Search

Objective·To explore the predictive capability of retinal vascular features in preeclampsia (PE) based on artificial intelligence (AI) models.Methods·This retrospective study enrolled 789 pregnant women who registered from June 2020 to January 2021 at Shanghai First Maternity and Infant Hospital of Tongji University in the first 16 weeks of gestation. These women underwent regular prenatal examinations, had retinal fundus images captured, and delivered singleton live births at the hospital. According to whether they developed hypertensive disorders of pregnancy (HDP), they were divided into unaffected group (n=685) and HDP group (n=104). Within the HDP group, pregnancies were further categorized into gestational hypertension (GH) group (n=36) and PE group (n=68) based on the occurrence of PE. Based on the gestational age at onset, the PE group was further divided into early-onset PE group (gestational age

Purpose: Thyroid-associated ophthalmopathy (TAO) may result in increased metabolism and abnormalities in microcirculation. The fractal dimension (Df) of retinal vessels has been shown to be related to the pathology of a number of ophthalmic disorders, but it hasn't been investigated in TAO. Methods: We analyzed 1078 participants aged 18 to 72 (548 healthy volunteers and 530 TAO). Images were captured using a non-mydriatic 45-degree fundus camera. Baseline retinal characteristics, such as vessel width, tortuosity, and Df were measured using semiautomated software from fundus images. The average retinal parameters were compared between the two groups. The receiver operation curve (ROC) was used to assess the diagnostic efficacy of various retinal vascular parameters for TAO. Results: Despite controlling for potential confounding variables, Df, vessel width, and tortuosity significantly increased in TAO compared to healthy volunteers. Compared to active TAO, patients in the inactive phase had a larger retinal venous caliber (p < 0.05), but there was no difference in Df or arterial caliber. Moderate and severe cases had a higher Df compared with mild cases (EUGOGO guidelines). The area under the ROC for Df, tortuosity, and vascular caliber in the diagnosis of TAO was 0.904 (95% CI: 0.884–0.924), 0.638 (95% CI: 0.598–0.679), and 0.617 (95% CI: 0.576–0.658), respectively. Conclusions: Due to its accessibility, affordability, and non-invasive nature, retinal vascular Df may serve as a surrogate marker for TAO and might be used to identify severe cases. With relatively high diagnostic performance, the Df is of some utility for the detection of TAO. [ABSTRACT FROM AUTHOR]

Objective·To explore the predictive capability of retinal vascular features in preeclampsia (PE) based on artificial intelligence (AI) models. Methods·This retrospective study enrolled 789 pregnant women who registered from June 2020 to January 2021 at Shanghai First Maternity and Infant Hospital of Tongji University in the first 16 weeks of gestation. These women underwent regular prenatal examinations, had retinal fundus images captured, and delivered singleton live births at the hospital. According to whether they developed hypertensive disorders of pregnancy (HDP), they were divided into unaffected group (n=685) and HDP group (n=104). Within the HDP group, pregnancies were further categorized into gestational hypertension (GH) group (n=36) and PE group (n=68) based on the occurrence of PE. Based on the gestational age at onset, the PE group was further divided into early-onset PE group (gestational age<34 weeks) and late-onset PE group (gestational age≥34 weeks). Fundus images of the pregnant women were obtained, and an AI algorithm was utilized to diagnose retinal lesions and quantify retinal vascular features. Comparative analyses were conducted on fundus features and retinal vascular features. Univariate Logistic regression model was employed to analyze the influencing factors of PE occurrence, and multivariate Logistic regression model was further utilized to assess the correlation between retinal vascular features and the occurrence of PE. The predictive capability of retinal vascular features for PE (both early- and late-onset PE) was analyzed by using area under the curve (AUC) of receiver operator characteristic curve (ROC curve). Results·The comparative analysis of fundus features and retinal vascular features demonstrated statistically significant differences between the unaffected group and PE group in terms of central retinal artery equivalent (CRAE), central retinal vein equivalent (CRVE), arteriole-to-venular ratio (AVR), retinal artery tortuosity and retinal artery fractal dimension (all P< 0.05). Univariate Logistic regression analysis indicated that second-trimester mean arterial pressure (MAP), second-trimester estimated fetal weight (EFW), CRAE, CRVE, AVR, retinal artery tortuosity and retinal artery fractal dimension were the influencing factors for PE occurrence (all P<0.05). Multivariate Logistic regression analysis revealed that second-trimester EFW, CRAE, CRVE, AVR, retinal artery tortuosity and retinal artery fractal dimension were the protective factors for the occurrence of PE, while secondtrimester MAP was the risk factor for PE (all P<0.05). The analysis of ROC curves revealed that maternal risk factors along with second-trimester prenatal examination data (including MAP and EFW) and retinal vascular features model had good predictive ability for PE [AUC (95% CI)=0.784 (0.725－0.843), and this model exhibited better predictive capability for early-onset PE, with an AUC (95% CI) of 0.840 (0.756－0.924). Conclusion·The integration of quantified retinal vascular features based on AI models with maternal risk factors and second-trimester prenatal examination data (including MAP and EFW) enables a more effective prediction of PE occurrence, particularly early-onset PE. [ABSTRACT FROM AUTHOR]

Abnormal changes in the retinal vessel width usually indicate the presence of certain diseases. This paper presents a novel model to measure the width of retinal vessels. This method firstly employs cubic spline fitting to determine the vessel cross‐sectional direction at the center point of a vessel profile, then uses the extended edge‐searching mode to detect vessel edge points along the vessel cross‐sectional direction, and finally obtains the width value by calculating the distance between the edge point and the center point. The method can accurately locate vessel edge points and successfully solve the problem of central light reflex in blood vessels. Experimental analyses on a publicly available database show that the proposed approach has excellent performance in accuracy with other existing measurement techniques. It provides an effective idea for analyzing morphological changes in blood vessels and can be extended to obtain the shape features of other objects. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hyperglycemia in early postnatal life of preterm infants with incompletely vascularized retinas is associated with increased risk of potentially blinding neovascular retinopathy of prematurity (ROP). Neovascular ROP (Phase II ROP) is a compensatory but ultimately pathological response to the suppression of physiological postnatal retinal vascular development (Phase I ROP). Hyperglycemia in neonatal mice which suppresses physiological retinal vascular growth is associated with decreased expression of systemic and retinal fibroblast growth factor 21 (FGF21). FGF21 administration promoted and FGF21 deficiency suppressed the physiological retinal vessel growth. FGF21 increased serum adiponectin (APN) levels and loss of APN abolished FGF21 promotion of physiological retinal vascular development. Blocking mitochondrial fatty acid oxidation also abolished FGF21 protection against delayed physiological retinal vessel growth. Clinically, preterm infants developing severe neovascular ROP (versus non-severe ROP) had a lower total lipid intake with more parenteral and less enteral during the first 4 weeks of life. Our data suggest that increasing FGF21 levels in the presence of adequate enteral lipids may help prevent Phase I retinopathy (and therefore prevent neovascular disease). [ABSTRACT FROM AUTHOR]

The state of retinal vessels in fundus images is a reliable biomarker for many diseases, and the accurate segmentation of retinal vessels is important for the diagnosis of related diseases. To address the problem of many layers and high complexity of deep learningbased vascular segmentation network, this paper proposes a lightweight encoderdecoder network NAUNet by reasonably reducing the number of network layers. By introducing the DropBlock regularization strategy, the local semantic information can be discarded more effectively to motivate the network to learn more robust and effective features. Efficient attention module uses appropriate crosschannel interaction to capture richer global information. In the skip connection part, the nested connection strategy is adopted to effectively fuse the feature maps gathered from the intermediate decoder and the original feature maps from the encoder, which makes up for the semantic gap caused by direct simple connection. In addition, data augmentation is performed on the original image to improve the robustness and prevent the overfitting problem caused by insufficient data. A mixed loss function is proposed to solve the problem of class imbalance in vascular images. Finally, NAUNet was tested and achieved F1 scores of 80.92%/81.25%/74.86% and AUC values of 0.9831/0.9849/0.9841 on the DRIVE, STARE and CHASE_DB1 datasets, respectively.The number of parameters for the proposed method was only 2.66 M. [ABSTRACT FROM AUTHOR]

The morphological characteristics of retinal vessels in the fundus serve as the primary basis for diagnosing and assessing the risk of ophthalmic diseases. An effective segmentation scheme for retinal vessels can aid in the early diagnosis and treatment of these diseases, as well as help prevent their progression. However, accurate vessel segmentation is challenging due to the low contrast of fundus images and the complexity of the vessels’ morphological structure. To address the low sensitivity and poor generalization ability of the existing methods in vascular extraction, a Dual-decoder Network based on Attention-enhancing and multi-scale Feature Fusion (AFFD-Net) is proposed. AFFD-Net inherits the codec concept of U-Net. To improve the performance of our U-Net model, we made two modifications. Firstly, we reduced the number of convolution kernel filters in each layer, thereby significantly reducing the number of training parameters. This helps to avoid overfitting and improves the model’s ability to generalize. Secondly, we added a Multi-scale Feature Extraction (MFE) module and an M/A intermediate decoder to enhance the model’s sensitivity. MFE is designed as the first encoding unit of AFFD-Net to obtain rich vascular features in the complex anatomical background and adapt to the large-scale variations of vessels. The M/A intermediate decoder is composed of the Multi-scale Feature Fusion (MFF) module and the Attention-enhancing Hybrid Feature Fusion (AHFF) module. The MFF module integrates deep semantic information and shallow spatial information to ensure that the features at each scale in the middle layer are fully utilized. The AHFF module adaptively fuses the hybrid features at different scales to generate two feature descriptors with different focuses which can improve the expressiveness of the model. AFFD-Net is evaluated on three public databases including DRIVE, STARE, and CHASE_DB1, and the sensitivity values obtained are 84.19%, 84.58%, and 82.62%, respectively. It has higher sensitivity and better generalization ability than other state-of-the-art methods. Compared with classical networks including U-Net, U-Net++, and U-Net3+, AFFD-Net has fewer parameters and higher segmentation accuracy. Our proposed segmentation model exhibits superior performance across a range of metrics, indicating its promising potential for practical applications.

The presence of high blood sugar levels damages blood vessels and causes an eye condition called diabetic retinopathy. The ophthalmologist can detect this disease by looking at the variations in retinal blood vasculature. Manual segmentation of vessels requires highly skilled specialists, and not possible for many patients to be done quickly in their daily routine. For these reasons, it is of great importance to isolate retinal vessels precisely, quickly, and accurately. The difficulty distinguishing the retinal vessels from the background, and the small number of samples in the databases make this segmentation problem difficult. In this study, we propose a novel network called Block Feature Map Distorted Switchable Normalization U-net with Global Context Informative Convolutional Block Attention Module (BFMD SN U-net with GCI- CBAM). We improve the traditional Fully Convolutional Segmentation Networks in multiple aspects with the proposed model as follows; The model converges in earlier epochs, adapts more flexibly to different data, is more robust against overfitting, and gets better feature refinement at different dilation rates to cope with different sizes of retinal vessels. We evaluate the proposed network on two reference retinal datasets, DRIVE and CHASE DB1, and achieve state-of-the-art performances with 97.00 % accuracy and 98.71 % AUC in DRIVE and 97.62 % accuracy and 99.11 % AUC on CHASE DB1 databases. Additionally, the convergence step of the model is reduced and it has fewer parameters than the baseline U-net. In summary, the proposed model surpasses the U-net -based approaches used for retinal vessel separation in the literature.

Retinal images have been proven significant in diagnosing multiple diseases such as diabetes, glaucoma, and hypertension. Retinal vessel segmentation is crucial for the quantitative analysis of retinal images. However, current methods mainly concentrate on the segmentation performance of overall retinal vessel structures. The small vessels do not receive enough attention due to their small percentage in the full retinal images. Small retinal vessels are much more sensitive to the blood circulation system and have great significance in the early diagnosis and warning of various diseases. This paper combined two unsupervised methods, local phase congruency (LPC) and orientation scores (OS), with a deep learning network based on the U-Net as attention. And we proposed the U-Net using local phase congruency and orientation scores (UN-LPCOS), which showed a remarkable ability to identify and segment small retinal vessels. A new metric called sensitivity on a small ship (Sesv) was also proposed to evaluate the methods’ performance on the small vessel segmentation. Our strategy was validated on both the DRIVE dataset and the data from Maastricht Study and achieved outstanding segmentation performance on both the overall vessel structure and small vessels.

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The retina is one of the most metabolically active tissues in the human body. The retinal vessels provide blood to the inner retinal neurons. The retinal blood vessels are affected by diseases such as Hypertensive retinopathy and Diabetic retinopathy. The early diagnosis prevents the patients from blindness and fatality in some cases. Thus, examining the retinal blood vessels becomes an important work of an ophthalmologist. Thus, automated retinal blood vessel segmentation aids the ophthalmologist and makes their work easier. In this paper, a supervised Convolutional Neural Network (CNN) is suggested that enhances the performance of retinal blood vessel segmentation. Three publicly available datasets are used: STARE, DRIVE, and CHASE_DB1. A novel model, 'Staircase-Net,' is proposed, which has a series of up-sampling and down-sampling processes for feature extraction (extracting the thick and thin blood vessel features, respectively). The images in the datasets undergo a series of transformations in the preprocessing steps. The evaluation metrics considered are specificity, accuracy, sensitivity, and area under the curve. Finally, the proposed model results are compared with the state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

It has been proven that the deformability of red blood cells (RBC) is reduced owing to changes in mechanical properties, such as diabetes mellitus and hypertension. To probe the effects of RBC morphological and physical parameters on the flow field in bifurcated arterioles, three types of RBC models with various degrees of biconcave shapes were built based on the in vitro experimental data. The dynamic behaviors of the RBCs in shear flow were simulated to validate the feasibility of the finite element-Arbitrary Lagrangian–Eulerian method with a moving mesh. The influences of the shear rate and viscosity ratios on RBC motions were investigated. The motion of RBCs in arteriolar bifurcations was further simulated. Abnormal variations in the morphological and physical parameters of RBCs may lead to diminished tank-tread motion and enhanced tumbling motion in shear flow. Moreover, abnormal RBC variations can result in slower RBC motion at the bifurcation with a longer transmit time and greater flow resistance, which may further cause inadequate local oxygen supply. These findings would provide useful insights into the microvascular complications in diabetes mellitus. [ABSTRACT FROM AUTHOR]

Giant cell arteritis (GCA) is a potential sight-threatening disease. Although it is associated with polymyalgia rheumatica (PMR), visual loss is not common in PMR. A retinal oximeter can be used to conduct a direct, non-invasive, in vivo assessment of the vascular system. In a cross-sectional study, we measured the retinal oxygen saturation and retinal vessel calibers in GCA patients, PMR patients, and control participants. Twenty GCA patients (38 eyes), 19 PMR patients (33 eyes), and 12 controls (20 eyes) were investigated. Images were analyzed using Oxymap Analyzer software 2.5.0 (Oxymap ehf., Reykjavik, Iceland). Groups were compared using an age- and sex-adjusted linear mixed model regression. The median (IQR) age for GCA patients was 69.0 (66.5–76.5) years, for PMR 69.0 (67.0–72.0) years, and for the controls 75.5 (71.5–81.0) years, respectively. As compared to the controls (115.3 µm), the retinal arterioles were significantly wider in patients with GCA (124.4 µm; p = 0.023) and PMR (124.8 µm; p = 0.049). No difference was found in the retinal venular caliber or vascular oxygen saturation. These results indicate that GCA and PMR patients differ similarly in the retinal arteriolar diameter compared to controls. Further studies are needed in order to clarify the underlying inflammatory mechanisms in retinal arteriolar vessels and if these parameters can be used to predict clinical outcomes. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the short-term effects of half-fluence photodynamic therapy (PDT) on retinal and choroidal vascular parameters obtained by optical coherence tomography angiography. Materials and Methods: Fifteen patients who underwent half-fluence PDT for chronic central serous chorioretinopathy between 20182020 were included in the study retrospectively. Patients underwent optic coherence tomography angiography imaging before and after PDT. Foveal avascular zone (FAZ) area, FAZ perimeter, acircularity index, foveal vascular density 300 microns around FAZ, outer retina flow, choriocapillaris flow and the whole area, foveal, parafoveal and perifoveal vessel densities of superficial and deep capillary networks were compared before and after treatment. Results: The vessel density of the superficial foveal capillary plexus was significantly decreased after PDT (p=0.044). However whole area, parafoveal and perifoveal vessel densities of superficial capillary plexus were not significantly different. The vessel density of the deep parafoveal capillary plexus was significantly increased after PDT (p=0.027). The whole area, foveal and perifoveal vessel densities of deep capillary plexus were not significantly different before and after PDT (p>0.05). Foveal avascular zone (FAZ) area, FAZ perimeter, acircularity index, outer retina flow and choriocapillaris flow did not change after photodynamic therapy in short term. Conclusion: This study showed that vessel density of superficial foveal capillary plexus was decreased and vessel density of deep parafoveal capillary plexus was increased in short term after half fluence PDT. However, the foveal avascular zone area, ourter retinal and choroidal flow, choroidal signal voids and vascular densities of other remaining macular vascular areas were not changed. [ABSTRACT FROM AUTHOR]

• We propose a novel medical image segmentation framework based on deep learning. • This work learns multi-scale contextual dependencies from two dimensions. • Our framework significantly reduces the missed diagnosis rate compared to others. • This work successfully avoids feature disappearance of small ROIs in deep layers. • Visualization comparisons of learned features boost networks' interpretability. • This work conducts comprehensive experiments on three real-world medical datasets. Automatic medical image segmentation plays an important role as a diagnostic aid in the identification of diseases and their treatment in clinical settings. Recently proposed methods based on Convolutional Neural Networks (CNNs) have demonstrated their potential in image processing tasks, including some medical image analysis tasks. Those methods can learn various feature representations with numerous weight-shared convolutional kernels, however, the missed diagnosis rate of regions of interest (ROIs) is still high in medical image segmentation. Two crucial factors behind this shortcoming, which have been overlooked, are small ROIs from medical images and the limited context information from the existing network models. In order to reduce the missed diagnosis rate of ROIs from medical images, we propose a new segmentation framework which enhances the representative capability of small ROIs (particularly in deep layers) and explicitly learns global contextual dependencies in multi-scale feature spaces. In particular, the local features and their global dependencies from each feature space are adaptively aggregated based on both the spatial and the channel dimensions. Moreover, some visualization comparisons of the learned features from our framework further boost neural networks' interpretability. Experimental results show that, in comparison to some popular medical image segmentation and general image segmentation methods, our proposed framework achieves the state-of-the-art performance on the liver tumor segmentation task with 91.18% Sensitivity, the COVID-19 lung infection segmentation task with 75.73% Sensitivity and the retinal vessel detection task with 82.68% Sensitivity. Moreover, it is possible to integrate (parts of) the proposed framework into most of the recently proposed Fully CNN-based models, in order to improve their effectiveness in medical image segmentation tasks. [ABSTRACT FROM AUTHOR]

There is a gap in understanding the effect of the essential ω-3 and ω-6 long-chain polyunsaturated fatty acids (LCPUFA) on Phase I retinopathy of prematurity (ROP), which precipitates proliferative ROP. Postnatal hyperglycemia contributes to Phase I ROP by delaying retinal vascularization. In mouse neonates with hyperglycemia-associated Phase I retinopathy, dietary ω-3 (vs. ω-6 LCPUFA) supplementation promoted retinal vessel development. However, ω-6 (vs. ω-3 LCPUFA) was also developmentally essential, promoting neuronal growth and metabolism as suggested by a strong metabolic shift in almost all types of retinal neuronal and glial cells identified with single-cell transcriptomics. Loss of adiponectin (APN) in mice (mimicking the low APN levels in Phase I ROP) decreased LCPUFA levels (including ω-3 and ω-6) in retinas under normoglycemic and hyperglycemic conditions. ω-3 (vs. ω-6) LCPUFA activated the APN pathway by increasing the circulating APN levels and inducing expression of the retinal APN receptor. Our findings suggested that both ω-3 and ω-6 LCPUFA are crucial in protecting against retinal neurovascular dysfunction in a Phase I ROP model; adequate ω-6 LCPUFA levels must be maintained in addition to ω-3 supplementation to prevent retinopathy. Activation of the APN pathway may further enhance the ω-3 and ω-6 LCPUFA's protection against ROP. [ABSTRACT FROM AUTHOR]

The aim of this prospective study was to compare retinal vascular diameter measurements taken from standard fundus images and adaptive optics (AO) images. We analysed retinal images of twenty healthy subjects with 45-degree funduscopic colour photographs (CR-2 Canon fundus camera, Canon™) and adaptive optics (AO) fundus images (rtx1 camera, Imagine Eyes®). Diameters were measured using three software applications: the VAMPIRE (Vessel Assessment and Measurement Platform for Images of the REtina) annotation tool, IVAN (Interactive Vessel ANalyzer) for funduscopic colour photographs, and AO_Detect_Artery™ for AO images. For the arterial diameters, the mean difference between AO_Detect_Artery™ and IVAN was 9.1 µm (−27.4 to 9.2 µm, p = 0.005) and the measurements were significantly correlated (r = 0.79). The mean difference between AO_Detect_Artery™ and VAMPIRE annotation tool was 3.8 µm (−34.4 to 26.8 µm, p = 0.16) and the measurements were poorly correlated (r = 0.12). For the venous diameters, the mean difference between the AO_Detect_Artery™ and IVAN was 3.9 µm (−40.9 to 41.9 µm, p = 0.35) and the measurements were highly correlated (r = 0.83). The mean difference between the AO_Detect_Artery™ and VAMPIRE annotation tool was 0.4 µm (−17.44 to 25.3 µm, p = 0.91) and the correlations were moderate (r = 0.41). We found that the VAMPIRE annotation tool, an entirely manual software, is accurate for the measurement of arterial and venular diameters, but the correlation with AO measurements is poor. On the contrary, IVAN, a semi-automatic software tool, presents slightly greater differences with AO imaging, but the correlation is stronger. Data from arteries should be considered with caution, since IVAN seems to significantly under-estimate arterial diameters. [ABSTRACT FROM AUTHOR]

The effective segmentation of retinal blood vessels is essential for the medical diagnosis of ophthalmology diseases. In this paper, a novel approach is presented to segment retinal vessels accurately and efficiently. Firstly, we propose a simple simplified pulse coupled neural network utilizing the similarity of adjacent neurons to acquire the basic structure of blood vessels. Then we apply a line connector to solve the problem of broken vessels occurring in the segmentation, in order to present a complete structure of the blood vessels and improve the accuracy of vessel identification. Experimental analyses on two publicly available databases show that the proposed methods with or without the line connector outperform the most existing methods in terms of average accuracy and have a fast response time. It is of great importance for medical diagnosis with high accuracy and short time consumption. Our methods are practicable either for retinal vessel segmentation, or for other applications of clinical research. [ABSTRACT FROM AUTHOR]

Many network designs in recent years have offered deeper layered solutions. However, models that achieve high-performance results with fewer layers are preferred due to causing less processing load for the system. The U-Net authors succeeded in efficiently creating a model with fewer layers. However, the U-Net architecture also requires improvement to become more efficient. For this purpose, we offer a novel encoder-decoder architecture based on the U-Net and the LU-Net. Furthermore, we propose using a reduced number of up-sampling operations, which were utilized together with the down-sampling operations intensively in the encoder section in our previous research, in the encoder part. The proposed architecture was evaluated on the IOSTAR dataset for the segmentation of retinal vessels. The preprocessing and data augmentation processes were applied to the images before training. The U-Net, LU-Net, and the proposed model were evaluated by using the accuracy, sensitivity, specificity, Dice, and Jaccard metrics. The proposed model achieved performance metric values such as an accuracy of 97.29%, a sensitivity of 81.10%, a specificity of 98.94%, a Dice coefficient of 84.66%, and a Jaccard coefficient of 73.41%. The proposed model obtained improved results compared with the other models, especially for test samples. [ABSTRACT FROM AUTHOR]

Accurate segmentation of fine-grained information is an important step in medical image analysis applications. With the development of the encoder-decoder-based networks, various network structures and algorithms have made significant progress in semantic segmentation tasks. This work aims to present a novel high-resolution encoder-decoder network (HRED-Net) for fine-grained image segmentation that is highly accurate for small-scale targets. We design a multiscale context connection module to extract feature information without reducing the resolution, and propose a multiresolution fusion model to fine-tune the final results. In addition, these modules are trained together with a detail-oriented loss function to enhance the model's perception of fine-grained parts. Through experiments on the DRIVE dataset, we found a balance between these modules, and our comparison results show that in addition to the extraction multiscale features, the fusion of multiresolution prediction information is also beneficial for fine-grained segmentation. Our method yielded significant improvements in the accuracy and sensitivity in retinal vessel and lung segmentation tasks.

Introduction: Physical activity has beneficial effects on both cardiovascular and neuro-cognitive parameters, and these two modalities are known to interact at rest. However, findings on their interaction during exercise are inconclusive. Purpose: Therefore, this longitudinal study aimed to investigate the effects of different forms of exercise (training period, marathon race, and recovery period) on both parameters and their interaction. Methods: We included 100 marathon runners (MA) (mean±SD age = 43.6 ± 10.0 yr, 80 males) and 46 age- and sex-matched sedentary controls (SC, for baseline comparison). Over the 6-month study period with six visits (12 and 2 wk before the marathon; immediately, 24 h, 72 h, and 12 wk after the marathon), we assessed cognitive parameters by evaluating the 1- to 3-back d prime, the d2 task, and the Trail Making Tests A (TMT A) and B (TMT B), and the retinal vessel parameters by assessing arteriolar-to-venular ratio (AVR), central retinal arteriolar equivalent (CRAE), and central retinal venular equivalent (CRVE). Results: In the long-term analysis, 3-back d prime correlated positively with AVR (P=0.024, B = 1.86, SE = 0.824) and negatively with CRVE (P=0.05, B = -0.006, SE = 0.003), and TMT B correlated negatively with CRAE (P=0.025, B = -0.155, SE = 0.069), even after correcting for age and systolic blood pressure as possible confounders. Acute effects were inconsistent with maximal cognitive improvement 24 h after the marathon. AVR was significantly smaller in SC compared with MA. Conclusion: Chronic exercise seems to prime the central nervous system for acute, intensive bouts of exercise. Our findings indicate a possible relationship between cognitive performance in high-demand tasks and retinal vasculature and support the idea of a neuroplastic effect of exercise. [ABSTRACT FROM AUTHOR]

To identify various retinal pathologies like diabetic retinopathy, hypertension, glaucoma, arteriosclerosis fundus vasculature plays important role. To assist specialists for the determination of diseases it is essential to extract the retinal vasculature. This paper represents a method to segment the retinal vasculature. This paper contains four parts: first part is preprocessing which prepare funds images to extract vessels. Secondly an image enhancement includes bottom-hat transform followed by filtering. In third stage K-means is used to acquire binary segmented image; and lastly wrongly selected and detached group of pixels removed in postprocessing step. Online available databases STARE and DRIVE are used to test the method. [ABSTRACT FROM AUTHOR]

Purpose: To present a case of atypical unilateral developmental retinal vascular anomaly. Observations: A 10-year-old girl presented to her paediatrician after an absent red reflex was noted in a photograph. She had right anisometropic amblyopia and right iris heterochromia, but was otherwise healthy, with no visual complaints. Fundus examination revealed abnormal right retinal vasculature in keeping with an arteriovenous malformation (AVM). OCTA performed at age 16, showed large aberrant veins in the right eye, whereas OCTA B-Scans showed that the same eye had significantly higher retinal blood perfusion than the unaffected eye. Conclusions and Importance: OCTA is a valuable, non-invasive emerging method of evaluating patients with AVMs, with this patient having a unique unilateral presentation of a developmental anomaly, without evidence of progression or other vessel malformation. OCTA allowed assessment of flow between the affected and non-affected eye, quantifying the greater blood perfusion in the affected eye due to the AVM.

It has been proven that the deformability of red blood cells (RBC) is reduced owing to changes in mechanical properties, such as diabetes mellitus and hypertension. To probe the effects of RBC morphological and physical parameters on the flow field in bifurcated arterioles, three types of RBC models with various degrees of biconcave shapes were built based on the in vitro experimental data. The dynamic behaviors of the RBCs in shear flow were simulated to validate the feasibility of the finite element-Arbitrary Lagrangian–Eulerian method with a moving mesh. The influences of the shear rate and viscosity ratios on RBC motions were investigated. The motion of RBCs in arteriolar bifurcations was further simulated. Abnormal variations in the morphological and physical parameters of RBCs may lead to diminished tank-tread motion and enhanced tumbling motion in shear flow. Moreover, abnormal RBC variations can result in slower RBC motion at the bifurcation with a longer transmit time and greater flow resistance, which may further cause inadequate local oxygen supply. These findings would provide useful insights into the microvascular complications in diabetes mellitus.

Giant cell arteritis (GCA) is a potential sight-threatening disease. Although it is associated with polymyalgia rheumatica (PMR), visual loss is not common in PMR. A retinal oximeter can be used to conduct a direct, non-invasive, in vivo assessment of the vascular system. In a cross-sectional study, we measured the retinal oxygen saturation and retinal vessel calibers in GCA patients, PMR patients, and control participants. Twenty GCA patients (38 eyes), 19 PMR patients (33 eyes), and 12 controls (20 eyes) were investigated. Images were analyzed using Oxymap Analyzer software 2.5.0 (Oxymap ehf., Reykjavik, Iceland). Groups were compared using an age- and sex-adjusted linear mixed model regression. The median (IQR) age for GCA patients was 69.0 (66.5–76.5) years, for PMR 69.0 (67.0–72.0) years, and for the controls 75.5 (71.5–81.0) years, respectively. As compared to the controls (115.3 µm), the retinal arterioles were significantly wider in patients with GCA (124.4 µm; p = 0.023) and PMR (124.8 µm; p = 0.049). No difference was found in the retinal venular caliber or vascular oxygen saturation. These results indicate that GCA and PMR patients differ similarly in the retinal arteriolar diameter compared to controls. Further studies are needed in order to clarify the underlying inflammatory mechanisms in retinal arteriolar vessels and if these parameters can be used to predict clinical outcomes.

Purpose: To investigate the changes in the retinal vessels (RVs) in different sectors in patients with primary open-angle glaucoma (POAG), and their possible correlations with retinal nerve fiber layer thickness (RNFLT) and visual-field defects in the temporal parapapillary region.Methods: The RV diameters, RNFLTs, and visual-field parameters were measured. The temporal parapapillary region was divided into the temporal (T, 315°-45°), temporal superior (TS, 45°-90°), and temporal inferior sectors (TI, 270°-315°). The changes in the RV diameters in each sector were determined, and their relationships with RNFLT, the mean deviation (MD), and visual field sensitivity (VFS) were examined.Results: Fifty POAG patients (50 eyes) and 50 healthy subjects (50 eyes) were included. Compared with the healthy subjects, the POAG group had a significantly smaller accumulated parapapillary RV diameter (P < 0.001), which was positively correlated with the MD and RNFLT. When the different temporal sectors were examined, the accumulated RV diameters were significantly smaller in the POAG group than in the healthy controls in the TI and T sectors, but not in the TS sector. The accumulated diameters in the TI and T sectors were correlated with the corresponding RNFLTs (all P < 0.05), but only the accumulated diameter in the TI sector was correlated with the VFS.Conclusions: In POAG, the changes in the RVs differed between different temporal sectors, with the most prominent changes occurring in the TI and T sectors.

There is a gap in understanding the effect of the essential ω-3 and ω-6 long-chain polyunsaturated fatty acids (LCPUFA) on Phase I retinopathy of prematurity (ROP), which precipitates proliferative ROP. Postnatal hyperglycemia contributes to Phase I ROP by delaying retinal vascularization. In mouse neonates with hyperglycemia-associated Phase I retinopathy, dietary ω-3 (vs. ω-6 LCPUFA) supplementation promoted retinal vessel development. However, ω-6 (vs. ω-3 LCPUFA) was also developmentally essential, promoting neuronal growth and metabolism as suggested by a strong metabolic shift in almost all types of retinal neuronal and glial cells identified with single-cell transcriptomics. Loss of adiponectin (APN) in mice (mimicking the low APN levels in Phase I ROP) decreased LCPUFA levels (including ω-3 and ω-6) in retinas under normoglycemic and hyperglycemic conditions. ω-3 (vs. ω-6) LCPUFA activated the APN pathway by increasing the circulating APN levels and inducing expression of the retinal APN receptor. Our findings suggested that both ω-3 and ω-6 LCPUFA are crucial in protecting against retinal neurovascular dysfunction in a Phase I ROP model; adequate ω-6 LCPUFA levels must be maintained in addition to ω-3 supplementation to prevent retinopathy. Activation of the APN pathway may further enhance the ω-3 and ω-6 LCPUFA’s protection against ROP.

The aim of this prospective study was to compare retinal vascular diameter measurements taken from standard fundus images and adaptive optics (AO) images. We analysed retinal images of twenty healthy subjects with 45-degree funduscopic colour photographs (CR-2 Canon fundus camera, Canon™) and adaptive optics (AO) fundus images (rtx1 camera, Imagine Eyes®). Diameters were measured using three software applications: the VAMPIRE (Vessel Assessment and Measurement Platform for Images of the REtina) annotation tool, IVAN (Interactive Vessel ANalyzer) for funduscopic colour photographs, and AO_Detect_Artery™ for AO images. For the arterial diameters, the mean difference between AO_Detect_Artery™ and IVAN was 9.1 µm (−27.4 to 9.2 µm, p = 0.005) and the measurements were significantly correlated (r = 0.79). The mean difference between AO_Detect_Artery™ and VAMPIRE annotation tool was 3.8 µm (−34.4 to 26.8 µm, p = 0.16) and the measurements were poorly correlated (r = 0.12). For the venous diameters, the mean difference between the AO_Detect_Artery™ and IVAN was 3.9 µm (−40.9 to 41.9 µm, p = 0.35) and the measurements were highly correlated (r = 0.83). The mean difference between the AO_Detect_Artery™ and VAMPIRE annotation tool was 0.4 µm (−17.44 to 25.3 µm, p = 0.91) and the correlations were moderate (r = 0.41). We found that the VAMPIRE annotation tool, an entirely manual software, is accurate for the measurement of arterial and venular diameters, but the correlation with AO measurements is poor. On the contrary, IVAN, a semi-automatic software tool, presents slightly greater differences with AO imaging, but the correlation is stronger. Data from arteries should be considered with caution, since IVAN seems to significantly under-estimate arterial diameters.

Retinal artery–vein (AV) classification is a prerequisite for quantitative analysis of retinal vessels, which provides a biomarker for neurologic, cardiac, and systemic diseases, as well as ocular diseases. Although convolutional neural networks have presented remarkable performance on AV classification, it often comes with a topological error, like an abrupt class flipping on the same vessel segment or a weakness for thin vessels due to their indistinct appearances. In this paper, we present a new method for AV classification where the underlying vessel topology is estimated to give consistent prediction along the actual vessel structure. We cast the vessel topology estimation as iterative vascular connectivity prediction, which is implemented as deep-learning-based pairwise classification. In consequence, a whole vessel graph is separated into sub-trees, and each of them is classified as an artery or vein in whole via a voting scheme. The effectiveness and efficiency of the proposed method is validated by conducting experiments on two retinal image datasets acquired using different imaging techniques called DRIVE and IOSTAR. [ABSTRACT FROM AUTHOR]

Importance: Vascular delay that occurs early in the development of retinopathy of prematurity (ROP) is a risk factor that can be compensated by ensuring a good rate of retinal vascularization to avoid ROP that requires treatment.Background: The objective of the present study was to determine the association between ROP that requires treatment and risk factors such as the extent of the temporal avascular area of the retina and the number of days of mechanical ventilation (MV).Design: Observational retrospective case-control study.Participants: Two hundred and twenty-eight premature newborns included in the screening protocol for retinopathy of prematurity.Methods: Subjects underwent retinal examination in the 4 and 6th postnatal weeks.Main Outcome Measures: The temporal avascular area was measured in disc diameters (DD), while the MV time was measured in days of treatment.Results: Patients with a longer MV time had a higher risk of treatment (R2: 24.7, p < 0.0001; increase in risk of 8.1% for each additional day), as did those who showed greater avascular area (R2: 24.7, p < 0.0001; increase in risk of 111% for each additional DD). An online calculator system and a table are presented for calculating the risk of ROP requiring treatment as a function of these two risk factors.Conclusions and Relevance: The temporal avascular area of the retina and MV time must be taken into account in the first examination of the newborn to predict the need for ROP treatment.

The tortuosity changes of curvilinear anatomical organs such as nerve fibers or vessels have a close relationship with a number of diseases. Therefore, the automatic estimation and representation of the tortuosity is desired in medical image for such organs. In this paper, an automated framework for tortuosity estimation is proposed for corneal nerve and retinal vessel images. First, the weighted local phase tensor-based enhancement method is employed and the curvilinear structure is extracted from raw image. For each curvilinear structure with a different position and orientation, the curvature is measured by the exponential curvature estimation in the 3D space. Then, the tortuosity of an image is calculated as the weighted average of all the curvilinear structures. Our proposed framework has been evaluated on two corneal nerve fiber datasets and one retinal vessel dataset. Experiments on three curvilinear organ datasets demonstrate that our proposed tortuosity estimation method achieves a promising performance compared with other state-of-the-art methods in terms of accuracy and generality. In our nerve fiber dataset, the method achieved overall accuray of 0.820, and 0.734, 0.881 for sensitivity and specificity, respectively. The proposed method also achieved Spearman correlation scores 0.945 and 0.868 correlated with tortuosity grading ground truth for arteries and veins in the retinal vessel dataset. Furthermore, the manual labeled 403 corneal nerve fiber images with different levels of tortuosity, and all of them are also released for public access for further research. [ABSTRACT FROM AUTHOR]

Purpose of Review: The aim of this study to is report the findings of a systemic review and meta-analysis of the literature on the association between retinal vascular caliber and cardiovascular diseases. Recent Findings: The caliber of retinal vessels has been recognized as an important biomarker for risk stratification in various cardiovascular diseases, such as coronary artery disease, heart failure, stroke, and mortality. Summary: Non-invasively quantifying retinal vasculature may be useful in screening individuals who are at risk of cardiovascular disease. Further evaluating the role of retinal vessel anatomy and incorporating it into a scoring system on risk of cardiovascular diseases are needed in future studies. [ABSTRACT FROM AUTHOR]

Purpose: To characterize the phenotype of retinal vessels using central retinal artery equivalent (CRAE), central retinal vein equivalent (CRVE), tortuosity and fractal dimension (FD) in primary open‐angle glaucoma (POAG) subjects. Methods: This prospective case–control multicentre study included 61 POAG subjects and 61 controls matched for age, systemic hypertension and body mass index. Fundus images of the right eye were acquired using a non‐mydriatic camera. Central retinal artery equivalent (CRAE), CRVE, arteriole‐to‐venule ratio, FD and tortuosity of the vascular network were measured using VAMPIRE software (Vessel Assessment and Measurement Platform for Images of the Retina). Primary open‐angle glaucoma (POAG) patients underwent 24.2 sita‐standard visual field and peri‐papillary optical coherence tomography (OCT) examinations. Data were expressed as median and interquartile range (75–25th percentiles). Results: The control group was comparable to the POAG group for sex ratio, refraction and intraocular pressure. The mean CRAE and the mean CRVE were significantly lower in the POAG group than in the control group [150.5 (137.9; 157.1) μm versus 161.3 (154.0; 168.4) μm and 204.8 (190.1; 218.1) μm versus 233.5 (222.3; 246.9) μm, respectively; p < 0.001] and for fractal parameters as well. No significant difference was found for tortuosity between the two groups. There was a significant correlation between CRAE and retinal nerve fibre layer (RNFL) thickness (r = 0.27; p = 0.03). VAMPIRE parameters were not correlated with visual field indices. Conclusion: Primary open‐angle glaucoma (POAG) was associated with a narrowing of arterial and venous retinal vessels, a higher arteriole‐to‐venule ratio and lower values of FD. The relationship between CRAE and RNFL thickness needs further investigation. [ABSTRACT FROM AUTHOR]

Tｈｉｓ ｐａｐｅｒ ｐｒｏｐｏｓｅｓ ａｎ ａｌｇｏｒｉｔｈｍ ｂａｓｅｄ ｏｎ ｏｒｉｅｎｔａｔｉｏｎ ｓｃｏｒｅｓ ｃｏｍｂｉｎｅｄ ｗｉｔｈ Ｆｒａｎｇｉ ｆｉｌｔｅｒ ｔｏ ｆｉｘ ｔｈｅ ｄｉｆｆｉｃｕｌｔｉｅｓ ｃａｕｓｅｄ ｂｙ ｂｉｆｕｒｃａｔｉｏｎ ａｎｄ ｃｒｏｓｓｉｎｇｓ ｏｆ ｒｅｔｉｎａｌ ｖｅｓｓｅｌｓ. Ｔｈｅ Ｆｒａｎｇｉ ｆｉｌｔｅｒꎬ ｗｈｉｃｈ ｉｓ ｃｏｎｓｔｒｕｃｔｅｄ ｂｙ Ｈｅｓｓｉａｎ ｍａｔｒｉｘ ａｎｄ ｓｕｉｔａｂｌｅ ｆｏｒ ｆｉｌｔｅｒｉｎｇ ｔｈｅ ｌｉｎｅａｒ ｏｂｊｅｃｔꎬ ｉｓ ｕｓｅｄ ｔｏ ｅｎｈａｎｃｅ ｔｈｅ ｃｏｎｔｒａｓｔ ｏｆ ｔｈｅ ｂｌｏｏｄ ｖｅｓｓｅｌｓ. Ｔｈｅ ａｎｉｓｏｔｒｏｐｙ ａｎｄ ｏｒｔｈｏｇｏｎａｌｉｔｙ ｏｆ ｔｈｅ ｃａｋｅ ｗａｖｅｌｅｔ ｉｎ ｔｈｅ ｏｒｉｅｎｔａｔｉｏｎ ｓｃｏｒｅｓ ａｒｅ ｕｓｅｄ ｔｏ ｆｉｌｔｅｒ ｔｈｅ ｂｌｏｏｄ ｖｅｓｓｅｌｓ ｉｎ ｍｕｌｔｉｐｌｅ ａｎｇｌｅｓ ａｎｄ ｄｉｒｅｃｔｉｏｎｓꎬ ｗｈｉｃｈ ｉｓ ｂｅｎｅｆｉｃｉａｌ ｔｏ ｔｈｅ ｐｒｏｃｅｓｓｉｎｇ ｏｆ ｄｅｔａｉｌｓ ａｎｄ ｔｈｅ ｃｏｍｐｌｅｔｅ ｓｅｇｍｅｎｔａｔｉｏｎ ｏｆ ｔｈｅ ｒｅｔｉｎａｌ ｖａｓｃｕｌａｒ ｎｅｔｗｏｒｋ. Ｔｈｅ ｃｏｍｐａｒｉｓｏｎ ｏｆ ｔｈｅ ｍｅｔｈｏｄ ｐｒｏｐｏｓｅｄ ｗｉｔｈ ｏｔｈｅｒ ｅｘｉｓｔｉｎｇ ｍｅｔｈｏｄｓ ｓｈｏｗｓ ｔｈａｔ ｔｈｅ ａｌｇｏｒｉｔｈｍ ｉｓ ｂｅｔｔｅｒ ｔｈａｎ ｏｔｈｅｒ ａｌｇｏｒｉｔｈｍｓ ｉｎ ｐｒｏｃｅｓｓｉｎｇ ｔｈｅ ｂｉｆｕｒｃａｔｉｏｎ ａｎｄ ｃｒｏｓｓｉｎｇｓꎬ ａｎｄ ｔｈｅ ｍｅａｓｕｒｅｍｅｎｔｓ ｏｆ ａｃｃｕｒａｃｙꎬ ｓｅｎｓｉｔｉｖｉｔｙ ａｎｄ ｓｐｅｃｉｆｉｃｉｔｙ ａｒｅ ｓｕｐｅｒｉｏｒ ｔｏ ｅｘｉｓｔｉｎｇ ａｌｇｏｒｉｔｈｍｓ. [ABSTRACT FROM AUTHOR]

Retinal blood vessel extraction is considered to be the indispensable action for the diagnostic purpose of many retinal diseases. In this work, a parallel fully convolved neural network–based architecture is proposed for the retinal blood vessel segmentation. Also, the network performance improvement is studied by applying different levels of preprocessed images. The proposed method is experimented on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (STructured Analysis of the Retina) which are the widely accepted public database for this research area. The proposed work attains high accuracy, sensitivity, and specificity of about 96.37%, 86.53%, and 98.18% respectively. Data independence is also proved by testing abnormal STARE images with DRIVE trained model. The proposed architecture shows better result in the vessel extraction irrespective of vessel thickness. The obtained results show that the proposed work outperforms most of the existing segmentation methodologies, and it can be implemented as the real time application tool since the entire work is carried out on CPU. The proposed work is executed with low-cost computation; at the same time, it takes less than 2 s per image for vessel extraction. [ABSTRACT FROM AUTHOR]

The detection of vessels is the first step towards an automatic diagnosis and in-depth study of retinal images to aid ophthalmologists. In this paper, a real-time algorithm based on fuzzy morphological techniques is introduced to segment vessels in retinal images. This framework provides a good trade-off between expressive power and computational requirements, since the information in the local neighbourhood is quickly processed by combining a series of fast procedures. Specifically, this method is based on the fuzzy black top-hat transform, which proves to be a simple yet very effective technique. The algorithm processes images of the DRIVE and STARE datasets, in average, in 37 and 57 ms, respectively. Thus, it can be employed while a patient is being examined, embedded into more complex systems or as a pre-screening method for large volumes of data. It outstands when it is compared with other state-of-the-art methodologies in terms of its real-time processing time and its competitive performance. [ABSTRACT FROM AUTHOR]

Objectives: The examination of retinal microvascular abnormalities through fundus photography is currently the best available non‐invasive technique for assessment of cerebral vascular status. Several studies in the last decade have reported higher incidences of adverse cerebrovascular events in Schizophrenia (SCZ) and bipolar disorder (BD). However, retinal microvasculature abnormalities in SCZ and BD have remained under‐explored, and no study has compared this aspect of SCZ and BD till date. Methods: Retinal Images of 100 SCZ patients, BD patients, and healthy volunteers each were acquired by trained individuals using a non‐mydriatic camera with a 40‐degree field of view. The retinal images were quantified using a valid semi‐automated method. The average of left and right eye diameters of the venules and arterioles passing through the extended zone between 0.5 and 2 disc diameters from the optic disc were calculated. Results: The groups differed significantly with respect to average diameters of both retinal venules (P < 0.001) and retinal arterioles (P < 0.001), after controlling for age and sex. Both SCZ and BD patients had significantly narrower arterioles and wider venules compared to HV. There were also significant differences between SCZ and BD patients; patients with BD had narrower arterioles and wider venules. Conclusion: Considering the affordability and easy accessibility of the investigative procedure, retinal microvascular examination could serve as a potential screening tool to identify individuals at risk for adverse cerebrovascular events. The findings of the current study also provide a strong rationale for further systematic examination of retinal vascular abnormalities in SCZ and BD. [ABSTRACT FROM AUTHOR]