Refined Anam-Net:Lightweight Deep Learning Model for Improved Segmentation Performance of Optic Cup and Disc for Glaucoma Diagnosis

In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR is a reliable measure for the early diagnosis of Glaucoma.In this study,we developed a lightweight DNN model for OC and OD segmentation in retinal fundus images.Our DNN model is based on modifications to Anam-Net,incorporating an anamorphic depth embedding block.To reduce computational complexity,we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network deepens.This modification significantly reduces the number of trainable parameters,making the model lightweight and suitable for resource-constrained applications.We evaluate the performance of the developed model using two publicly available retinal image databases,namely RIM-ONE and Drishti-GS.The results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD segmentation.We used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images,respectively.For OD segmentation using the RIM-ONE we obtain an f1-score(F1),Jaccard coefficient(JC),and overlapping error(OE)of 0.950,0.9219,and 0.0781,respectively.Similarly,for OC segmentation using the same databases,we achieve scores of 0.8481(F1),0.7428(JC),and 0.2572(OE).Based on these experimental results and the significantly lower number of trainable parameters,we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR.

Association of age at diagnosis of diabetes with subsequent risk of age-related ocular diseases and vision acuity

BACKGROUND The importance of age on the development of ocular conditions has been reported by numerous studies.Diabetes may have different associations with different stages of ocular conditions,and the duration of diabetes may affect the development of diabetic eye disease.While there is a dose-response relationship between the age at diagnosis of diabetes and the risk of cardiovascular disease and mortality,whether the age at diagnosis of diabetes is associated with incident ocular conditions remains to be explored.It is unclear which types of diabetes are more predictive of ocular conditions.AIM To examine associations between the age of diabetes diagnosis and the incidence of cataract,glaucoma,age-related macular degeneration(AMD),and vision acuity.METHODS Our analysis was using the UK Biobank.The cohort included 8709 diabetic participants and 17418 controls for ocular condition analysis,and 6689 diabetic participants and 13378 controls for vision analysis.Ocular diseases were identified using inpatient records until January 2021.Vision acuity was assessed using a chart.RESULTS During a median follow-up of 11.0 years,3874,665,and 616 new cases of cataract,glaucoma,and AMD,respectively,were identified.A stronger association between diabetes and incident ocular conditions was observed where diabetes was diagnosed at a younger age.Individuals with type 2 diabetes(T2D)diagnosed at<45 years[HR(95%CI):2.71(1.49-4.93)],45-49 years[2.57(1.17-5.65)],50-54 years[1.85(1.13-3.04)],or 50-59 years of age[1.53(1.00-2.34)]had a higher risk of AMD independent of glycated haemoglobin.T2D diagnosed<45 years[HR(95%CI):2.18(1.71-2.79)],45-49 years[1.54(1.19-2.01)],50-54 years[1.60(1.31-1.96)],or 55-59 years of age[1.21(1.02-1.43)]was associated with an increased cataract risk.T2D diagnosed<45 years of age only was associated with an increased risk of glaucoma[HR(95%CI):1.76(1.00-3.12)].HRs(95%CIs)for AMD,cataract,and glaucoma associated with type 1 diabetes(T1D)were 4.12(1.99-8.53),2.95(2.17-4.02),and 2.40(1.09-5.31),respectively.In multivariable-adjusted analysis,individuals with T2D diagnosed<45 years of age[β95%CI:0.025(0.009,0.040)]had a larger increase in LogMAR.Theβ(95%CI)for LogMAR associated with T1D was 0.044(0.014,0.073).CONCLUSION The younger age at the diagnosis of diabetes is associated with a larger relative risk of incident ocular diseases and greater vision loss.

Etiology, pathogenesis, and diagnosis of neovascular glaucoma

Neovascular glaucoma is defined as iris and/or anterior chamber angle neovascularization associated with increased intraocular pressure. It is a secondary glaucoma that is most frequently caused by severe retinal ischemia. The most common diseases responsible for the development of neovascular glaucoma are diabetic retinopathy, ischemic central retinal vein occlusion,and ocular ischemic syndrome. Uncommon causes include ocular radiation, ocular tumors, uveitis and other miscellaneous conditions. Vascular endothelial growth factor is an important and likely predominant agent involved in the pathogenesis of intraocular neovascularization and neovascular glaucoma. The evolution of clinical and histopathological changes from predisposing conditions to the occurrence of rubeosis iridis and neovascular glaucoma is divided into four stages: prerubeosis, preglaucoma, open angle glaucoma, and angle-closure glaucoma.

Current applications of machine learning in the screening and diagnosis of glaucoma: a systematic review and Meta-analysis

AIM: To compare the effectiveness of two well described machine learning modalities, ocular coherence tomography(OCT) and fundal photography, in terms of diagnostic accuracy in the screening and diagnosis of glaucoma. METHODS: A systematic search of Embase and Pub Med databases was undertaken up to 1 st of February 2019. Articles were identified alongside their reference lists and relevant studies were aggregated. A Meta-analysis of diagnostic accuracy in terms of area under the receiver operating curve(AUROC) was performed. For the studies which did not report an AUROC, reported sensitivity and specificity values were combined to create a summary ROC curve which was included in the Meta-analysis.RESULTS: A total of 23 studies were deemed suitable for inclusion in the Meta-analysis. This included 10 papers from the OCT cohort and 13 from the fundal photos cohort. Random effects Meta-analysis gave a pooled AUROC of 0.957(95%CI=0.917 to 0.997) for fundal photos and 0.923(95%CI=0.889 to 0.957) for the OCT cohort. The slightly higher accuracy of fundal photos methods is likely attributable to the much larger database of images used to train the models(59 788 vs 1743). CONCLUSION: No demonstrable difference is shown between the diagnostic accuracy of the two modalities. The ease of access and lower cost associated with fundal photo acquisition make that the more appealing option in terms of screening on a global scale, however further studies need to be undertaken, owing largely to the poor study quality associated with the fundal photography cohort.

The change of anterior segment parameters after cataract surgery in normal-tension glaucoma

AIM： To investigate the change of anterior chamber angle morphology and intraocular pressure （lOP） reduction after cataract surgery in patients with normal-tension glaucoma （NTG） using swept-source optical coherence tomography （SS-OCT）. METHODS： This prospective, comparative, observational study recruited patients into two groups. Group 1 was the control group including normal subjects except those with cataracts （cataract group, n=67 eyes of 67 patients）, and group 2 was NTG group including patients who were diagnosed with NTG and cataracts （n=43 eyes of 43 patients）, which were treated with phacoemulsification and intraocular lens implantation. Before surgery, and at postoperative 1 and 6too, anterior chamber angles were evaluated by SS-OCT under dark conditions using three- dimensional angle analysis scan protocol. Angle opening distance （AOD）, angle recess area （ARA）, and trabecular- iris surface area （TISA） at four quadrants （temporal, nasal, superior, and inferior） were calculated automatically by SS-OGT, after the observer marked scleral spurs. RESULTS： A total of 106 patients （54 males and 52 females） were enrolled in the study. Angle parameters, AOD, ARA, and TISA were increased after surgery in both groups. However, changes of angle parameters were only significant in group 2. In group 2, preoperative lOP was 13.2＋2.9 mm Hg, and postoperative lOP at 1 and 6mo were 10.5＋3.0 and 10.7＋2.8 mm Hg, respectively. In group 1, preoperative lOP was 12.42.8 mm Hg, and postoperative lOP at 1 and 6mo were 11.6＋2.5 and 12.0＋2.8 mm Hg, respectively. After cataract surgery, angle parameters changed significantly while IOP significantly reduced and was maintained in group 2 （P〈0.001）. The changes in angle parameters （＆AOD500, ATISAS00 at temporal; ＆AOD500, S, RA500 at nasal） were linearly correlated with postoperative IOP changes. CONCLUSION： Cataract surgery may have improved antedor chamber angle parameters and decreased lOP in NTG patients.

High interpretable machine learning classifier for early glaucoma diagnosis

AIM:To develop a classifier for differentiating between healthy and early stage glaucoma eyes based on peripapillary retinal nerve fiber layer(RNFL)thicknesses measured with optical coherence tomography(OCT),using machine learning algorithms with a high interpretability.METHODS:Ninety patients with early glaucoma and 85 healthy eyes were included.Early glaucoma eyes showed a visual field(VF)defect with mean deviation>-6.00 d B and characteristic glaucomatous morphology.RNFL thickness in every quadrant,clock-hour and average thickness were used to feed machine learning algorithms.Cluster analysis was conducted to detect and exclude outliers.Tree gradient boosting algorithms were used to calculate the importance of parameters on the classifier and to check the relation between their values and its impact on the classifier.Parameters with the lowest importance were excluded and a weighted decision tree analysis was applied to obtain an interpretable classifier.Area under the ROC curve(AUC),accuracy and generalization ability of the model were estimated using cross validation techniques.RESULTS:Average and 7 clock-hour RNFL thicknesses were the parameters with the highest impor tance.Correlation between parameter values and impact on classification displayed a stepped pattern for average thickness.Decision tree model revealed that average thickness lower than 82μm was a high predictor for early glaucoma.Model scores had AUC of 0.953(95%CI:0.903-0998),with an accuracy of 89%.CONCLUSION:Gradient boosting methods provide accurate and highly interpretable classifiers to discriminate between early glaucoma and healthy eyes.Average and 7-hour RNFL thicknesses have the best discriminant power.

Critical pathway for primary open angle glaucoma diagnosis

AIM： To develop a critical pathway for primary open angle glaucoma （POAG） diagnosis intended to be efficient, to unify criteria, reduce resource use and minimize costs to the health system. METHODS： We performed a systematic search on PubMed, Cochrane, Embase and ClinicalTrials.org databases and classified the quality of evidence from level I through III. RESULTS： A critical pathway was designed by setting a key-decision step by step model on the basis of the best current evidence. CONCLUSION： A critical pathway, evidence-based guideline, may be a useful tool intended to reduce costs while maintaining or even improving the quality of care for diagnosing a highly prevalent pathology such as open angle glaucoma.

A case of 9p deletion syndrome with congenital infantile glaucoma,effective method of diagnosis,and treatment

Dear Editor,I am Dr.Jia X from the Department of Ophthalmology,Second Xiangya Hospital,Central South University,Changsha,China.I write to present a rare case report of 9p deletion syndrome with congenital infantile glaucoma in an infant,accompanying with an effective method of both diagnosis and treatment.

A new strategy to interpret OCT posterior pole asymmetry analysis for glaucoma diagnosis

AIM：To detect early glaucoma by optical coherence tomography（OCT） posterior pole asymmetry analysis.METHODS：Totally 39 eyes from 39 healthy subjects,40 eyes from 40 mild glaucoma patients,33 eyes from 33 moderate glaucoma patients and 41 eyes from severe glaucoma patients were included in this study.All subjects underwent posterior pole asymmetry analysis（PPAA） of OCT and the posterior pole area was divided into three zones.Means,standard deviations and 95% confidence intervals of each zone asymmetry in control group were assessed.Retina thickness asymmetry（RTA） of different stage of glaucoma were compared for each zone,and receiver operating characteristic（ROC） curves were made to test the efficacy of strategies using different zones to discriminate glaucomatous eyes from the healthy ones.RESULTS：In a healthy population,RTA of the centre zone showed the minimal mean value（3.085 μm）,standard deviation（1.756）,and the narrowest 95% confidence interval（from 2.360 to 3.810 μm）.It was only in the center zone that RTA exhibited significant difference between control and moderate glaucoma group（P〈0.01）,as well as control and severe glaucoma group（P〈0.00001）.The strategy utilized in the center zone had the strongest diagnostic capability（zone 3 AUROC=0.816,P=0.0016） in comparison to that of the periphery area（zone 1 AUROC=0.675,P=0.0016;zone 2 AUROC=0.623,P=0.0197）,the whole posterior pole involved interpreting strategy showed inferior diagnostic power than the centre zone dependent strategy（z=2.851,P=0.0044）.CONCLUSION：Utilizing the posterior pole centre zone to interpret OCT PPAA results are more effective than making use of the whole posterior pole map.

Discovery of a normal-tension glaucoma-suspect rhesus macaque with craniocerebral injury:Hints of elevated translaminar cribrosa pressure difference

To the Editor:Normal-tension glaucoma(NTG)is a progressive optic neuropathy characterized by irreversible blindness with statistically normal intraocular pressure(IOP)(≤21 mmHg),^([1,2])which makes early-stage diagnosis in the clinical practice difficult.Pathophysiological pathways underlying NTG include vascular dysregulation,toxic metabolite accumulation,and elevated translaminar cribrosa pressure difference(TLCPD).^([3])Although various small animal models have provided evidence of different pathophysiological mechanisms,the complicated clinical phenotype cannot be fully imitated by secondary disease models,and the gap between rodents and humans weakens their translational potential.Thus,the pathological changes associated with NTG remain unclear.

Peripapillary and macular vascular densities in healthy,ocular hypertensive,and different stages of glaucomatous eyes

AIM:To investigate vascular changes in different stages of glaucoma and to evaluate the role of optical coherence tomography angiography(OCTA)in the early diagnosis of glaucoma.METHODS:Glaucoma patients and healthy controls(n=29 eyes)were investigated in this cross-sectional comparative study.Glaucoma patients were grouped as ocular hypertension(n=44 eyes),preperimetric glaucoma(PPG;n=32 eyes),early glaucoma(EG;n=35 eyes),moderate stage glaucoma(MG;n=36 eyes),and advanced glaucoma(AG;n=35 eyes).Peripapillary and macular vascular densities(VDs)of all participants were compared and correlations of VDs and retinal nerve fiber layer thickness(RNFLT),ganglion cell analysis(GCA),and visual field(VF)tests were evaluated.Area under the receiver operation characteristic curves(AUC)of the peripapillary and macular VD parameters were obtained.RESULTS:VD values decreased with the progression of glaucoma.Most peripapillary and macular VD parameters of PPG and EG groups were lower than healthy controls(P<0.001).There was no significant difference in RNFLT between the PPG and EG groups,but most peripapillary and macular VDs were found to be lower in EG group than in PPG group(P<0.05).In most disease group,VDs were significantly correlated with OCT parameters(P<0.001)and VF index(P<0.05).There were no significant correlations between VF and RNFLT indices in the AG group,but significant correlations were found between VF and VD values(P<0.05).AUC for discriminating between healthy and glaucomatous eyes were highest in whole image peripapillary VD(AUC:0.865,0.929,and 0.986,respectively in EG,MG,and AG groups).CONCLUSION:OCTA can be used in the early diagnosis of glaucoma and can be useful in follow-up of the advanced disease.In cases where limitations or suspicions in structural and functional tests are present,OCTA can be used as a supportive diagnostic test,both in EG and AG.

基于多任务学习的青光眼智能诊断

为了提高青光眼检测的准确率,降低青光眼的危害,本文提出一种基于多任务学习的青光眼智能诊断方法,将U-Net网络和VGG16网络结合,U-Net网络和VGG16网络共用U-Net网络的编码器部分,通过U-Net网络得到杯盘比(cup-to-disc ratio,CDR),并且将CDR作为眼底图像的特征之一输入VGG16网络,实现眼底图像的青光眼分类。实验使用REFUGE挑战数据集进行验证,网络模型在训练后得到的工作特性曲线下面积为0.9788,且视盘和视杯的分割准确率分别达到0.8745和0.9624,对比其他使用相同数据集的方法,本方法具有更高的青光眼分类准确率。

青少年型开角型青光眼的遗传特征和基因研究进展

青少年型开角型青光眼(JOAG)是原发性开角型青光眼(POAG)的一个亚型,具有较高的致残率,严重影响年轻患者的生活质量。研究发现JOAG有着多样化的遗传方式,虽然JOAG通常被认为是一种常染色体显性遗传疾病,但在特定人群中,常染色体隐性遗传同样存在。而JOAG的多变遗传倾向可能是由多个关键致病基因共同调控的结果,其中包括MYOC、CYP1B1和CPAMD8等代表性基因。这些基因的突变通常与眼部组织的多种生物学过程密切相关,主要包括细胞代谢调控、氧化应激反应以及程序性死亡的异常诱导。因此,深入研究JOAG相关的致病基因至关重要,这将为揭示该疾病的发生、发展及临床表型的具体遗传背景,并且为早期识别和筛查高风险人群提供有力依据。文章旨在重点关注JOAG的遗传特征和基因研究。通过系统性回顾相关文献,总结了与JOAG疾病相关的致病基因及其突变,并探讨其在JOAG研究领域未来发展中的潜在应用和价值,为JOAG的诊断和治疗提供有益的见解。

新型纳米材料在青光眼诊疗中的研究进展

青光眼是导致视力丧失的主要原因之一,其诊疗仍存在诸多困难,如持续眼压监测、抗青光眼药物制剂的副作用和长期应用以及引流物植入术后的并发症等。纳米材料因其具有尺寸小、生物相容性好、靶向性等优点,为改善青光眼诊疗等方面提供了更多选择。目前,纳米材料已被应用于24 h眼压监测、药物缓释以及制备新型植入物,有望在一定程度上克服目前青光眼诊疗的局限。本文将对近年来多种新型纳米材料在青光眼疾病诊疗中应用的研究进展做一综述,并探索未来纳米材料用于治疗眼部疾病的新可能。

猫继发性青光眼的诊治

青光眼是小动物临床眼科常见疾病,病因可分为原发性与继发性。在猫科动物中原发性较罕见,临床上更常见的是继发性青光眼,多与眼内炎症有关。现将1例猫继发性青光眼的诊治方法报道,以期为猫青光眼临床诊断和治疗提供参考。

近视病人青光眼诊断的研究进展

近视是青光眼发病的高危因素,且研究表明近视程度越高,患青光眼的可能性就越大。近视病人青光眼诊断是一个特殊问题,这可能因为早期青光眼与近视的表现相似,所以许多近视病人因青光眼而使视力受到损害,但未引起临床医生考虑青光眼的可能性。近年来随着眼科影像技术的发展,尤其是光学相干断层扫描与共焦激光眼底扫描红外成像及无赤光眼底照相技术的结合、光学相干断层扫描离散傅里叶变换分析与视野的结合,光学相干断层扫描血流成像的快速革新,临床医生可以从多方面了解近视与青光眼的发生发展,为早期诊断近视眼青光眼,及时干预治疗,从而为提高近视病人的视觉生活质量提供坚实的基础。

邦纳综合征研究进展

邦纳综合征(CBS)描述了在没有神经精神障碍的人群中,由于视觉通路损害而出现的幻视。CBS患者通常能洞察到幻觉不是真实的,该病可能是偶发性的、周期性的或者慢性的。由于CBS缺乏统一的诊断标准,加上部分患者对承认幻视存在顾虑,该病的患病率存在差异,从0.4%到30%不等。大量研究表明CBS可能与许多眼部疾病有关,如年龄相关性黄斑变性、青光眼等。除此之外,也有继发于眼科手术或药物治疗的CBS相关报道,因此临床医生应提高对该病的重视,及时诊断并缓解患者情绪。目前有关CBS的眼科学文献资料较少,有必要对其进行总结分析,以探讨其发病机制和诊疗方案。本文就以近年来一些与CBS有关的研究做一综述。

计算机视觉辅助青光眼诊断算法研究

青光眼是一类视神经损伤疾病,青光眼筛查工作对眼科医师的诊断水平有很高的要求。为帮助医生更好地观察青光眼病理特征,提高医生的主观诊断效率和准确率,本文应用计算机视觉辅助诊断算法增强视网膜图像,并使用神经网络构建图像的分类识别模型。实验结果显示,所构建的神经网络对视网膜图像分类的准确率为92.05%。

The East London glaucoma prediction score: web-based validation of glaucoma risk screening tool

AIM:It is difficult for Optometrists and General Practitioners to know which patients are at risk. The East London glaucoma prediction score (ELGPS) is a web based risk calculator that has been developed to determine Glaucoma risk at the time of screening. Multiple risk factors that are available in a low tech environment are assessed to provide a risk assessment. This is extremely useful in settings where access to specialist care is difficult. Use of the calculator is educational. It is a free web based service. Data capture is user specific. METHODS:The scoring system is a web based questionnaire that captures and subsequently calculates the relative risk for the presence of Glaucoma at the time of screening. Three categories of patient are described:Unlikely to have Glaucoma; Glaucoma Suspect and Glaucoma. A case review methodology of patients with known diagnosis is employed to validate the calculator risk assessment. RESULTS:Data from the patient records of 400 patients with an established diagnosis has been captured and used to validate the screening tool. The website reports that the calculated diagnosis correlates with the actual diagnosis 82% of the time. Biostatistics analysis showed:Sensitivity = 88% ; Positive predictive value = 97%; Specificity = 75%. CONCLUSION:Analysis of the first 400 patients validates the web based screening tool as being a good method of screening for the at risk population. The validation is ongoing. The web based format will allow a more widespread recruitment for different geographic, population and personnel variables.

Applications of the isolated-check visual evoked potential in primary open angle glaucoma with or without high myopia

AIM:To explore the diagnostic performance of isolatedcheck visual evoked potential(ic VEP)for primary open angle glaucoma(POAG)in both highly myopic and nonhighly myopic populations and compare it with those of optical coherence tomography(OCT)and Heidelberg retinal tomography(HRT)parameters.METHODS:A total of 126 participants were recruited,including 31 highly myopic participants with POAG(HM-POAG),36 non-highly myopic participants with POAG(NHM-POAG),25 highly myopic participants without POAG(HM)and 34 controls without high myopia(Normal).All the participants underwent a complete ophthalmic examination.The signal-to-noise ratio(SNR)was used to assess the ic VEP.Both qualitative and quantitative diagnostic performances of OCT,HRT and the ic VEP were analyzed and compared.RESULTS:Based on the criterion of SNR≤1,the diagnostic performance of the ic VEP in highly myopic subjects[area under the receiver operating characteristic curve(AUC)=0.862]was better than that in non-highly myopic subjects(AUC=0.789),and the SNR had fairly good specificity.In distinguishing the HM-POAG and HM groups,the AUC of the SNR was not different from those of the OCT and HRT parameters(P>0.05)in either the qualitative or quantitative comparison.In the qualitative analysis,the ic VEP showed good consistency with damage to the central 10°of the visual field(kappa=0.695-0.747,P<0.001).CONCLUSION:The ic VEP has the potential to discriminate individuals with and without POAG,especially in populations with high myopia.