Predictive visual field outcomes after optic chiasm decompressive surgery by retinal vessels parameters using optical coherence tomography angiography

AIM:To evaluate the predictive value of superficial retinal capillary plexus(SRCP)and radial peripapillary capillary(RPC)for visual field recovery after optic cross decompression and compare them with peripapillary nerve fiber layer(pRNFL)and ganglion cell complex(GCC).METHODS:This prospective longitudinal observational study included patients with chiasmal compression due to sellar region mass scheduled for decompressive surgery.Generalized estimating equations were used to compare retinal vessel density and retinal layer thickness preand post-operatively and with healthy controls.Logistic regression models were used to assess the relationship between preoperative GCC,pRNFL,SRCP,and RPC parameters and visual field recovery after surgery.RESULTS:The study included 43 eyes of 24 patients and 48 eyes of 24 healthy controls.Preoperative RPC and SRCP vessel density and pRNFL and GCC thickness were lower than healthy controls and higher than postoperative values.The best predictive GCC and pRNFL models were based on the superior GCC[area under the curve(AUC)=0.866]and the tempo-inferior pRNFL(AUC=0.824),and the best predictive SRCP and RPC models were based on the nasal SRCP(AUC=0.718)and tempo-inferior RPC(AUC=0.825).There was no statistical difference in the predictive value of the superior GCC,tempo-inferior pRNFL,and tempo-inferior RPC(all P>0.05).CONCLUSION:Compression of the optic chiasm by tumors in the saddle area can reduce retinal thickness and blood perfusion.This reduction persists despite the recovery of the visual field after decompression surgery.GCC,pRNFL,and RPC can be used as sensitive predictors of visual field recovery after decompression surgery.

A Deformable Network with Attention Mechanism for Retinal Vessel Segmentation

The intensive application of deep learning in medical image processing has facilitated the advancement of automatic retinal vessel segmentation research.To overcome the limitation that traditional U-shaped vessel segmentation networks fail to extract features in fundus image sufficiently,we propose a novel network(DSeU-net)based on deformable convolution and squeeze excitation residual module.The deformable convolution is utilized to dynamically adjust the receptive field for the feature extraction of retinal vessel.And the squeeze excitation residual module is used to scale the weights of the low-level features so that the network learns the complex relationships of the different feature layers efficiently.We validate the DSeU-net on three public retinal vessel segmentation datasets including DRIVE,CHASEDB1,and STARE,and the experimental results demonstrate the satisfactory segmentation performance of the network.

SepFE:Separable Fusion Enhanced Network for Retinal Vessel Segmentation

The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.

DT-Net:Joint Dual-Input Transformer and CNN for Retinal Vessel Segmentation

Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high noise,and complex structure.It makes vessel segmentation very challenging.Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network(U-Net)models,and they have many limitations and shortcomings,such as the loss of microvascular details at the end of the vessels.We address the limitations of convolution by introducing the transformer into retinal vessel segmentation.Therefore,we propose a hybrid method for retinal vessel segmentation based on modulated deformable convolution and the transformer,named DT-Net.Firstly,multi-scale image features are extracted by deformable convolution and multi-head selfattention(MHSA).Secondly,image information is recovered,and vessel morphology is refined by the proposed transformer decoder block.Finally,the local prediction results are obtained by the side output layer.The accuracy of the vessel segmentation is improved by the hybrid loss function.Experimental results show that our method obtains good segmentation performance on Specificity(SP),Sensitivity(SE),Accuracy(ACC),Curve(AUC),and F1-score on three publicly available fundus datasets such as DRIVE,STARE,and CHASE_DB1.

Effects of two different doses of intravitreal bevacizumab on subfoveal choroidal thickness and retinal vessel diameter in branch retinal vein occlusion

AIM： To investigate the effects of two different doses of intravitreal bevacizumab on subfoveal choroidal thickness （SFChT） and retinal vessel diameter in patients with branch retinal vein occlusion. METHODS： An interventional, restrospective study of 41 eyes of 41 patients who had completed 12mo of follow-up, divided into group 1 （1.25 mg of bevacizumab, 21 eyes of 21 patients） and group 2 （2.5 mg of bevacizumab, 20 eyes of 21 patients）. Complete ophthalmic examination, fluorescein angiography, enhanced depth imaging optical coherence tomography and measurement of retinal vessel diameter with IVAN software were performed at baseline and follow-up. RESULTS： The SFChT changed from 279.1 （165-431） μm at baseline to 277.0 （149-413） μm at 12mo in group 1 （P= 0.086）, and from 301.4 （212-483） μm to 300.3 （199-514） μm in group 2 （P=0.076）. The central retinal arteriolar equivalent （CRAE） changed from 128.8 ±11.2 μm at baseline to 134.5±8.4 μm at 12mo in group 1, and from 134.6±9.0 μm to 131.4±12.7 μm in group 2 （P =0.767）. The central retinal venular equivalent （CRVE） changed from 204.1±24.4 μm at baseline to 196.3±28.2 μm at 12mo in group 1, and from 205.8±16.3 μm to 194.8±18.2 μm in group 2 （P=0.019）. The mean central macular thickness （P〈0.05） and average best-corrected visual acuity （BCVA; P〈0.05） improved in both groups CONCLUSION： Changes in the SFChT are not statistically significant and not different according to the doses of bevacizumab. The CRAE did not show significant change, however, the CRVE showed significant decrease regardless of the dose.

MIA-UNet:Multi-Scale Iterative Aggregation U-Network for Retinal Vessel Segmentation

As an important part of the new generation of information technology,the Internet of Things(IoT)has been widely concerned and regarded as an enabling technology of the next generation of health care system.The fundus photography equipment is connected to the cloud platform through the IoT,so as to realize the realtime uploading of fundus images and the rapid issuance of diagnostic suggestions by artificial intelligence.At the same time,important security and privacy issues have emerged.The data uploaded to the cloud platform involves more personal attributes,health status and medical application data of patients.Once leaked,abused or improperly disclosed,personal information security will be violated.Therefore,it is important to address the security and privacy issues of massive medical and healthcare equipment connecting to the infrastructure of IoT healthcare and health systems.To meet this challenge,we propose MIA-UNet,a multi-scale iterative aggregation U-network,which aims to achieve accurate and efficient retinal vessel segmentation for ophthalmic auxiliary diagnosis while ensuring that the network has low computational complexity to adapt to mobile terminals.In this way,users do not need to upload the data to the cloud platform,and can analyze and process the fundus images on their own mobile terminals,thus eliminating the leakage of personal information.Specifically,the interconnection between encoder and decoder,as well as the internal connection between decoder subnetworks in classic U-Net are redefined and redesigned.Furthermore,we propose a hybrid loss function to smooth the gradient and deal with the imbalance between foreground and background.Compared with the UNet,the segmentation performance of the proposed network is significantly improved on the premise that the number of parameters is only increased by 2%.When applied to three publicly available datasets:DRIVE,STARE and CHASE DB1,the proposed network achieves the accuracy/F1-score of 96.33%/84.34%,97.12%/83.17%and 97.06%/84.10%,respectively.The experimental results show that the MIA-UNet is superior to the state-of-the-art methods.

Characterization of human retinal vessel arborisation in normal and amblyopic eyes using multifractal analysis

AIMTo characterize the human retinal vessel arborisation in normal and amblyopic eyes using multifractal geometry and lacunarity parameters.METHODSMultifractal analysis using a box counting algorithm was carried out for a set of 12 segmented and skeletonized human retinal images, corresponding to both normal (6 images) and amblyopia states of the retina (6 images).RESULTSIt was found that the microvascular geometry of the human retina network represents geometrical multifractals, characterized through subsets of regions having different scaling properties that are not evident in the fractal analysis. Multifractal analysis of the amblyopia images (segmented and skeletonized versions) show a higher average of the generalized dimensions (Dq) for q=0, 1, 2 indicating a higher degree of the tree-dimensional complexity associated with the human retinal microvasculature network whereas images of healthy subjects show a lower value of generalized dimensions indicating normal complexity of biostructure. On the other hand, the lacunarity analysis of the amblyopia images (segmented and skeletonized versions) show a lower average of the lacunarity parameter Λ than the corresponding values for normal images (segmented and skeletonized versions).CONCLUSIONThe multifractal and lacunarity analysis may be used as a non-invasive predictive complementary tool to distinguish amblyopic subjects from healthy subjects and hence this technique could be used for an early diagnosis of patients with amblyopia.

Modified Anam-Net Based Lightweight Deep Learning Model for Retinal Vessel Segmentation

The accurate segmentation of retinal vessels is a challenging taskdue to the presence of various pathologies as well as the low-contrast ofthin vessels and non-uniform illumination. In recent years, encoder-decodernetworks have achieved outstanding performance in retinal vessel segmentation at the cost of high computational complexity. To address the aforementioned challenges and to reduce the computational complexity, we proposea lightweight convolutional neural network (CNN)-based encoder-decoderdeep learning model for accurate retinal vessels segmentation. The proposeddeep learning model consists of encoder-decoder architecture along withbottleneck layers that consist of depth-wise squeezing, followed by fullconvolution, and finally depth-wise stretching. The inspiration for the proposed model is taken from the recently developed Anam-Net model, whichwas tested on CT images for COVID-19 identification. For our lightweightmodel, we used a stack of two 3 × 3 convolution layers (without spatialpooling in between) instead of a single 3 × 3 convolution layer as proposedin Anam-Net to increase the receptive field and to reduce the trainableparameters. The proposed method includes fewer filters in all convolutionallayers than the original Anam-Net and does not have an increasing numberof filters for decreasing resolution. These modifications do not compromiseon the segmentation accuracy, but they do make the architecture significantlylighter in terms of the number of trainable parameters and computation time.The proposed architecture has comparatively fewer parameters (1.01M) thanAnam-Net (4.47M), U-Net (31.05M), SegNet (29.50M), and most of the otherrecent works. The proposed model does not require any problem-specificpre- or post-processing, nor does it rely on handcrafted features. In addition,the attribute of being efficient in terms of segmentation accuracy as well aslightweight makes the proposed method a suitable candidate to be used in thescreening platforms at the point of care. We evaluated our proposed modelon open-access datasets namely, DRIVE, STARE, and CHASE_DB. Theexperimental results show that the proposed model outperforms several stateof-the-art methods, such as U-Net and its variants, fully convolutional network (FCN), SegNet, CCNet, ResWNet, residual connection-based encoderdecoder network (RCED-Net), and scale-space approx. network (SSANet) in terms of {dice coefficient, sensitivity (SN), accuracy (ACC), and the areaunder the ROC curve (AUC)} with the scores of {0.8184, 0.8561, 0.9669, and0.9868} on the DRIVE dataset, the scores of {0.8233, 0.8581, 0.9726, and0.9901} on the STARE dataset, and the scores of {0.8138, 0.8604, 0.9752,and 0.9906} on the CHASE_DB dataset. Additionally, we perform crosstraining experiments on the DRIVE and STARE datasets. The result of thisexperiment indicates the generalization ability and robustness of the proposedmodel.

Changes in retinal vessel diameters in migraine patients during attack-free period

AIM：To evaluate the retinal vessel diameters in patients with migraine by optical coherence tomography（OCT）.METHODS：In this cross-sectional study,124 eyes of 62 patients with a diagnosis of unilateral migraine during attack-free period and 42 age-and sex-matched control subjects were included. Migraine patients were divided into the ≤2 migraine attacks per month group and the ≥5 migraine attacks per month group. All subjects underwent complete ophthalmological and neurological examinations before measurements. Retinal vessel diameters and choroidal thickness were examined with the Spectralis OCT.RESULTS：The mean diameters of the arteries in the eyes on the headache side of control group,≥5 migraine attacks per month and ≤2 migraine attacks per month group at 480 μm from the optic disk（Raster 3）were 119.54±46.69,136.68±25.93 and 119.34±31.75 μm respectively with a steady decline to 105.57±32.15,118.18±31.87 and 108.05±38.77 μm at 1440 μm（Raster 7）,the last measurement point,respectively. The retinal artery diameter measurements were significantly increased in ≥5 migraine attacks per month patients at four out of five measured points compared to control group（P〈0.05）. There were no statistical differences at any of the points of vein measurements. The choroidal thickness measurements were significantly decreased in ≥5 migraine attacks per month patients at all measured points compared to control group（P〈0.05）.CONCLUSION：The retinal artery diameter is found to increase significantly and the choroidal thickness is found to decrease in the eyes on the headache side in ≥5 migraine attacks per month patients compared to control group.

OCTA characteristics in non-arteritic central retinal artery occlusion and correlation with visual acuity

AIM:To observe the retinal and choroidal circulations in patients with non-arteritic permanent central retinal artery occlusion(NA-CRAO)via optical coherence tomography angiography(OCTA)and analyze their correlation with visual acuity.METHODS:Sixty-two eyes with clinically confirmed acute NA-CRAO were included in the study and divided into:A type(mild n=29),B type(moderate n=27)and C type(severe n=6)based on the degree of visual loss,retinal edema,and arterial blood flow delay in fundus fluorescence angiography(FFA).Contralateral healthy eyes were used as the control group.Best-corrected visual acuity(BCVA),slit lamp microscopy,indirect ophthalmoscopy,fundus color photography,OCTA,and FFA were performed.Spearman’s correlation analysis was used to determine the correlations between retinal and choroidal vessels and visual acuity.RESULTS:There were no statistically significant differences in age,gender,and intraocular pressure among the three types and the control group(P>0.05).Vessel density in deep capillary plexus(VD-DCP)significantly decreased(P<0.05)in all three types of NA-CRAO patients compared to the control group.Vessel density in superficial vascular plexus(VD-SVP)significantly decreased(P<0.05)in type A patients and choriocapillaris flow area significantly decreased(P<0.05)in type B and type C patients compared to the control group;while outer retinal flow areas significantly increased in the type A(P<0.05)and decreased in type C patients(P<0.05).The retinal thickness significantly increased in type C group(P<0.05).The VD-SVP at fovea in the type A was significantly lower than both of type B and C.The VD-SVP at nasal parafovea in type A and B was significantly lower than type C(P<0.05).The logMAR BCVA of type A was significantly better than that of type B and C groups(P<0.05).Spearman’s correlation analysis showed that the logMAR BCVA was positively correlated with VD-SVP at fovea(r=0.679,P=0.031)and nasal parafovea(r=0.826,P=0.013).CONCLUSION:OCTA is valuable for assessing retinal ischemia,and evaluating visual impairment.Deep retinal vasculature is commonly affected in all NA-CRAO types.VDSVPs at fovea and nasal parafovea can serve as reliable markers of visual impairment in NA-CRAO.

A saliency and Gaussian net model for retinal vessel segmentation

Retinal vessel segmentation is a significant problem in the analysis of fundus images.A novel deep learning structure called the Gaussian net(GNET)model combined with a saliency model is proposed for retinal vessel segmentation.A saliency image is used as the input of the GNET model replacing the original image.The GNET model adopts a bilaterally symmetrical structure.In the left structure,the first layer is upsampling and the other layers are max-pooling.In the right structure,the final layer is max-pooling and the other layers are upsampling.The proposed approach is evaluated using the DRIVE database.Experimental results indicate that the GNET model can obtain more precise features and subtle details than the UNET models.The proposed algorithm performs well in extracting vessel networks,and is more accurate than other deep learning methods.Retinal vessel segmentation can help extract vessel change characteristics and provide a basis for screening the cerebrovascular diseases.

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.

Identification of retinal thickness and blood flow in agerelated macular degeneration with reticular pseudodrusen

AIM:To investigate thickness characteristics and vascular plexuses in retinas with reticular pseudodrusen(RPD)as an early detection strategy for age-related macular degeneration(AMD).METHODS:This retrospective study included 24 subjects(33 eyes)with RPD and 25 heathy control subjects(34 eyes).The superficial capillary plexus(SCP)and the deep capillary plexus(DCP)of the retinal posterior poles were investigated with optical coherence tomography angiography(OCTA).Retinal thicknesses and vessel densities were analyzed statistically.RESULTS:The general retinal thicknesses of RPD eyes were significantly decreased(95%CI-14.080,-0.655;P=0.032).The vessel densities of DCP in RPD eyes were significantly increased in the global(95%CI 1.067,7.312;P=0.027),parafoveal(95%CI 0.417,5.241;P=0.022),and perifoveal(95%CI 0.181,6.842;P=0.039)quadrants.However,the vessel densities of the SCP were rarely increased in the eyes with RPD.CONCLUSION:The thinning of retinas in the RPD group suggests a reduction in the number of cells.Additionally,the increased vessel density of the DCP in retinas with RPD indicates a greater demand for blood supply,possibly due to the hypoxia induced RPD compensation caused by RPD in the outer retina.This study highlights the pathological risks associated with RPD and emphasizes the importance of early intervention to retard the progression of AMD.

Structural measurements and vessel density of spectraldomain optic coherence tomography in early,moderate,and severe primary angle-closure glaucoma

AIM:To compare the macular ganglion cell-inner plexiform layer(GCIPL)thickness,retinal nerve fiber layer(RNFL)thickness,optic nerve head(ONH)parameters,and retinal vessel density(VD)measured by spectral-domain optical coherence tomography(SD-OCT)and analyze the correlations between them in the early,moderate,severe primary angle-closure glaucoma(PACG)and normal eyes.METHODS:Totally 70 PACG eyes and 20 normal eyes were recruited for this retrospective analysis.PACG eyes were further separated into early,moderate,or severe PACG eyes using the Enhanced Glaucoma Staging System(GSS2).The GCIPL thickness,RNFL thickness,ONH parameters,and retinal VD were measured by SD-OCT,differences among the groups and correlations within the same group were calculated.RESULTS:The inferior and superotemporal sectors of the GCIPL thickness,rim area of ONH,average and inferior sector of the retinal VD were significantly reduced(all P<0.05)in the early PACG eyes compared to the normal and the optic disc area,cup to disc ratio(C/D),and cup volume were significantly higher(all P<0.05);but the RNFL was not significant changes in early and moderate PACG.In severe group,the GCIPL and RNFL thickness were obvious thinning with retinal VD were decreasing as well as C/D and cup volume increasing than other three groups(all P<0.01).In the early PACG subgroup,there were significant positive correlations between retinal VD and GCIPL thickness(except superonasal and inferonasal sectors,r=0.573 to 0.641,all P<0.05),superior sectors of RNFL thickness(r=0.055,P=0.049).More obvious significant positive correlations were existed in moderate PACG eyes between retinal VD and superior sectors of RNFL thickness(r=0.650,P=0.022),and temporal sectors of RNFL thickness(r=0.740,P=0.006).In the severe PACG eyes,neither GCIPL nor RNFL thickness was associated with retinal VD.CONCLUSION:The ONH damage and retinal VD loss appears earlier than RNFL thickness loss in PACG eyes.As the PACG disease progressed from the early to the moderate stage,the correlations between the retinal VD and RNFL thickness increases.

Automatic Vessel Segmentation on Retinal Images

Several features of retinal vessels can be used to monitor the progression of diseases. Changes in vascular structures, for example, vessel caliber, branching angle, and tortuosity, are portents of many diseases such as diabetic retinopathy and arterial hypertension. This paper proposes an automatic retinal vessel segmentation method based on morphological closing and multi-scale line detection. First, an illumination correction is performed on the green band retinal image. Next, the morphological closing and subtraction processing are applied to obtain the crude retinal vessel image. Then, the multi-scale line detection is used to fine the vessel image. Finally, the binary vasculature is extracted by the Otsu algorithm, in this paper, for improving the drawbacks of multi-scale line detection, only the line detectors at 4 scales are used. The experimental results show that the accuracy is 0.939 for DRIVE （digital retinal images for vessel extraction） retinal database, which is much better than other methods.

MF~2ResU-Net:a multi-feature fusion deep learning architecture for retinal blood vessel segmentation

Objective For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation,a novel multi-level method based on the multi-scale fusion residual neural network(MF2ResU-Net)model is proposed.Methods To obtain refined features of retinal blood vessels,three cascade connected UNet networks are employed.To deal with the problem of difference between the parts of encoder and decoder,in MF2ResU-Net,shortcut connections are used to combine the encoder and decoder layers in the blocks.To refine the feature of segmentation,atrous spatial pyramid pooling(ASPP)is embedded to achieve multi-scale features for the final segmentation networks.Results The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity(Sen),specificity(Spe),accuracy(ACC),and area under curve(AUC),the values of which are 0.8013 and 0.8102,0.9842 and 0.9809,0.9700 and 0.9776,and 0.9797 and 0.9837,respectively for DRIVE and CHASE DB1.The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.Conclusion Based on residual connections and multi-feature fusion,the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features,which can provide another diagnosis method for computer-aided Chinese medical diagnosis.

A retinal blood vessel extraction algorithm based on CART decision tree and improved AdaBoost

This paper presents a supervised learning algorithm for retinal vascular segmentation based on classification and regression tree (CART) algorithm and improved adptive bosting (AdaBoost). Local binary patterns (LBP) texture features and local features are extracted by extracting,reversing,dilating and enhancing the green components of retinal images to construct a 17-dimensional feature vector. A dataset is constructed by using the feature vector and the data manually marked by the experts. The feature is used to generate CART binary tree for nodes,where CART binary tree is as the AdaBoost weak classifier,and AdaBoost is improved by adding some re-judgment functions to form a strong classifier. The proposed algorithm is simulated on the digital retinal images for vessel extraction (DRIVE). The experimental results show that the proposed algorithm has higher segmentation accuracy for blood vessels,and the result basically contains complete blood vessel details. Moreover,the segmented blood vessel tree has good connectivity,which basically reflects the distribution trend of blood vessels. Compared with the traditional AdaBoost classification algorithm and the support vector machine (SVM) based classification algorithm,the proposed algorithm has higher average accuracy and reliability index,which is similar to the segmentation results of the state-of-the-art segmentation algorithm.

Changes of the peripapillary vascular parameters inpremature infants without retinopathy of prematurityusing U-net segmentation

AIM:To quantitatively assess the changes in mean vascular tortuosity(mVT)and mean vascular width(mVW)around the optic disc and their correlation with gestational age(GA)and birth weight(BW)in premature infants without retinopathy of prematurity(ROP).METHODS:A single-center retrospective study included a total of 133(133 eyes)premature infants[mean corrected gestational age(CGA)43.6wk]without ROP as the premature group and 130(130 eyes)CGA-matched fullterm infants as the control group.The peripapillary mVT and mVW were quantitatively measured using computerassisted techniques.RESULTS:Premature infants had significantly higher mVT(P=0.0032)and lower mVW(P=0.0086)by 2.68(10^(4) cm^(-3))and 1.85μm,respectively.Subgroup analysis with GA showed significant differences(P=0.0244)in mVT between the early preterm and middle to late preterm groups,but the differences between mVW were not significant(P=0.6652).The results of the multiple linear regression model showed a significant negative correlation between GA and BW with mVT after adjusting sex and CGA(P=0.0211 and P=0.0006,respectively).For each day increase in GA at birth,mVT decreased by 0.1281(10^(4) cm^(-3))and for each 1 g increase in BW,mVT decreased by 0.006(10^(4) cm^(-3)).However,GA(P=0.9402)and BW(P=0.7275)were not significantly correlated with mVW.CONCLUSION:Preterm birth significantly affects the peripapillary vascular parameters that indicate higher mVT and narrower mVW in premature infants without ROP.Alterations in these parameters may provide new insights into the pathogenesis of ocular vascular disease.

Hyperuricemia Accompanied with Changes in the Retinal Microcirculation in a Chinese High-risk Population for Diabetes

Objective To investigate the association of retinal vascular calibers with hyperuricemia in a middle‐aged and elderly population. Methods A cross‐sectional design was applied in this study and 869 participants aged ≥40 years from a high‐risk group for diabetes were recruited. All participants received the anthropometrical measurements and laboratory tests. Retinal arteriolar and venular caliber of the participants were measured with a semi‐automated system. Hyperuricemia was defined as a serum uric acid level 420 μmol/L in men and 360 μmol/L in women. Linear regression models were used to assess the association of hyperuricemia with retinal vascular calibers. These models were additionally adjusted for age, central obesity, hypertension, dyslipidemia, weekly activity, smoking status, and education. Results Among the 869 participants, 133 （15.3%） suffered from hyperuricemia. The crude mean serum uric acid level was 312.3 μmol/L （Standard Deviation 79.5）; mean concentration was 355.0 μmol/L （SD 75.5） in male participants, and 288.0 μmol/L （SD 71.1） in female participants （age‐adjusted difference 58.1 μmol/L, 95% Confidence Internal 48.5, 67.6）. After adjusting for additional covariates, male participants with hyperuricemia had 3.77 μm （95% CI ‐0.46, 8.00） smaller arteriolar caliber and 6.20 μm （95% CI 0.36, 12.04） larger venule than those without hyperuricemia; the corresponding numbers among female participants were 1.57 μm （95% CI ‐1.07, 4.21） for retinal arteriolar caliber and 2.28 μm （95% CI ‐1.72, 6.27） for retinal venular caliber. Conclusion Hyperuricemia was associated with smaller retinal arteriolar caliber and larger venular caliber mainly in male participants in this study.

Analysis of normal human retinal vascular network architecture using multifractal geometry

AIM：To apply the multifractal analysis method as a quantitative approach to a comprehensive description of the microvascular network architecture of the normal human retina.METHODS：Fifty volunteers were enrolled in this study in the Ophthalmological Clinic of Cluj-Napoca,Romania,between January 2012 and January 2014. A set of 100 segmented and skeletonised human retinal images,corresponding to normal states of the retina were studied. An automatic unsupervised method for retinal vessel segmentation was applied before multifractal analysis. The multifractal analysis of digital retinal images was made with computer algorithms,applying the standard boxcounting method. Statistical analyses were performed using the Graph Pad In Stat software.RESULTS：The architecture of normal human retinal microvascular network was able to be described using the multifractal geometry. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα=α_（max）-α_（min））and the spectrum arms＇ heights difference（│Δf│）of the normal images were expressed as mean±standard deviation（SD）：for segmented versions,D_0=1.7014±0.0057; D_1=1.6507±0.0058; D_2=1.5772±0.0059; Δα=0.92441±0.0085; │Δf│= 0.1453±0.0051; for skeletonised versions,D_0=1.6303±0.0051; D_1=1.6012±0.0059; D_2=1.5531± 0.0058; Δα=0.65032±0.0162; │Δf│= 0.0238±0.0161. The average of generalized dimensions（D_q）for q=0,1,2,the width of the multifractal spectrum（Δα）and the spectrum arms＇ heights difference（│Δf│）of the segmented versions was slightly greater than the skeletonised versions.CONCLUSION：The multifractal analysis of fundus photographs may be used as a quantitative parameter for the evaluation of the complex three-dimensional structure of the retinal microvasculature as a potential marker for early detection of topological changes associated with retinal diseases.