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.

The optimal atropine concentration for myopia control in Chinese children: a systematic review and network Metaanalysis

AIM:To figure out whether various atropine dosages may slow the progression of myopia in Chinese kids and teenagers and to determine the optimal atropine concentration for effectively slowing the progression of myopia.METHODS:A systematic search was conducted across the Cochrane Library,PubMed,Web of Science,EMBASE,CNKI,CBM,VIP,and Wanfang database,encompassing literature on slowing progression of myopia with varying atropine concentrations from database inception to January 17,2024.Data extraction and quality assessment were performed,and a network Meta-analysis was executed using Stata version 14.0 Software.Results were visually represented through graphs.RESULTS:Fourteen papers comprising 2475 cases were included;five different concentrations of atropine solution were used.The network Meta-analysis,along with the surface under the cumulative ranking curve(SUCRA),showed that 1%atropine(100%)>0.05%atropine(74.9%)>0.025%atropine(51.6%)>0.02%atropine(47.9%)>0.01%atropine(25.6%)>control in refraction change and 1%atropine(98.7%)>0.05%atropine(70.4%)>0.02%atropine(61.4%)>0.025%atropine(42%)>0.01%atropine(27.4%)>control in axial length(AL)change.CONCLUSION:In Chinese children and teenagers,the five various concentrations of atropine can reduce the progression of myopia.Although the network Meta-analysis showed that 1%atropine is the best one for controlling refraction and AL change,there is a high incidence of adverse effects with the use of 1%atropine.Therefore,we suggest that 0.05%atropine is optimal for Chinese children to slow myopia progression.

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.

直流燃烧室内气体辐射换热特性研究

As one of the core components of aero-engine,the thermal protection scheme of combustion chamber has an important impact on its service life.In order to improve the design level of high-performance combustion chamber,the radiation heat transfer characteristics of combustion chamber are studied by experimental method.The following results are obtained:1)With the increase of oil-gas ratio,the gas temperature increases first and then tends to be stable,the radiant heat flow increases gradually,the convective heat flow increases gradually and then tends to be stable,and the proportion of radiant heat flow remains basically unchanged;2)With the increase of the inlet temperature,the gas temperature increases gradually,the radiant heat flow,especially in the flame barrel head area,increases significantly,the convective heat flow remains basically unchanged,and the proportion of radiant heat flow increases significantly;3)With the increase of the combustion chamber pressure,the gas temperature increases gradually.When the combustion chamber pressure is low,the radiant heat flow increases sharply with the increase of the pressure;When the combustion chamber pressure is high,the radiant heat flow increases slowly with the increase of the pressure.The convective heat flow gradually decreases and tends to be stable,and the proportion of radiant heat flow gradually increases and tends to be stable.This study is of great significance to improve the calculation accuracy of radiant heat flow of combustion chamber and the reliability design of thermal protection scheme of combustion chamber.

飞秒激光与传统LASIK术后干眼参数变化

目的:应用Keratograph5M比较飞秒激光与传统LASIK术后干眼症状和体征的变化。方法:收集2017-06/11行角膜屈光手术患者60例120眼,其中行飞秒激光LASIK手术30例60眼,传统LASIK手术30例60眼,于术前和术后1wk,1、3、6mo进行眼科常规检查和Keratograph5M干眼检查并完成眼表疾病指数(OSDI)问卷。结果:术后1wk,两组OSDI评分均高于术前(P<0.01),术后1mo两组均恢复到术前水平(P>0.05)。传统组术后1wk,1、3mo非侵入性泪膜破裂时间均比术前缩短(P<0.01),飞秒激光组术后1wk,1mo泪膜破裂时间均比术前缩短(P<0.01),术后3mo,飞秒激光组泪膜破裂时间均明显高于传统组(P<0.01)。术后1wk,1mo,两组泪河高度均较术前降低(P<0.01),脂质层均较术前变薄(P<0.05)。结论:无论飞秒激光制瓣LASIK还是传统LASIK术都可影响泪膜的稳定性,引起干眼症状,影响程度随术后时间逐渐减弱,但飞秒制瓣能更快恢复至术前水平。

双眼慢性原发性闭角型青光眼术前房水中炎症因子的表达及其对预后的影响

目的:探讨慢性原发性闭角型青光眼(CPACG)双眼先后行小梁切除术前房水中炎症因子的表达水平及其与术后滤过泡和眼压的相关性。方法:选取2021-09/12在南京医科大学附属眼科医院就诊并行小梁切除术的双眼CPACG患者15例30眼,双眼手术间隔7d,利用酶联免疫吸附试验(ELISA)分别检测双眼术前房水中单核细胞趋化蛋白-1(MCP-1)、白细胞介素-17(IL-17)、转化生长因子-β(TGF-β)和干扰素-γ(IFN-γ)的表达水平,并于术后1mo评估眼压及滤过泡形态。结果:纳入患者第一眼术前房水中MCP-1、IL-17、TGF-β和IFN-γ的含量分别为330.4±46.2、357.3±46.9、2347.5±363.8、527.7±101.6pg/mL,第二眼术前房水中MCP-1、IL-17、TGF-β和IFN-γ的含量分别为298.2±40.7、309.1±53.5、1938.3±426.0、628.2±104.9pg/mL,双眼术前房水中炎症因子表达水平均有差异(P≤0.05)。纳入患者双眼术前房水中IL-17、TGF-β表达水平与术后1mo眼压、滤过泡高度均具有相关性(P<0.05)。结论:CPACG患者第一眼术后第二眼房水中炎症因子的表达水平可能发生一定变化,其中双眼术前房水中IL-17、TGF-β的表达水平与术后眼压和滤过泡高度具有一定的相关性。

眼科人工智能临床研究评价指南(2023)

人工智能(AI)技术在医学领域的应用是当前的热点。眼科作为医学领域中的AI应用前沿专业之一,运用机器学习技术应用于诊断、干预和预测眼科疾病方面取得了显著的成果。基于眼科AI临床研究的需求,为契合眼科AI临床诊疗发展的实际情况,中国医药教育协会眼科影像与智能医疗分会和智能医学专业委员会组织专家结合近年来国内外AI临床研究的评价报告,经过多轮讨论和修改,形成了针对眼科AI临床研究的评价指南。该指南包括了眼科AI临床研究评价指南制定的背景和方法、AI临床研究评价的国际指南介绍、眼科AI临床研究评价方法等内容,详细介绍了眼科AI临床研究通用评价方法、眼科AI临床研究模型评价方法、常用眼科AI临床研究模型评价指标和计算公式,并详细阐述了眼科AI临床试验评价方法。该指南的制定旨在为眼科AI临床研究人员提供指导和规范,并推动眼科AI临床研究的评价向着规范化和标准化方向发展,进一步提高眼科AI临床研究评价的整体水平。

人工智能在干眼诊断中的研究进展

干眼(dry eye,DE)是世界范围内最常见的眼科疾病之一,患病率在5%~50%。由于病因复杂且诊断的相应设备有限,干眼尚不能得到及时、精准的诊断。近年来,随着人工智能(artificial intelligence,AI)在医学领域的广泛应用,利用机器学习和深度学习辅助检查干眼也得到了深入研究,如干涉测量、裂隙灯检查和睑板腺图像的分类和评估等。研究发现人工智能能够对干眼患者的测量数据和图像进行准确分析,灵敏度和特异度均可达90%以上。人工智能将在辅助临床医生客观诊断干眼、改善干眼患者生活质量方面具有巨大潜力。在这篇综述中,我们总结了人工智能在干眼领域的应用现状以及应用中潜在的挑战,展望了人工智能辅助诊断干眼的前景。

基于深度学习的翼状胬肉自动分类系统研究

目的:评估基于深度学习的翼状胬肉自动分类诊断系统的应用价值。方法:在2020-05/2021-04期间,从南京医科大学附属眼科医院共收集750张翼状胬肉正常、观察期和手术期眼前节图片。在原始数据集和增强数据集上分别训练7个三分类模型。测试临床470张图片,比较数据增强前后模型的泛化能力,确定可用于翼状胬肉自动分类系统的最好模型。结果:在原始数据集上训练最好模型的灵敏度平均值为92.55%,特异度平均值为96.86%,AUC平均值为94.70%。数据增强后,不同模型灵敏度、特异度和AUC平均提升3.7%、1.9%和2.7%。在增强数据集上训练的EfficientNetB7模型灵敏度平均值为93.63%,特异度平均值为97.34%,AUC平均值为95.47%。结论:在增强数据集上训练的EfficientNetB7模型取得最好的分类效果,可用于翼状胬肉自动分类系统。该自动分类系统能较好地诊断翼状胬肉疾病,有望成为基层医疗的有效筛查工具,也为翼状胬肉的细化分级研究提供参考。

Guidelines on clinical research evaluation of artificial intelligence in ophthalmology(2023)

With the upsurge of artificial intelligence(AI)technology in the medical field,its application in ophthalmology has become a cutting-edge research field.Notably,machine learning techniques have shown remarkable achievements in diagnosing,intervening,and predicting ophthalmic diseases.To meet the requirements of clinical research and fit the actual progress of clinical diagnosis and treatment of ophthalmic AI,the Ophthalmic Imaging and Intelligent Medicine Branch and the Intelligent Medicine Committee of Chinese Medicine Education Association organized experts to integrate recent evaluation reports of clinical AI research at home and abroad and formed a guideline on clinical research evaluation of AI in ophthalmology after several rounds of discussion and modification.The main content includes the background and method of developing this guideline,an introduction to international guidelines on the clinical research evaluation of AI,and the evaluation methods of clinical ophthalmic AI models.This guideline introduces general evaluation methods of clinical ophthalmic AI research,evaluation methods of clinical ophthalmic AI models,and commonly-used indices and formulae for clinical ophthalmic AI model evaluation in detail,and amply elaborates the evaluation methods of clinical ophthalmic AI trials.This guideline aims to provide guidance and norms for clinical researchers of ophthalmic AI,promote the development of regularization and standardization,and further improve the overall level of clinical ophthalmic AI research evaluations.

Analysis of retinal arteriolar and venular parameters in primary open angle glaucoma

AIM: To measure the retinal vessels of primary open angle glaucoma(POAG) patients on spectral domain optical coherence tomography(SD-OCT) with a full-width at half-maximum(FWHM) algorithm to better explore their structural changes in the pathogenesis of POAG.METHODS: In this retrospective case-control study, the right eyes of 32 patients with POAG and 30 healthy individuals were routinely selected.Images of the supratemporal and infratemporal retinal vessels in the B zones were obtained by SD-OCT, and the edges of the vessels were identified by the FWHM method.The internal and external diameters, wall thickness(WT), wall cross-sectional area(WCSA) and wall-to-lumen ratio(WLR) of the blood vessels were studied.RESULTS: Compared with the healthy control group, the POAG group showed a significantly reduced retinal arteriolar outer diameter(RAOD), retinal arteriolar lumen diameter(RALD) and WSCA in the supratemporal(124.22±12.42 vs 138.32±10.73 μm, 96.09±11.09 vs 108.53±9.89 μm,and 4762.02 ± 913.51 vs 5785.75 ± 114 8.28 μm^(2), respectively, all P<0.05) and infratemporal regions(125.01±15.55 vs 141.57±10.77 μm, 96.27±13.29 vs 110.83 ± 10.99 μm, and 4925.56 ± 1302.88 vs 6087.78±1061.55 μm^(2), all P<0.05).The arteriolar WT and WLR were not significantly different between the POAG and control groups, nor were the retinal venular outer diameter(RVOD), retinal venular lumen diameter(RVLD) or venular WT in the supratemporal or infratemporal region.There was a positive correlation between the arteriolar parameters and visual function.CONCLUSION: In POAG, narrowing of the supratemporal and infratemporal arterioles and a significant reduction in the WSCA is observed, while the arteriolar WT and WLR do not change.Among the venular parameters, the external diameter, internal diameter, WT, WLR, and WSCA of the venules are not affected.

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+.

Artificial intelligence assisted pterygium diagnosis:current status and perspectives

Pterygium is a prevalent ocular disease that can cause discomfort and vision impairment.Early and accurate diagnosis is essential for effective management.Recently,artificial intelligence(AI)has shown promising potential in assisting clinicians with pterygium diagnosis.This paper provides an overview of AI-assisted pterygium diagnosis,including the AI techniques used such as machine learning,deep learning,and computer vision.Furthermore,recent studies that have evaluated the diagnostic performance of AI-based systems for pterygium detection,classification and segmentation were summarized.The advantages and limitations of AI-assisted pterygium diagnosis and discuss potential future developments in this field were also analyzed.The review aims to provide insights into the current state-of-the-art of AI and its potential applications in pterygium diagnosis,which may facilitate the development of more efficient and accurate diagnostic tools for this common ocular disease.

Artificial intelligence-aided diagnosis and treatment in the field of optometry

With the rapid development of computer technology,the application of artificial intelligence(AI)to ophthalmology has gained prominence in modern medicine.As modern optometry is closely related to ophthalmology,AI research on optometry has also increased.This review summarizes current AI research and technologies used for diagnosis in optometry,related to myopia,strabismus,amblyopia,optical glasses,contact lenses,and other aspects.The aim is to identify mature AI models that are suitable for research on optometry and potential algorithms that may be used in future clinical practice.

Evaluation of a novel deep learning based screening system for pathologic myopia

AIM:To evaluate the clinical application value of the artificial intelligence assisted pathologic myopia(PM-AI)diagnosis model based on deep learning.METHODS:A total of 1156 readable color fundus photographs were collected and annotated based on the diagnostic criteria of Meta-pathologic myopia(PM)(2015).The PM-AI system and four eye doctors(retinal specialists 1 and 2,and ophthalmologists 1 and 2)independently evaluated the color fundus photographs to determine whether they were indicative of PM or not and the presence of myopic choroidal neovascularization(mCNV).The performance of identification for PM and mCNV by the PMAI system and the eye doctors was compared and evaluated via the relevant statistical analysis.RESULTS:For PM identification,the sensitivity of the PM-AI system was 98.17%,which was comparable to specialist 1(P=0.307),but was higher than specialist 2 and ophthalmologists 1 and 2(P<0.001).The specificity of the PM-AI system was 93.06%,which was lower than specialists 1 and 2,but was higher than ophthalmologists 1 and 2.The PM-AI system showed the Kappa value of 0.904,while the Kappa values of specialists 1,2 and ophthalmologists 1,2 were 0.968,0.916,0.772 and 0.730,respectively.For mCNV identification,the AI system showed the sensitivity of 84.06%,which was comparable to specialists 1,2 and ophthalmologist 2(P>0.05),and was higher than ophthalmologist 1.The specificity of the PM-AI system was 95.31%,which was lower than specialists 1 and 2,but higher than ophthalmologists 1 and 2.The PM-AI system gave the Kappa value of 0.624,while the Kappa values of specialists 1,2 and ophthalmologists 1 and 2 were 0.864,0.732,0.304 and 0.238,respectively.CONCLUSION:In comparison to the senior ophthalmologists,the PM-AI system based on deep learning exhibits excellent performance in PM and mCNV identification.The effectiveness of PM-AI system is an auxiliary diagnosis tool for clinical screening of PM and mCNV.

CORRIGENDUM:Artificial intelligence-assisted pterygium diagnosis:current status and perspectives

The authors would like to make the following change to the above article:Co-first authors:Bang Chen and Xin-Wen Fang.The authors apologize for any inconvenience caused by this error.

MCSTransWnet:A new deep learning process for postoperative corneal topography prediction based on raw multimodal data from the Pentacam HR system

This work provides a new multimodal fusion generative adversarial net(GAN)model,Multiple Conditions Transform W-net(MCSTransWnet),which primarily uses femtosecond laser arcuate keratotomy surgical parameters and preoperative corneal topography to predict postoperative corneal topography in astigmatism-corrected patients.The MCSTransWnet model comprises a generator and a discriminator,and the generator is composed of two sub-generators.The first sub-generator extracts features using the U-net model,vision transform(ViT)and a multi-parameter conditional module branch.The second sub-generator uses a U-net network for further image denoising.The discriminator uses the pixel discriminator in Pix2Pix.Currently,most GAN models are convolutional neural networks;however,due to their feature extraction locality,it is difficult to comprehend the relationships among global features.Thus,we added a vision Transform network as the model branch to extract the global features.It is normally difficult to train the transformer,and image noise and geometric information loss are likely.Hence,we adopted the standard U-net fusion scheme and transform network as the generator,so that global features,local features,and rich image details could be obtained simultaneously.Our experimental results clearly demonstrate that MCSTransWnet successfully predicts postoperative corneal topographies(structural similarity=0.765,peak signal-to-noise ratio=16.012,and Fréchet inception distance=9.264).Using this technique to obtain the rough shape of the postoperative corneal topography in advance gives clinicians more references and guides changes to surgical planning and improves the success rate of surgery.

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.