Inherited retinal diseases(IRD)are a leading cause of blindness in the working age population.The advances in ocular genetics,retinal imaging and molecular biology,have conspired to create the ideal environment for es...Inherited retinal diseases(IRD)are a leading cause of blindness in the working age population.The advances in ocular genetics,retinal imaging and molecular biology,have conspired to create the ideal environment for establishing treatments for IRD,with the first approved gene therapy and the commencement of multiple therapy trials.The scope of this review is to familiarize clinicians and scientists with the current landscape of retinal imaging in IRD.Herein we present in a comprehensive and concise manner the imaging findings of:(I)macular dystrophies(MD)[Stargardt disease(ABCA4),X-linked retinoschisis(RS1),Best disease(BEST1),pattern dystrophy(PRPH2),Sorsby fundus dystrophy(TIMP3),and autosomal dominant drusen(EFEMP1)],(II)cone and cone-rod dystrophies(GUCA1A,PRPH2,ABCA4 and RPGR),(III)cone dysfunction syndromes[achromatopsia(CNGA3,CNGB3,PDE6C,PDE6H,GNAT2,ATF6],blue-cone monochromatism(OPN1LW/OPN1MW array),oligocone trichromacy,bradyopsia(RGS9/R9AP)and Bornholm eye disease(OPN1LW/OPN1MW),(IV)Leber congenital amaurosis(GUCY2D,CEP290,CRB1,RDH12,RPE65,TULP1,AIPL1 and NMNAT1),(V)rod-cone dystrophies[retinitis pigmentosa,enhanced S-Cone syndrome(NR2E3),Bietti crystalline corneoretinal dystrophy(CYP4V2)],(VI)rod dysfunction syndromes(congenital stationary night blindness,fundus albipunctatus(RDH5),Oguchi disease(SAG,GRK1),and(VII)chorioretinal dystrophies[choroideremia(CHM),gyrate atrophy(OAT)].展开更多
Retinal imaging is pivotal in the evaluation of ocular and systemic health,presenting significant promise for extensive popula-tion studies.However,the lack of standardized and automated techniques for extracting Imag...Retinal imaging is pivotal in the evaluation of ocular and systemic health,presenting significant promise for extensive popula-tion studies.However,the lack of standardized and automated techniques for extracting Imaging-Derived Phenotypes(IDPs)from retinal images is a major impediment.To counteract this challenge,the Chinese Human Phenome Project(CHPP)has developed a comprehensive protocol that includes Quality Control(QC),preprocessing,and automated or semi-automated extraction of IDPs from fundus photography and Optical Coherence Tomography(OCT)images.This protocol incorporates Artificial Intelligence(AI)-based methods to achieve accurate and efficient IDP extraction,facilitating standardized analysis of large-scale populations.We hope that this Standard Operating Procedure(SOP)guideline will impart valuable insights for ophthalmology-related disciplines and provides support for future research endeavors utilizing retinal imaging data.展开更多
Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility...Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata,and to offer a cost-effective approach for assessing brain health.Methods:Based on clinical information,retinal fundus images,and neuroimaging data derived from a multicenter,population-based cohort study,the Kai Luan Study,we proposed a cross-modal correlation representation(CMCR)network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects.Specifically,individual clinical information,which has been followed up for as long as 12 years,was encoded as a prompt to enhance the accuracy of brain volume estimation.Independent internal validation and external validation were performed to assess the robustness of the proposed model.Root mean square error(RMSE),peak signal-tonoise ratio(PSNR),and structural similarity index measure(SSIM)metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.Results:The proposed framework yielded average RMSE,PSNR,and SSIM values of 98.23,35.78 d B,and 0.64,respectively,which significantly outperformed 5 other methods:multi-channel Variational Autoencoder(mcVAE),Pixelto-Pixel(Pixel2pixel),transformer-based U-Net(Trans UNet),multi-scale transformer network(MT-Net),and residual vision transformer(ResViT).The two-(2D)and three-dimensional(3D)visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images.Thus,the CMCR framework accurately captured the latent structural correlations between the fundus and the brain.The average difference between predicted and actual brain volumes was 61.36 cm~3,with a relative error of 4.54%.When all of the clinical information(including age and sex,daily habits,cardiovascular factors,metabolic factors,and inflammatory factors)was encoded,the difference was decreased to 53.89 cm~3,with a relative error of 3.98%.Based on the synthesized brain magnetic resonance images from retinal fundus images,the volumes of brain tissues could be estimated with high accuracy.Conclusion:This study provides an innovative,accurate,and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.展开更多
AIM： To describe retinal findings of various imaging modalities in acute retinal ischemia. METHODS： Fluorescein angiography（FA）, spectral domain optical coherence tomography（SD-OCT）, OCTangiography（OCT-A） and ...AIM： To describe retinal findings of various imaging modalities in acute retinal ischemia. METHODS： Fluorescein angiography（FA）, spectral domain optical coherence tomography（SD-OCT）, OCTangiography（OCT-A） and fundus autofluorescence（FAF） images of 13 patients（mean age 64y, range 28-86y） with acute retinal ischemia were evaluated. Six suffered from branch arterial occlusion, 2 had a central retinal artery occlusion, 2 had a combined arteriovenous occlusions, 1 patient had a retrobulbar arterial compression by an orbital haemangioma and 2 patients showed an ocular ischemic syndrome.RESULTS： All patients showed increased reflectivity and thickening of the ischemic retinal tissue. In 10 out of 13 patients SD-OCT revealed an additional highly reflective band located within or above the outer plexiform layer. Morphological characteristics were a decreasing intensity with distance from the fovea, partially segmental occurrence and manifestation limited in time. OCT-A showed a loss of flow signal in the superficial and deep capillary plexus at the affected areas. Reduced flow signal was detected underneath the regions with retinal edema. FAF showed areas of altered signal intensity at the posterior pole. The regions of decreased FAF signal corresponded to peri-venous regions. CONCLUSION： Multimodal imaging modalities in retinal ischemia yield characteristic findings and valuable diagnostic information. Conventional OCT identifies hyperreflectivity and thickening and a mid-retinal hyperreflective band is frequently observed. OCT-A examination reveals demarcation of the ischemic retinal area on the vascular level. FAF shows decreased fluorescence signal in areas of retinal edema often corresponding to peri-venous regions.展开更多
With the help of adaptive optics （AO） technology, cellular level imaging of living human retina can be achieved. Aiming to reduce distressing feelings and to avoid potential drug induced diseases, we attempted to im...With the help of adaptive optics （AO） technology, cellular level imaging of living human retina can be achieved. Aiming to reduce distressing feelings and to avoid potential drug induced diseases, we attempted to image retina with dilated pupil and froze accommodation without drugs. An optimized liquid crystal adaptive optics camera was adopted for retinal imaging. A novel eye stared system was used for stimulating accommodation and fixating imaging area. Illumination sources and imaging camera kept linkage for focusing and imaging different layers. Four subjects with diverse degree of myopia were imaged. Based on the optical properties of the human eye, the eye stared system reduced the defocus to less than the typical ocular depth of focus. In this way, the illumination light can be projected on certain retina layer precisely. Since that the defocus had been compensated by the eye stared system, the adopted 512 × 512 liquid crystal spatial light modulator （LC-SLM） corrector provided the crucial spatial fidelity to fully compensate high-order aberrations. The Strehl ratio of a subject with -8 diopter myopia was improved to 0.78, which was nearly close to diffraction-limited imaging. By finely adjusting the axial displacement of illumination sources and imaging camera, cone photoreceptors, blood vessels and nerve fiber layer were clearly imaged successfully.展开更多
Even in the early stage,endocrine metabolism disease may lead to micro aneurysms in retinal capillaries whose diameters are less than 10 μm.However,the fundus cameras used in clinic diagnosis can only obtain images o...Even in the early stage,endocrine metabolism disease may lead to micro aneurysms in retinal capillaries whose diameters are less than 10 μm.However,the fundus cameras used in clinic diagnosis can only obtain images of vessels larger than 20 μm in diameter.The human retina is a thin and multiple layer tissue,and the layer of capillaries less than10 μm in diameter only exists in the inner nuclear layer.The layer thickness of capillaries less than 10 μm in diameter is about 40 μm and the distance range to rod＆cone cell surface is tens of micrometers,which varies from person to person.Therefore,determining reasonable capillary layer（CL） position in different human eyes is very difficult.In this paper,we propose a method to determine the position of retinal CL based on the rod＆cone cell layer.The public positions of CL are recognized with 15 subjects from 40 to 59 years old,and the imaging planes of CL are calculated by the effective focal length of the human eye.High resolution retinal capillary imaging results obtained from 17 subjects with a liquid crystal adaptive optics system（LCAOS） validate our method.All of the subjects＇ CLs have public positions from 127 μm to 147 μm from the rod＆cone cell layer,which is influenced by the depth of focus.展开更多
AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited...AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.展开更多
A phase-aware cross-modal framework is presented that synthesizes UWF_FA from non-invasive UWF_RI for diabetic retinopathy(DR)stratification.A curated cohort of 1198 patients(2915 UWF_RI and 17,854 UWF_FA images)with ...A phase-aware cross-modal framework is presented that synthesizes UWF_FA from non-invasive UWF_RI for diabetic retinopathy(DR)stratification.A curated cohort of 1198 patients(2915 UWF_RI and 17,854 UWF_FA images)with strict registration quality supports training across three angiographic phases(initial,mid,final).The generator is based on a modified pix2pixHD with an added Gradient Variance Loss to better preserve microvasculature,and is evaluated using MAE,PSNR,SSIM,and MS-SSIM on held-out pairs.Quantitatively,the mid phase achieves the lowestMAE(98.76±42.67),while SSIM remains high across phases.Expert reviewshows substantial agreement(Cohen's κ=0.78–0.82)and Turing-stylemisclassification of 50%–70%of synthetic images as real,indicating strong perceptual realism.For downstream DR stratification,fusing multi-phase synthetic UWF_FA with UWF_RI in a Swin Transformer classifier yields significant gains over a UWF_RI-only baseline,with the full-phase setting(Set D)reaching AUC=0.910 and accuracy=0.829.These results support synthetic UWF_FA as a scalable,non-invasive complement to dye-based angiography that enhances screening accuracy while avoiding injection-related risks.展开更多
Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-...Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-consuming practice requiring specialized expertise and results may be subjective.To address these challenges,this research proposes a computer-aided diagnosis(CAD)approach using Artificial Intelligence(AI)techniques for binary and multiclass classification of glaucoma stages.An ensemble fusion mechanism that combines the outputs of three pre-trained convolutional neural network(ConvNet)models–ResNet-50,VGG-16,and InceptionV3 is utilized in this paper.This fusion technique enhances diagnostic accuracy and robustness by ensemble-averaging the predictions from individual models,leveraging their complementary strengths.The objective of this work is to assess the model’s capability for early-stage glaucoma diagnosis.Classification is performed on a dataset collected from the Harvard Dataverse repository.With the proposed technique,for Normal vs.Advanced glaucoma classification,a validation accuracy of 98.04%and testing accuracy of 98.03%is achieved,with a specificity of 100%which outperforms stateof-the-art methods.For multiclass classification,the suggested ensemble approach achieved a precision and sensitivity of 97%,specificity,and testing accuracy of 98.57%and 96.82%,respectively.The proposed E-GlauNet model has significant potential in assisting ophthalmologists in the screening and fast diagnosis of glaucoma,leading to more reliable,efficient,and timely diagnosis,particularly for early-stage detection and staging of the disease.While the proposed method demonstrates high accuracy and robustness,the study is limited by the evaluation of a single dataset.Future work will focus on external validation across diverse datasets and enhancing interpretability using explainable AI techniques.展开更多
AIM:To measure the difference of intraoperative central macular thickness(CMT)before,during,and after membrane peeling and investigate the influence of intraoperative macular stretching on postoperative best corrected...AIM:To measure the difference of intraoperative central macular thickness(CMT)before,during,and after membrane peeling and investigate the influence of intraoperative macular stretching on postoperative best corrected visual acuity(BCVA)outcome and postoperative CMT development.METHODS:A total of 59 eyes of 59 patients who underwent vitreoretinal surgery for epiretinal membrane was analyzed.Videos with intraoperative optical coherence tomography(OCT)were recorded.Difference of intraoperative CMT before,during,and after peeling was measured.Pre-and postoperatively obtained BCVA and spectral-domain OCT images were analyzed.RESULTS:Mean age of the patients was 70±8.13y(range 46-86y).Mean baseline BCVA was 0.49±0.27 log MAR(range 0.1-1.3).Three and six months postoperatively the mean BCVA was 0.36±0.25(P=0.01 vs baseline)and 0.38±0.35(P=0.08 vs baseline)log MAR respectively.Mean stretch of the macula during surgery was 29%from baseline(range 2%-159%).Intraoperative findings of macular stretching did not correlate with visual acuity outcome within 6mo after surgery(r=-0.06,P=0.72).However,extent of macular stretching during surgery significantly correlated with less reduction of CMT at the fovea centralis(r=-0.43,P<0.01)and 1 mm nasal and temporal from the fovea(r=-0.37,P=0.02 and r=-0.50,P<0.01 respectively)3mo postoperatively.CONCLUSION:The extent of retinal stretching during membrane peeling may predict the development of postoperative central retinal thickness,though there is no correlation with visual acuity development within the first 6mo postoperatively.展开更多
The parafoveal area,with its high concentration of photoreceptors andfine retinal capillaries,is crucial for central vision and often exhibits early signs of pathological changes.The current adaptive optics scanning l...The parafoveal area,with its high concentration of photoreceptors andfine retinal capillaries,is crucial for central vision and often exhibits early signs of pathological changes.The current adaptive optics scanning laser ophthalmoscope(AOSLO)provides an excellent tool to acquire accurate and detailed information about the parafoveal area with cellular resolution.However,limited by the scanning speed of two-dimensional scanning,thefield of view(FOV)in the AOSLO system was usually less than or equal to 2,and the stitching for the parafoveal area required dozens of images,which was time-consuming and laborious.Unfortunately,almost half of patients are unable to obtain stitched images because of their poorfixation.To solve this problem,we integrate AO technology with the line-scan imaging method to build an adaptive optics line scanning ophthalmoscope(AOLSO)system with a larger FOV.In the AOLSO,afocal spherical mirrors in pairs are nonplanar arranged and the distance and angle between optical elements are optimized to minimize the aberrations,two cylinder lenses are orthogonally placed before the imaging sensor to stretch the point spread function(PSF)for sufficiently digitizing light energy.Captured human retinal images show the whole parafoveal area with 55FOV,60 Hz frame rate and cellular resolutions.Take advantage of the 5FOV of the AOLSO,only 9 frames of the retina are captured with several minutes to stitch a montage image with an FOV of 99,in which photoreceptor counting is performed within approximately 5eccentricity.The AOLSO system not only provides cellular resolution but also has the capability to capture the parafoveal region in a single frame,which offers great potential for noninvasive studying of the parafoveal area.展开更多
Microvasculature of the retina is considered an alternative marker of cerebral vascular risk in healthy populations.However,the ability of retinal vasculature changes,specifically focusing on retinal vessel diameter,t...Microvasculature of the retina is considered an alternative marker of cerebral vascular risk in healthy populations.However,the ability of retinal vasculature changes,specifically focusing on retinal vessel diameter,to predict the recurrence of cerebrovascular events in patients with ischemic stroke has not been determined comprehensively.While previous studies have shown a link between retinal vessel diameter and recurrent cerebrovascular events,they have not incorporated this information into a predictive model.Therefore,this study aimed to investigate the relationship between retinal vessel diameter and subsequent cerebrovascular events in patients with acute ischemic stroke.Additionally,we sought to establish a predictive model by combining retinal veessel diameter with traditional risk factors.We performed a prospective observational study of 141 patients with acute ischemic stroke who were admitted to the First Affiliated Hospital of Jinan University.All of these patients underwent digital retinal imaging within 72 hours of admission and were followed up for 3 years.We found that,after adjusting for related risk factors,patients with acute ischemic stroke with mean arteriolar diameter within 0.5-1.0 disc diameters of the disc margin(MAD_(0.5-1.0DD))of≥74.14μm and mean venular diameter within 0.5-1.0 disc diameters of the disc margin(MVD_(0.5-1.0DD))of≥83.91μm tended to experience recurrent cerebrovascular events.We established three multivariate Cox proportional hazard regression models:model 1 included traditional risk factors,model 2 added MAD_(0.5-1.0DD)to model 1,and model 3 added MVD0.5-1.0DD to model 1.Model 3 had the greatest potential to predict subsequent cerebrovascular events,followed by model 2,and finally model 1.These findings indicate that combining retinal venular or arteriolar diameter with traditional risk factors could improve the prediction of recurrent cerebrovascular events in patients with acute ischemic stroke,and that retinal imaging could be a useful and non-invasive method for identifying high-risk patients who require closer monitoring and more aggressive management.展开更多
AIM： To determine the association between retinal vasculature changes and stroke.METHODS： MEDLINE and EMBASE were searched for relevant human studies to September 2015 that investigated the association between retin...AIM： To determine the association between retinal vasculature changes and stroke.METHODS： MEDLINE and EMBASE were searched for relevant human studies to September 2015 that investigated the association between retinal vasculature changes and the prevalence or incidence of stroke; the studies were independently examined for their qualities. Data on clinical characteristics and calculated summary odds ratios （ORs） were extracted for associations between retinal microvascular abnormalities and stroke, including stroke subtypes where possible, and adjusted for key variables. RESULTS： Nine cases were included in the study comprising 20 659 patients, 1178 of whom were stroke patients. The retinal microvascular morphological markers used were hemorrhage, microaneurysm, vessel caliber, arteriovenous nicking, and fractal dimension. OR of retinal arteriole narrowing and retinal arteriovenous nicking and stroke was 1.42 and 1.91, respectively, indicating that a small-caliber retinal arteriole and retinal arteriovenous nicking were associated with stroke. OR of retinal hemorrhage and retinal microaneurysm and stroke was 3.21 and 3.83, respectively, indicating that retinal microvascular lesions were highly associated with stroke. Results also showed that retinal fractal dimension reduction was associated with stroke （OR： 2.28 for arteriole network, OR： 1.80 for venular network）.CONCLUSION： Retinal vasculature changes have a specific relationship to stroke, which is promising evidence for the prediction of stroke using computerized retinal vessel analysis.展开更多
Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this pap...Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this paper,which takes the advantage of both adversarial learning and recurrent neural network.An iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image gradually.Recurrent unit preserves high-level semantic information for feature reuse,so as to output a sufficiently refined segmentation map instead of a coarse mask.Moreover,an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions,thus greatly reducing topology errors of segmentation.The experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17%and 80.64%,respectively.Our method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.展开更多
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 ...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.展开更多
The discovery of dark noise in retinal photoreceptors resulted in a long-lasting controversy over its origin and the underlying mechanisms.Here,we used a novel ultra-weak biophoton imaging system（UBIS） to detect bio...The discovery of dark noise in retinal photoreceptors resulted in a long-lasting controversy over its origin and the underlying mechanisms.Here,we used a novel ultra-weak biophoton imaging system（UBIS） to detect biophotonic activity（emission） under dark conditions in rat and bullfrog（Rana catesbeiana） retinas in vitro.We found a significant temperature-dependent increase in biophotonic activity that was completely blocked either by removing intracellular and extracellular Ca^（2＋）together or inhibiting phosphodiesterase 6.These findings suggest that the photon-like component of discrete dark noise may not be caused by a direct contribution of the thermal activation of rhodopsin,but rather by an indirect thermal induction of biophotonic activity,which then activates the retinal chromophore of rhodopsin.Therefore,this study suggests a possible solution regarding the thermal activation energy barrier for discrete dark noise,which has been debated for almost half a century.展开更多
The intuitive fuzzy set has found important application in decision-making and machine learning.To enrich and utilize the intuitive fuzzy set,this study designed and developed a deep neural network-based glaucoma eye ...The intuitive fuzzy set has found important application in decision-making and machine learning.To enrich and utilize the intuitive fuzzy set,this study designed and developed a deep neural network-based glaucoma eye detection using fuzzy difference equations in the domain where the retinal images converge.Retinal image detections are categorized as normal eye recognition,suspected glaucomatous eye recognition,and glaucomatous eye recognition.Fuzzy degrees associated with weighted values are calculated to determine the level of concentration between the fuzzy partition and the retinal images.The proposed model was used to diagnose glaucoma using retinal images and involved utilizing the Convolutional Neural Network(CNN)and deep learning to identify the fuzzy weighted regularization between images.This methodology was used to clarify the input images and make them adequate for the process of glaucoma detection.The objective of this study was to propose a novel approach to the early diagnosis of glaucoma using the Fuzzy Expert System(FES)and Fuzzy differential equation(FDE).The intensities of the different regions in the images and their respective peak levels were determined.Once the peak regions were identified,the recurrence relationships among those peaks were then measured.Image partitioning was done due to varying degrees of similar and dissimilar concentrations in the image.Similar and dissimilar concentration levels and spatial frequency generated a threshold image from the combined fuzzy matrix and FDE.This distinguished between a normal and abnormal eye condition,thus detecting patients with glaucomatous eyes.展开更多
In recent years,the three dimensional reconstruction of vascular structures in the field of medical research has been extensively developed.Several studies describe the various numerical methods to numerical modeling ...In recent years,the three dimensional reconstruction of vascular structures in the field of medical research has been extensively developed.Several studies describe the various numerical methods to numerical modeling of vascular structures in near-reality.However,the current approaches remain too expensive in terms of storage capacity.Therefore,it is necessary to find the right balance between the relevance of information and storage space.This article adopts two sets of human retinal blood vessel data in 3D to proceed with data reduction in the first part and then via 3D fractal reconstruction,recreate them in a second part.The results show that the reduction rate obtained is between 66%and 95%as a function of the tolerance rate.Depending on the number of iterations used,the 3D blood vessel model is successful at reconstruction with an average error of 0.19 to 5.73 percent between the original picture and the reconstructed image.展开更多
Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and cla...Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.展开更多
Automated segmentation of blood vessels in retinal fundus images is essential for medical image analysis.The segmentation of retinal vessels is assumed to be essential to the progress of the decision support system fo...Automated segmentation of blood vessels in retinal fundus images is essential for medical image analysis.The segmentation of retinal vessels is assumed to be essential to the progress of the decision support system for initial analysis and treatment of retinal disease.This article develops a new Grasshopper Optimization with Fuzzy Edge Detection based Retinal Blood Vessel Segmentation and Classification(GOFED-RBVSC)model.The proposed GOFED-RBVSC model initially employs contrast enhancement process.Besides,GOAFED approach is employed to detect the edges in the retinal fundus images in which the use of GOA adjusts the membership functions.The ORB(Oriented FAST and Rotated BRIEF)feature extractor is exploited to generate feature vectors.Finally,Improved Conditional Variational Auto Encoder(ICAVE)is utilized for retinal image classification,shows the novelty of the work.The performance validation of the GOFEDRBVSC model is tested using benchmark dataset,and the comparative study highlighted the betterment of the GOFED-RBVSC model over the recent approaches.展开更多
基金Supported by grants from the National Institute for Health Research Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology,Macular Society(UK),Fight for Sight(UK),Onassis Foundation,Leventis Foundation,The Wellcome Trust(099173/Z/12/Z)Moorfields Eye Hospital Special Trustees,Moorfields Eye Charity,Retina UK,and the Foundation Fighting Blindness(USA).
文摘Inherited retinal diseases(IRD)are a leading cause of blindness in the working age population.The advances in ocular genetics,retinal imaging and molecular biology,have conspired to create the ideal environment for establishing treatments for IRD,with the first approved gene therapy and the commencement of multiple therapy trials.The scope of this review is to familiarize clinicians and scientists with the current landscape of retinal imaging in IRD.Herein we present in a comprehensive and concise manner the imaging findings of:(I)macular dystrophies(MD)[Stargardt disease(ABCA4),X-linked retinoschisis(RS1),Best disease(BEST1),pattern dystrophy(PRPH2),Sorsby fundus dystrophy(TIMP3),and autosomal dominant drusen(EFEMP1)],(II)cone and cone-rod dystrophies(GUCA1A,PRPH2,ABCA4 and RPGR),(III)cone dysfunction syndromes[achromatopsia(CNGA3,CNGB3,PDE6C,PDE6H,GNAT2,ATF6],blue-cone monochromatism(OPN1LW/OPN1MW array),oligocone trichromacy,bradyopsia(RGS9/R9AP)and Bornholm eye disease(OPN1LW/OPN1MW),(IV)Leber congenital amaurosis(GUCY2D,CEP290,CRB1,RDH12,RPE65,TULP1,AIPL1 and NMNAT1),(V)rod-cone dystrophies[retinitis pigmentosa,enhanced S-Cone syndrome(NR2E3),Bietti crystalline corneoretinal dystrophy(CYP4V2)],(VI)rod dysfunction syndromes(congenital stationary night blindness,fundus albipunctatus(RDH5),Oguchi disease(SAG,GRK1),and(VII)chorioretinal dystrophies[choroideremia(CHM),gyrate atrophy(OAT)].
基金funded by the Shanghai Municipal Science and Technology Major Project(No.2017SHZDZX01).
文摘Retinal imaging is pivotal in the evaluation of ocular and systemic health,presenting significant promise for extensive popula-tion studies.However,the lack of standardized and automated techniques for extracting Imaging-Derived Phenotypes(IDPs)from retinal images is a major impediment.To counteract this challenge,the Chinese Human Phenome Project(CHPP)has developed a comprehensive protocol that includes Quality Control(QC),preprocessing,and automated or semi-automated extraction of IDPs from fundus photography and Optical Coherence Tomography(OCT)images.This protocol incorporates Artificial Intelligence(AI)-based methods to achieve accurate and efficient IDP extraction,facilitating standardized analysis of large-scale populations.We hope that this Standard Operating Procedure(SOP)guideline will impart valuable insights for ophthalmology-related disciplines and provides support for future research endeavors utilizing retinal imaging data.
基金supported by the National Natural Science Foundation of China(62522119 and 62372358)the Beijing Natural Science Foundation(7242267)+2 种基金the Beijing Scholars Program([2015]160)the Natural Science Basic Research Program of Shaanxi(2023-JC-QN-0719)the Guangdong Basic and Applied Basic Research Foundation(2022A1515110453)。
文摘Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata,and to offer a cost-effective approach for assessing brain health.Methods:Based on clinical information,retinal fundus images,and neuroimaging data derived from a multicenter,population-based cohort study,the Kai Luan Study,we proposed a cross-modal correlation representation(CMCR)network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects.Specifically,individual clinical information,which has been followed up for as long as 12 years,was encoded as a prompt to enhance the accuracy of brain volume estimation.Independent internal validation and external validation were performed to assess the robustness of the proposed model.Root mean square error(RMSE),peak signal-tonoise ratio(PSNR),and structural similarity index measure(SSIM)metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.Results:The proposed framework yielded average RMSE,PSNR,and SSIM values of 98.23,35.78 d B,and 0.64,respectively,which significantly outperformed 5 other methods:multi-channel Variational Autoencoder(mcVAE),Pixelto-Pixel(Pixel2pixel),transformer-based U-Net(Trans UNet),multi-scale transformer network(MT-Net),and residual vision transformer(ResViT).The two-(2D)and three-dimensional(3D)visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images.Thus,the CMCR framework accurately captured the latent structural correlations between the fundus and the brain.The average difference between predicted and actual brain volumes was 61.36 cm~3,with a relative error of 4.54%.When all of the clinical information(including age and sex,daily habits,cardiovascular factors,metabolic factors,and inflammatory factors)was encoded,the difference was decreased to 53.89 cm~3,with a relative error of 3.98%.Based on the synthesized brain magnetic resonance images from retinal fundus images,the volumes of brain tissues could be estimated with high accuracy.Conclusion:This study provides an innovative,accurate,and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.
文摘AIM： To describe retinal findings of various imaging modalities in acute retinal ischemia. METHODS： Fluorescein angiography（FA）, spectral domain optical coherence tomography（SD-OCT）, OCTangiography（OCT-A） and fundus autofluorescence（FAF） images of 13 patients（mean age 64y, range 28-86y） with acute retinal ischemia were evaluated. Six suffered from branch arterial occlusion, 2 had a central retinal artery occlusion, 2 had a combined arteriovenous occlusions, 1 patient had a retrobulbar arterial compression by an orbital haemangioma and 2 patients showed an ocular ischemic syndrome.RESULTS： All patients showed increased reflectivity and thickening of the ischemic retinal tissue. In 10 out of 13 patients SD-OCT revealed an additional highly reflective band located within or above the outer plexiform layer. Morphological characteristics were a decreasing intensity with distance from the fovea, partially segmental occurrence and manifestation limited in time. OCT-A showed a loss of flow signal in the superficial and deep capillary plexus at the affected areas. Reduced flow signal was detected underneath the regions with retinal edema. FAF showed areas of altered signal intensity at the posterior pole. The regions of decreased FAF signal corresponded to peri-venous regions. CONCLUSION： Multimodal imaging modalities in retinal ischemia yield characteristic findings and valuable diagnostic information. Conventional OCT identifies hyperreflectivity and thickening and a mid-retinal hyperreflective band is frequently observed. OCT-A examination reveals demarcation of the ischemic retinal area on the vascular level. FAF shows decreased fluorescence signal in areas of retinal edema often corresponding to peri-venous regions.
基金supported by the National Natural Science Foundation of China(Grant Nos.60736042,1174274,and 1174279)the Plan for Scientific and Technology Development of Suzhou,China(Grant No.ZXS201001)
文摘With the help of adaptive optics （AO） technology, cellular level imaging of living human retina can be achieved. Aiming to reduce distressing feelings and to avoid potential drug induced diseases, we attempted to image retina with dilated pupil and froze accommodation without drugs. An optimized liquid crystal adaptive optics camera was adopted for retinal imaging. A novel eye stared system was used for stimulating accommodation and fixating imaging area. Illumination sources and imaging camera kept linkage for focusing and imaging different layers. Four subjects with diverse degree of myopia were imaged. Based on the optical properties of the human eye, the eye stared system reduced the defocus to less than the typical ocular depth of focus. In this way, the illumination light can be projected on certain retina layer precisely. Since that the defocus had been compensated by the eye stared system, the adopted 512 × 512 liquid crystal spatial light modulator （LC-SLM） corrector provided the crucial spatial fidelity to fully compensate high-order aberrations. The Strehl ratio of a subject with -8 diopter myopia was improved to 0.78, which was nearly close to diffraction-limited imaging. By finely adjusting the axial displacement of illumination sources and imaging camera, cone photoreceptors, blood vessels and nerve fiber layer were clearly imaged successfully.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11174274,11174279,61205021,11204299,61475152,and 61405194)
文摘Even in the early stage,endocrine metabolism disease may lead to micro aneurysms in retinal capillaries whose diameters are less than 10 μm.However,the fundus cameras used in clinic diagnosis can only obtain images of vessels larger than 20 μm in diameter.The human retina is a thin and multiple layer tissue,and the layer of capillaries less than10 μm in diameter only exists in the inner nuclear layer.The layer thickness of capillaries less than 10 μm in diameter is about 40 μm and the distance range to rod＆cone cell surface is tens of micrometers,which varies from person to person.Therefore,determining reasonable capillary layer（CL） position in different human eyes is very difficult.In this paper,we propose a method to determine the position of retinal CL based on the rod＆cone cell layer.The public positions of CL are recognized with 15 subjects from 40 to 59 years old,and the imaging planes of CL are calculated by the effective focal length of the human eye.High resolution retinal capillary imaging results obtained from 17 subjects with a liquid crystal adaptive optics system（LCAOS） validate our method.All of the subjects＇ CLs have public positions from 127 μm to 147 μm from the rod＆cone cell layer,which is influenced by the depth of focus.
文摘AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.
基金funded by theDeanship of Research andGraduate Studies at King Khalid University through Large Research Project under grant number RGP2/417/46.
文摘A phase-aware cross-modal framework is presented that synthesizes UWF_FA from non-invasive UWF_RI for diabetic retinopathy(DR)stratification.A curated cohort of 1198 patients(2915 UWF_RI and 17,854 UWF_FA images)with strict registration quality supports training across three angiographic phases(initial,mid,final).The generator is based on a modified pix2pixHD with an added Gradient Variance Loss to better preserve microvasculature,and is evaluated using MAE,PSNR,SSIM,and MS-SSIM on held-out pairs.Quantitatively,the mid phase achieves the lowestMAE(98.76±42.67),while SSIM remains high across phases.Expert reviewshows substantial agreement(Cohen's κ=0.78–0.82)and Turing-stylemisclassification of 50%–70%of synthetic images as real,indicating strong perceptual realism.For downstream DR stratification,fusing multi-phase synthetic UWF_FA with UWF_RI in a Swin Transformer classifier yields significant gains over a UWF_RI-only baseline,with the full-phase setting(Set D)reaching AUC=0.910 and accuracy=0.829.These results support synthetic UWF_FA as a scalable,non-invasive complement to dye-based angiography that enhances screening accuracy while avoiding injection-related risks.
基金funded by Department of Robotics and Mechatronics Engineering,Kennesaw State University,Marietta,GA 30060,USA.
文摘Glaucoma,a chronic eye disease affecting millions worldwide,poses a substantial threat to eyesight and can result in permanent vision loss if left untreated.Manual identification of glaucoma is a complicated and time-consuming practice requiring specialized expertise and results may be subjective.To address these challenges,this research proposes a computer-aided diagnosis(CAD)approach using Artificial Intelligence(AI)techniques for binary and multiclass classification of glaucoma stages.An ensemble fusion mechanism that combines the outputs of three pre-trained convolutional neural network(ConvNet)models–ResNet-50,VGG-16,and InceptionV3 is utilized in this paper.This fusion technique enhances diagnostic accuracy and robustness by ensemble-averaging the predictions from individual models,leveraging their complementary strengths.The objective of this work is to assess the model’s capability for early-stage glaucoma diagnosis.Classification is performed on a dataset collected from the Harvard Dataverse repository.With the proposed technique,for Normal vs.Advanced glaucoma classification,a validation accuracy of 98.04%and testing accuracy of 98.03%is achieved,with a specificity of 100%which outperforms stateof-the-art methods.For multiclass classification,the suggested ensemble approach achieved a precision and sensitivity of 97%,specificity,and testing accuracy of 98.57%and 96.82%,respectively.The proposed E-GlauNet model has significant potential in assisting ophthalmologists in the screening and fast diagnosis of glaucoma,leading to more reliable,efficient,and timely diagnosis,particularly for early-stage detection and staging of the disease.While the proposed method demonstrates high accuracy and robustness,the study is limited by the evaluation of a single dataset.Future work will focus on external validation across diverse datasets and enhancing interpretability using explainable AI techniques.
文摘AIM:To measure the difference of intraoperative central macular thickness(CMT)before,during,and after membrane peeling and investigate the influence of intraoperative macular stretching on postoperative best corrected visual acuity(BCVA)outcome and postoperative CMT development.METHODS:A total of 59 eyes of 59 patients who underwent vitreoretinal surgery for epiretinal membrane was analyzed.Videos with intraoperative optical coherence tomography(OCT)were recorded.Difference of intraoperative CMT before,during,and after peeling was measured.Pre-and postoperatively obtained BCVA and spectral-domain OCT images were analyzed.RESULTS:Mean age of the patients was 70±8.13y(range 46-86y).Mean baseline BCVA was 0.49±0.27 log MAR(range 0.1-1.3).Three and six months postoperatively the mean BCVA was 0.36±0.25(P=0.01 vs baseline)and 0.38±0.35(P=0.08 vs baseline)log MAR respectively.Mean stretch of the macula during surgery was 29%from baseline(range 2%-159%).Intraoperative findings of macular stretching did not correlate with visual acuity outcome within 6mo after surgery(r=-0.06,P=0.72).However,extent of macular stretching during surgery significantly correlated with less reduction of CMT at the fovea centralis(r=-0.43,P<0.01)and 1 mm nasal and temporal from the fovea(r=-0.37,P=0.02 and r=-0.50,P<0.01 respectively)3mo postoperatively.CONCLUSION:The extent of retinal stretching during membrane peeling may predict the development of postoperative central retinal thickness,though there is no correlation with visual acuity development within the first 6mo postoperatively.
基金supported by the National Natural Science Foundation of China under Grant No.62075235,National Key R&D Program of China under Grant No.2021YFF0700700Gusu Innovation and Entrepreneurship Leading Talents in Suzhou City under Grant No.ZXL2021425+1 种基金Youth Innovation Promotion Association of the Chinese Academy of Sciences under Grant No.2019320Innovation of Scientific Research Strategic Priority Research Program of the Chinese Academy of Sciences under Grant No.XDA15021304.
文摘The parafoveal area,with its high concentration of photoreceptors andfine retinal capillaries,is crucial for central vision and often exhibits early signs of pathological changes.The current adaptive optics scanning laser ophthalmoscope(AOSLO)provides an excellent tool to acquire accurate and detailed information about the parafoveal area with cellular resolution.However,limited by the scanning speed of two-dimensional scanning,thefield of view(FOV)in the AOSLO system was usually less than or equal to 2,and the stitching for the parafoveal area required dozens of images,which was time-consuming and laborious.Unfortunately,almost half of patients are unable to obtain stitched images because of their poorfixation.To solve this problem,we integrate AO technology with the line-scan imaging method to build an adaptive optics line scanning ophthalmoscope(AOLSO)system with a larger FOV.In the AOLSO,afocal spherical mirrors in pairs are nonplanar arranged and the distance and angle between optical elements are optimized to minimize the aberrations,two cylinder lenses are orthogonally placed before the imaging sensor to stretch the point spread function(PSF)for sufficiently digitizing light energy.Captured human retinal images show the whole parafoveal area with 55FOV,60 Hz frame rate and cellular resolutions.Take advantage of the 5FOV of the AOLSO,only 9 frames of the retina are captured with several minutes to stitch a montage image with an FOV of 99,in which photoreceptor counting is performed within approximately 5eccentricity.The AOLSO system not only provides cellular resolution but also has the capability to capture the parafoveal region in a single frame,which offers great potential for noninvasive studying of the parafoveal area.
基金supported by the Youth Fund of Fundamental Research Fund for the Central Universities of Jinan University,No.11622303(to YZ).
文摘Microvasculature of the retina is considered an alternative marker of cerebral vascular risk in healthy populations.However,the ability of retinal vasculature changes,specifically focusing on retinal vessel diameter,to predict the recurrence of cerebrovascular events in patients with ischemic stroke has not been determined comprehensively.While previous studies have shown a link between retinal vessel diameter and recurrent cerebrovascular events,they have not incorporated this information into a predictive model.Therefore,this study aimed to investigate the relationship between retinal vessel diameter and subsequent cerebrovascular events in patients with acute ischemic stroke.Additionally,we sought to establish a predictive model by combining retinal veessel diameter with traditional risk factors.We performed a prospective observational study of 141 patients with acute ischemic stroke who were admitted to the First Affiliated Hospital of Jinan University.All of these patients underwent digital retinal imaging within 72 hours of admission and were followed up for 3 years.We found that,after adjusting for related risk factors,patients with acute ischemic stroke with mean arteriolar diameter within 0.5-1.0 disc diameters of the disc margin(MAD_(0.5-1.0DD))of≥74.14μm and mean venular diameter within 0.5-1.0 disc diameters of the disc margin(MVD_(0.5-1.0DD))of≥83.91μm tended to experience recurrent cerebrovascular events.We established three multivariate Cox proportional hazard regression models:model 1 included traditional risk factors,model 2 added MAD_(0.5-1.0DD)to model 1,and model 3 added MVD0.5-1.0DD to model 1.Model 3 had the greatest potential to predict subsequent cerebrovascular events,followed by model 2,and finally model 1.These findings indicate that combining retinal venular or arteriolar diameter with traditional risk factors could improve the prediction of recurrent cerebrovascular events in patients with acute ischemic stroke,and that retinal imaging could be a useful and non-invasive method for identifying high-risk patients who require closer monitoring and more aggressive management.
基金Supported by the National Natural Science Foundation of China(No.81501559No.81271668)+4 种基金Natural Science Foundation of the Higher Education Institutions of Jiangsu Province(No.15KJB310015)Pre-research project for Natural Science Foundation of Nantong University(No.14ZY021)Science and Technology Project of Nantong City(No.MS12015105)Graduate Research and Innovation Plan Project of Nantong University(No.YKC14048No.YKC15056)
文摘AIM： To determine the association between retinal vasculature changes and stroke.METHODS： MEDLINE and EMBASE were searched for relevant human studies to September 2015 that investigated the association between retinal vasculature changes and the prevalence or incidence of stroke; the studies were independently examined for their qualities. Data on clinical characteristics and calculated summary odds ratios （ORs） were extracted for associations between retinal microvascular abnormalities and stroke, including stroke subtypes where possible, and adjusted for key variables. RESULTS： Nine cases were included in the study comprising 20 659 patients, 1178 of whom were stroke patients. The retinal microvascular morphological markers used were hemorrhage, microaneurysm, vessel caliber, arteriovenous nicking, and fractal dimension. OR of retinal arteriole narrowing and retinal arteriovenous nicking and stroke was 1.42 and 1.91, respectively, indicating that a small-caliber retinal arteriole and retinal arteriovenous nicking were associated with stroke. OR of retinal hemorrhage and retinal microaneurysm and stroke was 3.21 and 3.83, respectively, indicating that retinal microvascular lesions were highly associated with stroke. Results also showed that retinal fractal dimension reduction was associated with stroke （OR： 2.28 for arteriole network, OR： 1.80 for venular network）.CONCLUSION： Retinal vasculature changes have a specific relationship to stroke, which is promising evidence for the prediction of stroke using computerized retinal vessel analysis.
文摘Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image contrast.To address these issues,we introduce a novel convolutional neural network in this paper,which takes the advantage of both adversarial learning and recurrent neural network.An iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image gradually.Recurrent unit preserves high-level semantic information for feature reuse,so as to output a sufficiently refined segmentation map instead of a coarse mask.Moreover,an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions,thus greatly reducing topology errors of segmentation.The experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17%and 80.64%,respectively.Our method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.
基金the Program"Partnerships in priority domains"with the support of the National Education Ministry,the Executive Agency for Higher Education,Research,Development and Innovation Funding (UEFISCDI),Romania (Project code:PN-II-PT-PCCA-2013-4-1232)
文摘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.
基金supported by the National Natural Science Foundation of China (31070961)the Sci-Tech Support Plan of Hubei Province,China (2014BEC086)the Research Team Fund of South Central University for Nationalities,China (XTZ15014)
文摘The discovery of dark noise in retinal photoreceptors resulted in a long-lasting controversy over its origin and the underlying mechanisms.Here,we used a novel ultra-weak biophoton imaging system（UBIS） to detect biophotonic activity（emission） under dark conditions in rat and bullfrog（Rana catesbeiana） retinas in vitro.We found a significant temperature-dependent increase in biophotonic activity that was completely blocked either by removing intracellular and extracellular Ca^（2＋）together or inhibiting phosphodiesterase 6.These findings suggest that the photon-like component of discrete dark noise may not be caused by a direct contribution of the thermal activation of rhodopsin,but rather by an indirect thermal induction of biophotonic activity,which then activates the retinal chromophore of rhodopsin.Therefore,this study suggests a possible solution regarding the thermal activation energy barrier for discrete dark noise,which has been debated for almost half a century.
基金funding the publication of this research through the Researchers Supporting Program (RSPD2023R809),King Saud University,Riyadh,Saudi Arabia.
文摘The intuitive fuzzy set has found important application in decision-making and machine learning.To enrich and utilize the intuitive fuzzy set,this study designed and developed a deep neural network-based glaucoma eye detection using fuzzy difference equations in the domain where the retinal images converge.Retinal image detections are categorized as normal eye recognition,suspected glaucomatous eye recognition,and glaucomatous eye recognition.Fuzzy degrees associated with weighted values are calculated to determine the level of concentration between the fuzzy partition and the retinal images.The proposed model was used to diagnose glaucoma using retinal images and involved utilizing the Convolutional Neural Network(CNN)and deep learning to identify the fuzzy weighted regularization between images.This methodology was used to clarify the input images and make them adequate for the process of glaucoma detection.The objective of this study was to propose a novel approach to the early diagnosis of glaucoma using the Fuzzy Expert System(FES)and Fuzzy differential equation(FDE).The intensities of the different regions in the images and their respective peak levels were determined.Once the peak regions were identified,the recurrence relationships among those peaks were then measured.Image partitioning was done due to varying degrees of similar and dissimilar concentrations in the image.Similar and dissimilar concentration levels and spatial frequency generated a threshold image from the combined fuzzy matrix and FDE.This distinguished between a normal and abnormal eye condition,thus detecting patients with glaucomatous eyes.
文摘In recent years,the three dimensional reconstruction of vascular structures in the field of medical research has been extensively developed.Several studies describe the various numerical methods to numerical modeling of vascular structures in near-reality.However,the current approaches remain too expensive in terms of storage capacity.Therefore,it is necessary to find the right balance between the relevance of information and storage space.This article adopts two sets of human retinal blood vessel data in 3D to proceed with data reduction in the first part and then via 3D fractal reconstruction,recreate them in a second part.The results show that the reduction rate obtained is between 66%and 95%as a function of the tolerance rate.Depending on the number of iterations used,the 3D blood vessel model is successful at reconstruction with an average error of 0.19 to 5.73 percent between the original picture and the reconstructed image.
文摘Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.
文摘Automated segmentation of blood vessels in retinal fundus images is essential for medical image analysis.The segmentation of retinal vessels is assumed to be essential to the progress of the decision support system for initial analysis and treatment of retinal disease.This article develops a new Grasshopper Optimization with Fuzzy Edge Detection based Retinal Blood Vessel Segmentation and Classification(GOFED-RBVSC)model.The proposed GOFED-RBVSC model initially employs contrast enhancement process.Besides,GOAFED approach is employed to detect the edges in the retinal fundus images in which the use of GOA adjusts the membership functions.The ORB(Oriented FAST and Rotated BRIEF)feature extractor is exploited to generate feature vectors.Finally,Improved Conditional Variational Auto Encoder(ICAVE)is utilized for retinal image classification,shows the novelty of the work.The performance validation of the GOFEDRBVSC model is tested using benchmark dataset,and the comparative study highlighted the betterment of the GOFED-RBVSC model over the recent approaches.
