from the reduction of shadowing effect caused by the attenuation of macular edema. However, there were no significant changes in SCP and DCP vessel density after treatment. The flow area of the choriocapillaris at baseline was negatively correlated with retinal thickness.CONCLUSION: OCTA enables the non-invasive, layerspecific and quantitative assessment of microvascular changes both before and after treatment, and can therefore be used as a valuable imaging tool for the evaluation of the follow-up in CRVO patients.

基于文献计量学和高影响力论文的糖尿病视网膜病变人工智能研究热点和趋势分析

目的:基于文献计量学和高影响力论文研究糖尿病视网膜病变人工智能研究的热点和趋势。方法:检索2012-01-01/2022-12-31在Web of Science Core Collection(WoSCC)发表的关于糖尿病视网膜病变人工智能研究的论文,使用CiteSpace软件分析年发文量、国家、机构、论文来源、研究领域、关键词等,并进一步分析高影响力论文。结果:纳入79个国家关于糖尿病视网膜病变人工智能研究的论文1009篇,其中2022年发文量272篇;中国和印度发文量分别为287、234篇。英国的中心性为0.31,美国的H指数为48,英国的3家机构(伦敦大学、莫菲尔德眼科医院、伦敦大学学院)和埃及的1家机构(埃及知识库)H指数均达到14。该研究领域涉及的主要学科为眼科学、计算机科学和人工智能,2021~2022年突现关键词是迁移学习、血管分割和卷积神经网络。结论:中国在这一领域发文量最大,美国被认为是该领域的领先国家,埃及知识库和伦敦大学为该领域的领先机构,IEEE Access为该领域最活跃的期刊。糖尿病视网膜病变人工智能研究领域的研究重点已经从人工智能用于疾病检测和分级以辅助诊断转向对其辅助诊断系统的研究,迁移学习、血管分割和卷积神经网络在该领域具有广泛的应用前景。

Bibliometric analysis of artificial intelligence and optical coherence tomography images:research hotspots and frontiers

AIM:To explore the latest application of artificial intelligence(AI)in optical coherence tomography(OCT)images,and to analyze the current research status of AI in OCT,and discuss the future research trend.METHODS:On June 1,2023,a bibliometric analysis of the Web of Science Core Collection was performed in order to explore the utilization of AI in OCT imagery.Key parameters such as papers,countries/regions,citations,databases,organizations,keywords,journal names,and research hotspots were extracted and then visualized employing the VOSviewer and CiteSpace V bibliometric platforms.RESULTS:Fifty-five nations reported studies on AI biotechnology and its application in analyzing OCT images.The United States was the country with the largest number of published papers.Furthermore,197 institutions worldwide provided published articles,where University of London had more publications than the rest.The reference clusters from the study could be divided into four categories:thickness and eyes,diabetic retinopathy(DR),images and segmentation,and OCT classification.CONCLUSION:The latest hot topics and future directions in this field are identified,and the dynamic evolution of AIbased OCT imaging are outlined.AI-based OCT imaging holds great potential for revolutionizing clinical care.

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

AIM:To conduct a classification study of high myopic maculopathy(HMM)using limited datasets,including tessellated fundus,diffuse chorioretinal atrophy,patchy chorioretinal atrophy,and macular atrophy,and minimize annotation costs,and to optimize the ALFA-Mix active learning algorithm and apply it to HMM classification.METHODS:The optimized ALFA-Mix algorithm(ALFAMix+)was compared with five algorithms,including ALFA-Mix.Four models,including Res Net18,were established.Each algorithm was combined with four models for experiments on the HMM dataset.Each experiment consisted of 20 active learning rounds,with 100 images selected per round.The algorithm was evaluated by comparing the number of rounds in which ALFA-Mix+outperformed other algorithms.Finally,this study employed six models,including Efficient Former,to classify HMM.The best-performing model among these models was selected as the baseline model and combined with the ALFA-Mix+algorithm to achieve satisfactor y classification results with a small dataset.RESULTS:ALFA-Mix+outperforms other algorithms with an average superiority of 16.6,14.75,16.8,and 16.7 rounds in terms of accuracy,sensitivity,specificity,and Kappa value,respectively.This study conducted experiments on classifying HMM using several advanced deep learning models with a complete training set of 4252 images.The Efficient Former achieved the best results with an accuracy,sensitivity,specificity,and Kappa value of 0.8821,0.8334,0.9693,and 0.8339,respectively.Therefore,by combining ALFA-Mix+with Efficient Former,this study achieved results with an accuracy,sensitivity,specificity,and Kappa value of 0.8964,0.8643,0.9721,and 0.8537,respectively.CONCLUSION:The ALFA-Mix+algorithm reduces the required samples without compromising accuracy.Compared to other algorithms,ALFA-Mix+outperforms in more rounds of experiments.It effectively selects valuable samples compared to other algorithms.In HMM classification,combining ALFA-Mix+with Efficient Former enhances model performance,further demonstrating the effectiveness of ALFA-Mix+.

Prevalence and characteristics of peripheral myopic retinopathy in Guangzhou office workers

AIM： To determine the prevalence and characteristics of peripheral myopic retinopathy among a sample of Guangzhou office workers. METHODS： A cross-sectional study of Guangzhou Chinese office works in different departments and units of the Guangzhou Power Supply Bureau, China, in 2016. Myopic retinopathy was recorded and analyzed with a scanning laser ophthalmoscope and by slit-lamp microscopy combined with a three-mirror contact lens. RESULTS： In total, 1910 eyes of 955 subjects（508 females and 447 males） aged 21-59 y were included; 69.6% of these eyes were myopic. The myopia group had a younger age and worse uncorrected visual acuity（UCVA） and bestcorrected visual acuity（BCVA） when compared with hyperopia and emmetropia groups（P〈0.001）. The axial length（AL） was significantly longer, the spherical equivalent（SE） was more serious, and the optic nerve crescent was significantly larger in subjects with myopia than with hyperopia and emmetropia. Subjects with myopia, and especially high myopia, had the highest frequency of myopic retinal 18 changes（49.4%, P〈0.001） [white-without-pressure（43.8%, P〈0.001）, lattice degeneration（4.5%, P=0.044）] among the three groups. Logistic regression confirmed that any myopia（OR： 3.41, P〈0.001） [mild myopia（OR： 1.93, P=0.001）, moderate myopia（OR：3.64, P〈0.001）, and high myopia（OR：10.58, P〈0.001）], a greater AL（OR： 1.55, P〈0.001） and a much higher SE（OR： 0.77, P〈0.001） increased the risk for peripheral retinal changes.CONCLUSION： Myopia-related retinal changes are positively associated with greater AL, higher SE, and myopia.

Multimode imaging characteristics and treatment of uveal schwannoma

AIM: To delineate the different imaging characteristics of uveal schwannoma from melanoma and discuss the optimal treatment strategy for intraocular schwannoma.METHODS: Case series of three patients diagnosed with intraocular schwannoma was collected at Zhongshan Ophthalmic Center, Guangzhou, China from July 2014 to December 2020.All the study patients underwent ultrasonography and magnetic resonance imaging(MRI).The clinical features, therapeutic strategies, and prognoses of all patients were reviewed.RESULTS: Ultrasonography of all three patients(all females, mean age, 39y, age range, 23-54y) showed low to medium reflectivity with a homogeneous internal structure.MRI of all three patients demonstrated isointensity on T1-weighted imaging spin-echo(T1WI SE) images and hypointense on fast spin-echo T2-weighted images(FSE T2WI) images with respect to the brain.Minimally invasive pars plana vitrectomy(PPV) and local resection of the tumor was performed for all patients, and the diagnosis of schwannoma was confirmed by histopathological examination.CONCLUSION: The present study indicates that ultrasonography and MRI features of uveal schwannoma may contribute to the differentiation of uveal schwannoma from melanoma, and the optimal therapy for intraocular schwannoma is minimally invasive PPV and local resection.