Retinal Blood Vessels Research Articles

A novel compound heterozygous variant of MYO7A in Usher syndrome type 1

Usher syndrome (USH) is a recessive genetic disorder manifested by congenital sensorineural hearing loss and progressive retinitis pigmentosa, which leads to audiovisual impairment. We report a patient with Usher syndrome type 1 with new compound heterozygous MYO7A variants. A total of four members from the USH family were included. Medical history and retinal examinations were taken and genomic DNA from peripheral blood was extracted in the proband and other members. 381 retinal disease-associated genes were screened using targeted sequence capture array technology and Sanger sequencing was used to confirm the screening results. Scanning laser ophthalmoscope showed bone spicule pigmentary deposits in the mid-peripheral retina and whitish and thin retinal blood vessels especially in the arterioles. Optical coherence tomography showed that the centrality of the macular ellipsoid band disappeared in both eyes, and only remained near the fovea. Visual field examination showed a progressive loss of the visual field in a concentric pattern in both eyes. The electroretinography showed a significant decrease in the amplitudes of a- and b-waves in the scotopic and photopic condition. DNA sequencing identified the compound heterozygous variants including c.1003+1G > A: p. (?) and c.5957_5958del: p.G1987Lfs*50 of MYO7A, with the latter being novel. In this study, we found a novel compound heterozygous variant in MYO7A, which enriched the mutation spectrum and expanded our understanding of the heterogeneity of phenotype and genotype of Usher syndrome type 1.

Physics-informed deep generative learning for quantitative assessment of the retina

Disruption of retinal vasculature is linked to various diseases, including diabetic retinopathy and macular degeneration, leading to vision loss. We present here a novel algorithmic approach that generates highly realistic digital models of human retinal blood vessels, based on established biophysical principles, including fully-connected arterial and venous trees with a single inlet and outlet. This approach, using physics-informed generative adversarial networks (PI-GAN), enables the segmentation and reconstruction of blood vessel networks with no human input and which out-performs human labelling. Segmentation of DRIVE and STARE retina photograph datasets provided near state-of-the-art vessel segmentation, with training on only a small (n = 100) simulated dataset. Our findings highlight the potential of PI-GAN for accurate retinal vasculature characterization, with implications for improving early disease detection, monitoring disease progression, and improving patient care.

Retina Blood Vessels Segmentation and Classification with the Multi-featured Approach.

Segmenting retinal blood vessels poses a significant challenge due to the irregularities inherent in small vessels. The complexity arises from the intricate task of effectively merging features at multiple levels, coupled with potential spatial information loss during successive down-sampling steps. This particularly affects the identification of small and faintly contrasting vessels. To address these challenges, we present a model tailored for automated arterial and venous (A/V) classification, complementing blood vessel segmentation. This paper presents an advanced methodology for segmenting and classifying retinal vessels using a series of sophisticated pre-processing and feature extraction techniques. The ensemble filter approach, incorporating Bilateral and Laplacian edge detectors, enhances image contrast and preserves edges. The proposed algorithm further refines the image by generating an orientation map. During the vessel extraction step, a complete convolution network processes the input image to create a detailed vessel map, enhanced by attention operations that improve modeling perception and resilience. The encoder extracts semantic features, while the Attention Module refines blood vessel depiction, resulting in highly accurate segmentation outcomes. The model was verified using the STARE dataset, which includes 400 images; the DRIVE dataset with 40 images; the HRF dataset with 45 images; and the INSPIRE-AVR dataset containing 40 images. The proposed model demonstrated superior performance across all datasets, achieving an accuracy of 97.5% on the DRIVE dataset, 99.25% on the STARE dataset, 98.33% on the INSPIREAVR dataset, and 98.67% on the HRF dataset. These results highlight the method's effectiveness in accurately segmenting and classifying retinal vessels.

Retinochoroidal Vascular Changes in Long-Term Type 1 Diabetic Patients Assessed by Optic Coherence Tomography Angiography.

To study retinal and choriocapillaris (CC) alterations using optical coherence tomography angiography (OCTA) in long-term type 1 diabetic (DM1) patients without diabetic retinopathy (DR). Seventy-eight eyes from 78 well-controlled DM1 patients diagnosed at least 15 years prior and 130 eyes of 130 healthy subjects were included in a cross-sectional descriptive study. Six eyes were excluded from the DM1 group. OCTA with Deep Range Imaging (DRI)-Triton swept source (SS)-OCT was performed. Statistically significant differences were found in all areas of the superficial capillary plexus (SCP), with lower values in DM1 patients. Differences were noted in all quadrants of the deep capillary plexus (DCP) except for the central area. Significant changes in CC blood flow were only found in the center. The foveal avascular zone (FAZ) area and diameters in the SCP were significantly different, while the DCP FAZ area was similar in both groups. Disease duration and microalbuminuria correlated negatively with some SCP areas and positively with FAZ values. Anatomical evaluation revealed microaneurysms in both plexuses, FAZ modifications, and areas lacking blood perfusion. Long-term type 1 diabetic patients without DR display microvascular abnormalities affecting retinal and CC blood perfusion, along with anatomical changes in retinal blood vessels.

Soul: An OCTA dataset based on Human Machine Collaborative Annotation Framework

Branch retinal vein occlusion (BRVO) is the most prevalent retinal vascular disease that constitutes a threat to vision due to increased venous pressure caused by venous effluent in the space, leading to impaired visual function. Optical Coherence Tomography Angiography (OCTA) is an innovative non-invasive technique that offers high-resolution three-dimensional structures of retinal blood vessels. Most publicly available datasets are collected from single visits with different patients, encompassing various eye diseases for distinct tasks and areas. Moreover, due to the intricate nature of eye structure, professional labeling not only relies on the expertise of doctors but also demands considerable time and effort. Therefore, we have developed a BRVO-focused dataset named Soul (Source of ocular vascular) and propose a human machine collaborative annotation framework (HMCAF) using scrambled retinal blood vessels data. Soul is categorized into 6 subsets based on injection frequency and follow-up duration. The dataset comprises original images, corresponding blood vessel labels, and clinical text information sheets which can be effectively utilized when combined with machine learning.

Causal role of immune cells in uveitis: a Mendelian randomization study.

Uveitis refers to a group inflammation affecting the uvea, retina, retinal blood vessels as well as vitreous body, which is one of the common causes of blindness. There is growing evidence linking different types of immune cells to uveitis, although it remains uncertain if these associations imply causal relationships. Recent advancements in high-density genetic markers like SNPs or CNVs for genotyping, along with the progress in genome-wide association studies (GWAS) technologies, have improved our understanding of the immunological mechanisms involved in ocular diseases. Therefore, our objective was to investigate the potential causal link between immune cells and uveitis using a Mendelian randomization study. The exposure and outcome GWAS data for this study were sourced from an open-access database (https://gwas.mrcieu.ac.uk/). Two-sample MR analysis was utilized to evaluate the causal relationship between 731 immune cell features and uveitis. Various MR methods were employed to reduce bias and obtain dependable estimates of the causal link between the immune cell variables and the outcomes. Instrumental variable selection criteria were carefully chosen to enhance the accuracy and efficacy of the causal relationship between different immune cell types and the risk of uveitis. Using two-sample MR, IVW modeling showed that GAD had significant effect on immunophenotypes. CD3 levels on CD45RA- CD4+ T cells (OR = 1.087, 95%CI = 1.029 ~ 1.147, p = 0.003) and CD3 levels on CM CD4+ T cells (OR = 1.086, 95%CI = 1.033 ~ 1.141, p = 0.001) were found to be elevated in cases of uveitis. HLA DR levels in CD14- CD16+ monocyte cells (OR = 0.735, 95% CI = 0.635 ~ 0.850, p < 0.001) and HLA DR levels in NK cells (OR = 0.910, 95% CI = 0.851 ~ 0.972, p = 0.005) were observed to be reduced in individuals with uveitis. Furthermore, Two cells were identified to be significantly associated with uveitis risk: HLA DR on in NK cells (OR = 0.938, 95%CI = 0.899 ~ 0.979, p = 0.003), HLA DR on CD14- CD16+ monocytes (OR = 0.924, 95%CI = 0.878 ~ 0.972, p = 0.002). This study highlights the intricate relationship between immune cells and generalized anxiety disorder using genetic methods, offering valuable insights for future clinical investigations.

Retinal Image Dataset of Infants and Retinopathy of Prematurity

Retinopathy of prematurity (ROP) represents a vasoproliferative disease, especially in newborns and infants, which can potentially affect and damage the vision. Despite recent advances in neonatal care and medical guidelines, ROP still remains one of the leading causes of worldwide childhood blindness. The paper presents a unique dataset of 6,004 retinal images of 188 newborns, most of whom are premature infants. The dataset is accompanied by the anonymized patients’ information from the ROP screening acquired at the University Hospital Ostrava, Czech Republic. Three digital retinal imaging camera systems are used in the study: Clarity RetCam 3, Natus RetCam Envision, and Phoenix ICON. The study is enriched by the software tool ReLeSeT which is aimed at automatic retinal lesion segmentation and extraction from retinal images. Consequently, this tool enables computing geometric and intensity features of retinal lesions. Also, we publish a set of pre-processing tools for feature boosting of retinal lesions and retinal blood vessels for building classification and segmentation models in ROP analysis.

Unet retinal vessel image segmentation algorithm based on coordinate attention mechanism and Min-ASPP module optimisation

In this paper, the Unet image segmentation algorithm is optimised and improved by introducing the coordinate attention mechanism and integrating the Min-ASPP module, and compared with the traditional Unet model, targeting the segmentation of retinal blood vessel images, which is a key problem in the field of medical image processing. The experimental results show that the optimised Unet algorithm combining the coordinate attention mechanism and Min-ASPP module has a smoother performance in the loss curve, faster convergence speed, and lower final converged loss value, which has an obvious advantage compared with the traditional Unet algorithm. Meanwhile, the optimised Unet algorithm shows higher accuracy and stability in the prediction results, providing ophthalmologists with more reliable information about the retinal vascular structure. Therefore, the research results of this paper show that the Unet image segmentation algorithm optimised by combining the coordinate attention mechanism and Min-ASPP module has better application prospects and effects in the retinal blood vessel image segmentation task, which provides a useful exploration and practice for improving the level of medical image processing technology.

In Vivo Optogenetic Manipulation of Transgene Expression in Retinal Neurovasculature.

The retina is prone to developing pathological neovascularization, a leading cause of blindness in humans. Because excess neovascularization does not affect the entire retina, global inhibition treatment of angiogenesis critically interferes with healthy, unaffected retinal tissue. We therefore established an in vivo photoactivated gene expression paradigm which would allow light-mediated targeting of antiangiogenic genetic treatment only to affected retinal regions. We synthesized a "caged" (i.e., reversibly inhibited) photosensitive 4-hydroxytamoxifen analog. Molecular docking analyses validated its reduced transcriptional activity. Caged 4-hydroxytamoxifen was intravitreally injected into mice harboring the inducible Cre/lox system, with CreERT2 being expressed via the Tie2 promoter in the neurovasculature. Subsequent in vivo irradiation of eyes significantly induced retinal expression of a Cre-dependent transgene in retinal blood vessels. Using GFAP-CreERT2 mice, successful photoactivation was also achieved in eyes and also in ex vivo brain slices for validation of the approach. This highlights the possibility of light-mediated gene therapies specific for the retina, a key first step in personalized medicine.

Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images.

Segmentation of retinal fragments like blood vessels, Optic Disc (OD), and Optic Cup (OC) enables the early detection of different retinal pathologies like Diabetic Retinopathy (DR), Glaucoma, etc. Accurate segmentation of OD remains challenging due to blurred boundaries, vessel occlusion, and other distractions and limitations. These days, deep learning is rapidly progressing in the segmentation of image pixels, and a number of network models have been proposed for end-to-end image segmentation. However, there are still certain limitations, such as limited ability to represent context, inadequate feature processing, limited receptive field, etc., which lead to the loss of local details and blurred boundaries. A multi-dimensional dense attention network, or MDDA-Net, is proposed for pixel-wise segmentation of OD in retinal images in order to address the aforementioned issues and produce more thorough and accurate segmentation results. In order to acquire powerful contexts when faced with limited context representation capabilities, a dense attention block is recommended. A triple-attention (TA) block is introduced in order to better extract the relationship between pixels and obtain more comprehensive information, with the goal of addressing the insufficient feature processing. In the meantime, a multi-scale context fusion (MCF) is suggested for acquiring the multi-scale contexts through context improvement. Specifically, we provide a thorough assessment of the suggested approach on three difficult datasets. In the MESSIDOR and ORIGA data sets, the suggested MDDA-NET approach obtains accuracy levels of 99.28% and 98.95%, respectively. The experimental results show that the MDDA-Net can obtain better performance than state-of-the-art deep learning models under the same environmental conditions.

Characteristics of retinal vascularization in reactivated retinopathy of prematurity requiring treatment and clinical outcome after reinjection of ranibizumab

This study aimed to determine whether the state of retinal vascularization after anti-vascular endothelial growth factor (anti-VEGF) injection can help predict the risk of reactivated retinopathy of prematurity (ROP) requiring treatment and whether repeated ranibizumab injection will be effective in such cases. We retrospectively reviewed 24 infants (43 eyes) who received ranibizumab monotherapy between January 2021 and December 2022. All eyes were classified as having non-retreated ROP or retreated ROP. The state of ROP at the time of treatment, the time required for resolution of plus disease, and the extent of vascularization at 4 and 8 weeks after treatment were analyzed. Extent of temporal retinal vascularization was measured with serial fundus images using disc-fovea distance (DF) unit and disc diameter (DD). Reactivated ROP requiring treatment occurred in six infants (25.0%) and ten eyes (23.3%) after ranibizumab treatment. The mean retreatment interval was 9.0 ± 3.3 weeks (range 4–16). In the retreated ROP group, the time required for the resolution of plus disease after primary injection was longer compared to the control group (13.3 days vs 5.2 days), with a mean ROP regression time of 3.4 weeks. All eyes in the retreated ROP showed retinal vascularization < 0.5 DF from the original site at 4 weeks after injection. In 90% of cases with retreated ROP, the extent of vascularization at 8 weeks after injection was within 1 DF from the original ROP site, and all cases showed reactivation in the posterior Zone II area. The extent of retinal neovascularization in the retreated group was an average of 0.7 DD (vs 1.7 DD) and 1.3 DD (vs 3.3 DD) at 4 and 8 weeks after injection, respectively. After ranibizumab retreatment, only one reactivated case with vitreous traction progressed to focal retinal detachment, while all other cases regressed with peripheral vascular development. The continuation of delayed retinal blood vessel development after ≥ 8 weeks may indicate a high likelihood of reactivated ROP requiring treatment. In the absence of vitreous traction, ranibizumab reinjection is likely to be effective in treating reactivated ROP requiring treatment.

Laddernet retinal vessel segmentation algorithm fusing attentional mechanisms

A retinal blood vessel segmentation algorithm fusing the attention mechanism is proposed to address the problems of insufficient accuracy and incorrect segmentation of minutiae in existing retinal blood vessel segmentation algorithms. The network structure used in this algorithm is Laddernet (LCT-UNet for short), which fuses the Convolutional Block Attention Module (CBAM) and Transformer, i.e., the residual module of Laddernet, which shares the weights, is structurally optimised to decrease the parameter count; After the residual module, CBAM is incorporated to adaptively adjust the weights of channels and spatial features to enhance the feature representation; Transformer with global self-attention mechanism is introduced at the bottom of the network to overcome the shortcomings of UNet's inability to model long-range relationships and spatial dependencies, and gradually refine the features so that the segmentation results have finer boundary and detail information. The model validity was verified on the public datasets DRIVE and CHASEDB1, and the experimental results showed that the ACC of LCT-UNet was 95.81% and 96.88%, SE was 79.74% and 81.12%, SP was 98.15% and 98.83%, and AUC was 98.22% and 98.99%, and the F1 values were 82.88% and 85.14%, respectively, and the comprehensive segmentation performance of the LCT-UNet network showed significant enhancement over the algorithms such as U-Net, R2UNet, and Laddernet.

Epithelial Membrane Protein 2 (EMP2) Blockade Attenuates Pathological Neovascularization in Murine Oxygen-Induced Retinopathy.

Retinopathy of prematurity (ROP) results from postnatal hyperoxia exposure in premature infants and is characterized by aberrant neovascularization of retinal blood vessels. Epithelial membrane protein-2 (EMP2) regulates hypoxia-inducible factor (HIF)-induced vascular endothelial growth factor (VEGF) production in the ARPE-19 cell line and genetic knock-out of Emp2 in a murine oxygen-induced retinopathy (OIR) model attenuates neovascularization. We hypothesize that EMP2 blockade via intravitreal injection protects against neovascularization. Ex vivo choroid sprouting assay was performed, comparing media and human IgG controls versus anti-EMP2 antibody (Ab) treatment. In vivo, eyes from wild-type (WT) mice exposed to hyperoxia from postnatal (P) days 7 to 12 were treated with P12 intravitreal injections of control IgG or anti-EMP2 Abs. Neovascularization was assessed at P17 by flat mount imaging. Local and systemic effects of anti-EMP2 Ab treatment were assessed. Choroid sprouts treated with 30µg/mL of anti-EMP2 Ab demonstrated a 48% reduction in vessel growth compared to control IgG-treated sprouts. Compared to IgG-treated controls, WT OIR mice treated with 4µg/g of intravitreal anti-EMP2 Ab demonstrated a 42% reduction in neovascularization. They demonstrated down-regulation of retinal gene expression in pathways related to vasculature development and up-regulation in genes related to fatty acid oxidation and tricarboxylic acid cycle respiratory electron transport, compared to controls. Anti-EMP2 Ab-treated OIR mice did not exhibit gross retinal histologic abnormalities, vision transduction abnormalities, or weight loss. Our results suggest that EMP2 blockade could be a local and specific treatment modality for retinal neovascularization in oxygen-induced retinopathies, without systemic adverse effects.

LMBiS-Net: A lightweight bidirectional skip connection based multipath CNN for retinal blood vessel segmentation

Blinding eye diseases are often related to changes in retinal structure, which can be detected by analysing retinal blood vessels in fundus images. However, existing techniques struggle to accurately segment these delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on specific operations can limit its ability to capture crucial details such as the edges of the vessel. This paper introduces LMBiS-Net, a lightweight convolutional neural network designed for the segmentation of retinal vessels. LMBiS-Net achieves exceptional performance with a remarkably low number of learnable parameters (only 0.172 million). The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. In addition, we have optimised the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimisation significantly reduces training time and improves computational efficiency. To assess LMBiS-Net’s robustness and ability to generalise to unseen data, we conducted comprehensive evaluations on four publicly available datasets: DRIVE, STARE, CHASE_DB1, and HRF The proposed LMBiS-Net achieves significant performance metrics in various datasets. It obtains sensitivity values of 83.60%, 84.37%, 86.05%, and 83.48%, specificity values of 98.83%, 98.77%, 98.96%, and 98.77%, accuracy (acc) scores of 97.08%, 97.69%, 97.75%, and 96.90%, and AUC values of 98.80%, 98.82%, 98.71%, and 88.77% on the DRIVE, STARE, CHEASE_DB, and HRF datasets, respectively. In addition, it records F1 scores of 83.43%, 84.44%, 83.54%, and 78.73% on the same datasets. Our evaluations demonstrate that LMBiS-Net achieves high segmentation accuracy (acc) while exhibiting both robustness and generalisability across various retinal image datasets. This combination of qualities makes LMBiS-Net a promising tool for various clinical applications.

WITHDRAWN: LSAC-Net: A lightweight scale-aware CNN with densely connected focal modulation for retinal blood vessel segmentation

The diagnosis of sight-threatening eye conditions typically involves segmenting retinal structures in fundus images. The segmentation process enables clinicians to identify alterations in retinal morphology, facilitating the detection and diagnosis of various eye diseases. Despite recent developments in image processing, current approaches often fail to partition delicate arteries precisely. Although deep learning has great potential for segmenting medical images, the accuracy of the segmentation process may be limited due to its dependence on repetitive convolution and pooling processes, which may impair the representation of edge information. In this study, we present LSAC-Net, a pixel-level convolutional neural network (CNN) designed specifically for retinal vessel segmentation. Moreover, it is lightweight, with only 37.5 K learnable parameters. LSAC-Net integrates a unique scale-aware feature extraction block (SAFEB) and a densely connected focal modulation block (DCFMB) to improve segmentation accuracy. In addition, careful selection of filter numbers to avoid overlap effectively shortens training times and boosts computational performance, both of which improve overall model efficiency. We performed extensive tests on different aspects of retinal images to evaluate the robustness and generalizability of LSAC-Net. In particular, a thorough evaluation of the model's precision in retinal artery segmentation, a crucial task for ophthalmological diagnosis and treatment, was carried out. We evaluated the performance and efficacy of LSAC-Net with a particular focus on RBV. The model obtains 98.65% specificity, 97.54% accuracy, and 98.88% area under the curve surpassing existing approaches. Experimental results confirm that LSAC-Net is robust, generalizable, and maintains a high level of segmentation accuracy. These features highlight LSAC-Net's potential as a useful instrument for accurate and timely retinal image segmentation in a variety of therapeutic contexts.

مدى إنتشار عوامل الخطر وارتباطها في تطور إعتلال الشبكية السكري في قسم طب العيون، مركز طبرق الطبي، ليبيا

Diabetic retinopathy is a condition of the eyes that can affect people with diabetes. This is the degree at which the retina's blood vessels are damaged by high blood sugar. These vascular structures can expand and rupture. Additionally, the vessels might close, preventing the circulation of blood. Sometimes, abnormally new blood vessels might grow on the retina. Any of the foregoing changes could impair your vision. The aim of this study is to identify risk factors that may enhance the development of diabetic retinopathy and explore strategies for reducing the possibility of visual impairment caused by this condition. A prospective cross-sectional study of diabetic patients registered at the Eye Department of Tobruk Medical Center in Tobruk, Libya between (01.06.2023 to 29.02.2024). Data was collected using a self-administered questionnaire. Grading of DR (diabetic retinopathy) was done by slit-lamp examination and fundoscopy by an ophthalmologist. Descriptive analysis included percentage, mean of age, and p-value by using SPSS 25. Result: There were 85 diabetic patients, with a mean age of 63.5 and an age range of 31 to 85 years. Of these, 98.8% were of Libyan nationality and 96.4% were place of residencein Tobruk. Forty-three women were present. Compared to individuals with diabetes for less than ten years, those with diabetes for eleven to fifteen years had an almost five-fold increased chance of having diabetic retinopathy disease (DR). Patients with poor diabetes control (HbA1c &gt; 9) had a 25-fold increased chance of developing PR compared to those with adequate control (HbA1c &lt; 7.5). Conclusion: Patients with uncontrolled diabetes and those with the disease for a longer period of time are more likely to develop diabetic retinopathy and experience visual impairment. Key word: Diabetic retinopathy, poor diabetes control, longer period of diabetes, Tobruk, Libya.

Diabetic Retinopathy Severity Level Detection Using Convolution Neural Network

Diabetic retinopathy is a common complication of diabetes mellitus, leading to damage and blockage of retinal blood vessels. Early and accurate detection of diabetic retinopathy severity levels is crucial for timely treatment and prevention of blindness. Diagnostic methods rely on manual examination and human interpretation, resulting in slower and less efficient treatment processes. As a branch of artificial intelligence, computer vision offers a potential solution to analyze retinal images quickly and accurately. The developed system employs image processing techniques and a CNN-based classification model to detect and classify the severity levels of diabetic retinopathy. By providing an automated and efficient approach, the system aims to assist doctors and optometrists in making informed decisions and reducing subjectivity in diagnosis. Early detection through this system can facilitate prompt treatment and improve patient outcomes. The developed system achieves promising results through experimentation and testing with various datasets, with accuracy ranging from 80% to 97%. This project's integration of artificial intelligence, machine learning, and image processing technologies demonstrates their potential in healthcare applications, particularly in diabetic retinopathy diagnosis.

Evaluation of an Active Disturbance Rejection Controller for Ophthalmic Robots with Piezo-Driven Injector.

Retinal vein cannulation involves puncturing an occluded vessel on the micron scale. Even single millinewton force can cause permanent damage. An ophthalmic robot with a piezo-driven injector is precise enough to perform this delicate procedure, but the uncertain viscoelastic characteristics of the vessel make it difficult to achieve the desired contact force without harming the retina. The paper utilizes a viscoelastic contact model to explain the mechanical characteristics of retinal blood vessels to address this issue. The uncertainty in the viscoelastic properties is considered an internal disturbance of the contact model, and an active disturbance rejection controller is then proposed to precisely control the contact force. The experimental results show that this method can precisely adjust the contact force at the millinewton level even when the viscoelastic parameters vary significantly (up to 403.8%). The root mean square (RMS) and maximum value of steady-state error are 0.32 mN and 0.41 mN. The response time is below 2.51 s with no obvious overshoot.

Optical imaging for diabetic retinopathy diagnosis and detection using ensemble models

Diabetes, characterized by heightened blood sugar levels, can lead to a condition called Diabetic Retinopathy (DR), which adversely impacts the eyes due to elevated blood sugar affecting the retinal blood vessels. The most common cause of blindness in diabetics is thought to be Diabetic Retinopathy (DR), particularly in working-age individuals living in poor nations. People with type 1 or type 2 diabetes may develop this illness, and the risk rises with the length of diabetes and inadequate blood sugar management. There are limits to traditional approaches for the early identification of diabetic retinopathy (DR). In order to diagnose diabetic retinopathy, a model based on Convolutional neural network (CNN) is used in a unique way in this research. The suggested model uses a number of deep learning (DL) models, such as VGG19, Resnet50, and InceptionV3, to extract features. After concatenation, these characteristics are sent through the CNN algorithm for classification. By combining the advantages of several models, ensemble approaches can be effective tools for detecting diabetic retinopathy and increase overall performance and resilience. Classification and image recognition are just a few of the tasks that may be accomplished with ensemble approaches like combination of VGG19,Inception V3 and Resnet 50 to achieve high accuracy. The proposed model is evaluated using a publicly accessible collection of fundus images.VGG19, ResNet50, and InceptionV3 differ in their neural network architectures, feature extraction capabilities, object detection methods, and approaches to retinal delineation. VGG19 may excel in capturing fine details, ResNet50 in recognizing complex patterns, and InceptionV3 in efficiently capturing multi-scale features. Their combined use in an ensemble approach can provide a comprehensive analysis of retinal images, aiding in the delineation of retinal regions and identification of abnormalities associated with diabetic retinopathy. For instance, micro aneurysms, the earliest signs of DR, often require precise detection of subtle vascular abnormalities. VGG19′s proficiency in capturing fine details allows for the identification of these minute changes in retinal morphology. On the other hand, ResNet50′s strength lies in recognizing intricate patterns, making it effective in detecting neoneovascularization and complex haemorrhagic lesions. Meanwhile, InceptionV3′s multi-scale feature extraction enables comprehensive analysis, crucial for assessing macular oedema and ischaemic changes across different retinal layers.

TLTNet: A novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation

Extracting global and local feature information is still challenging due to the problems of retinal blood vessel medical images like fuzzy edge features, noise, difficulty in distinguishing between lesion regions and background information, and loss of low-level feature information, which leads to insufficient extraction of feature information. To better solve these problems and fully extract the global and local feature information of the image, we propose a novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation, which consists of an encoder and a decoder and is connected between the encoder and decoder by a transscale transformer cascade module. Among them, the encoder consists of a local–global transscale transformer module, a multi-head layered transscale adaptive embedding module, and a local context(LCNet) module. The transscale transformer cascade module learns local and global feature information from the first three layers of the encoder, and multi-scale dependent features, fuses the hierarchical feature information from the skip connection block and the channel-token interaction fusion block, respectively, and inputs it to the decoder. The decoder includes a decoding module for the local context network and a transscale position transformer module to input the local and global feature information extracted from the encoder with retained key position information into the decoding module and the position embedding transformer module for recovery and output of the prediction results that are consistent with the input feature information. In addition, we propose an improved cross-entropy loss function based on the difference between the deterministic observation samples and the prediction results with the deviation distance, which is validated on the DRIVE and STARE datasets combined with the proposed network model based on the dual transformer structure in this paper, and the segmentation accuracies are 97.26% and 97.87%, respectively. Compared with other state-of-the-art networks, the results show that the proposed network model has a significant competitive advantage in improving the segmentation performance of retinal blood vessel images.