Characteristics Of Blood Vessels Research Articles

Bi-directional ConvLSTM residual U-Net retinal vessel segmentation algorithm with improved focal loss function

Accurate blood vessel segmentation on retinal blood vessel images is helpful for the early detection of ophthalmic diseases such as diabetes, hypertension, cardiovascular and cerebrovascular diseases, and inhibits the deterioration of the disease. In current research within the field of retinal blood vessel segmentation, significant challenges exist in accurately segmenting small blood vessels and maintaining blood vessel continuity. The segmentation algorithm proposed in this article offers substantial improvements to address these issues. To enhance the segmentation performance of retinal blood vessels and facilitate more accurate diagnosis of fundus diseases by ophthalmologists, this paper introduces a novel bidirectional convolutional long short-term memory (LSTM) residual U-Net segmentation algorithm, incorporating improvements to the Focal loss function. Firstly, in the encoding part of U-Net, the multi-scale convolution kernels and Bi-ConvLSTM were adopted to improve the residual structure, obtain richer blood vessel features and enhance the detection ability of micro vessels and the continuity of blood vessel characteristics. At the same time, the class balanced cross entropy loss function was improved and the proportional modulation factor is introduced to enhance the learning ability of the network for difficult samples. By adding the Bi-ConvLSTM to the residual structure and introducing the proportional modulation coefficient to the loss function, the network structure realizes better feature information detection and greatly enhances the detection ability of small blood vessels. The experimental analysis on the DRIVE and CHASE_DB1 data sets showed that the sensitivity, specificity, accuracy and AUC reached 0.7961, 0.9796, 0.9563, 0.9792; 0.8344, 0.9665, 0.9547, 0.9758, respectively. The experimental results fully show that the Bi-ConvLSTM residual U-Net segmentation algorithm based on the improved Focal loss function enhances the detection ability of small blood vessel features, improves the continuity of blood vessel features and the network segmentation performance, and is superior to U-Net algorithm and some current mainstream retinal blood vessel segmentation algorithms.

MAFE-Net: retinal vessel segmentation based on a multiple attention-guided fusion mechanism and ensemble learning network.

The precise and automatic recognition of retinal vessels is of utmost importance in the prevention, diagnosis and assessment of certain eye diseases, yet it brings a nontrivial uncertainty for this challenging detection mission due to the presence of intricate factors, such as uneven and indistinct curvilinear shapes, unpredictable pathological deformations, and non-uniform contrast. Therefore, we propose a unique and practical approach based on a multiple attention-guided fusion mechanism and ensemble learning network (MAFE-Net) for retinal vessel segmentation. In conventional UNet-based models, long-distance dependencies are explicitly modeled, which may cause partial scene information loss. To compensate for the deficiency, various blood vessel features can be extracted from retinal images by using an attention-guided fusion module. In the skip connection part, a unique spatial attention module is applied to remove redundant and irrelevant information; this structure helps to better integrate low-level and high-level features. The final step involves a DropOut layer that removes some neurons randomly to prevent overfitting and improve generalization. Moreover, an ensemble learning framework is designed to detect retinal vessels by combining different deep learning models. To demonstrate the effectiveness of the proposed model, experimental results were verified in public datasets STARE, DRIVE, and CHASEDB1, which achieved F1 scores of 0.842, 0.825, and 0.814, and Accuracy values of 0.975, 0.969, and 0.975, respectively. Compared with eight state-of-the-art models, the designed model produces satisfactory results both visually and quantitatively.

Angio-Net: deep learning-based label-free detection and morphometric analysis of in vitro angiogenesis.

Despite significant advancements in three-dimensional (3D) cell culture technology and the acquisition of extensive data, there is an ongoing need for more effective and dependable data analysis methods. These concerns arise from the continued reliance on manual quantification techniques. In this study, we introduce a microphysiological system (MPS) that seamlessly integrates 3D cell culture to acquire large-scale imaging data and employs deep learning-based virtual staining for quantitative angiogenesis analysis. We utilize a standardized microfluidic device to obtain comprehensive angiogenesis data. Introducing Angio-Net, a novel solution that replaces conventional immunocytochemistry, we convert brightfield images into label-free virtual fluorescence images through the fusion of SegNet and cGAN. Moreover, we develop a tool capable of extracting morphological blood vessel features and automating their measurement, facilitating precise quantitative analysis. This integrated system proves to be invaluable for evaluating drug efficacy, including the assessment of anticancer drugs on targets such as the tumor microenvironment. Additionally, its unique ability to enable live cell imaging without the need for cell fixation promises to broaden the horizons of pharmaceutical and biological research. Our study pioneers a powerful approach to high-throughput angiogenesis analysis, marking a significant advancement in MPS.

Quantitative Analysis of Bone, Blood Vessels, and Metastases in Mice Tibiae Using Synchrotron Radiation Micro-Computed Tomography

Bone metastases are one of the most dangerous consequences of breast cancer. Early diagnosis and treatment would slow down the development of the disease and increase the survival rates of patients. Bone micro-vasculature is believed to play a major role in the development of bone metastases. It could be used for both diagnosis and as a therapeutic target. Synchrotron radiation micro-computed tomography (SR-µCT) with a contrast agent of blood vessels has been used to analyze the bone vasculature both in healthy and in metastatic bone. However, few studies have investigated the local features of blood vessels around metastases so far. For this purpose, the metastases first need to be automatically segmented. This is a challenging task, however, since the metastases do not contribute a specific contrast to the three-dimensional (3D) SR-µCT images. Here, we propose a new method for the simultaneous segmentation of bone, blood vessels, and metastases from contrast enhanced 3D SR-µCT images based on the nnU-Net architecture. In this study, we showed that only minimal training data was required to achieve a high quality of segmentation. The proposed method allowed for the automatic segmentation of metastases and provided an improved segmentation of bone and blood vessels compared to previous methods while being much more efficient to apply once trained. Further, the automatic segmentation allowed for the measurement of vascular metastases interdistance and to restrict measurements to volumes of interest around the metastases. Finally, we quantitatively analyzed blood vessel parameters locally around metastases. This allowed for the demonstration that a combined anti-angiogenic treatment significantly decreased the volume and thickness of blood vessels close to metastases. The proposed method showed the capacity of the method to reveal new aspects of the blood vessel structure interaction with metastases. This could be further used to both define new targets for precocious detection of metastases as well as to study the kinetics of metastasis development in bone and the action of drugs on this process.

The Combination of Black Hat Transform and U-Net in Image Enhancement and Blood Vessel Segmentation in Retinal Images

Diabetic Retinopathy (DR) is a disorder of the eye caused by damage to blood vessels in the retina. Damage to the retinal blood vessels can be analyzed by segmenting the blood vessels on the image. This study proposes a combination of image enhancement and blood vessel segmentation in retinal images. Retinal image enhancement is carried out using the black hat transform method to obtain a detailed view of blood vessels in retinal images. Segmentation of blood vessels in retinal images is carried out using the U-Net architecture. The results of image enhancement are measured using MSE and PSNR. This study has an MSE value below 0.05 and a PSNR above 90dB. The MSE and PSNR values obtained show that the black hat transform method is very good at image enhancement. Segmentation has an accuracy value above 0.95 and a sensitivity value above 0.85. In addition, the specificity value and f1-score are above 0.8. This shows that the proposed stages of image enhancement and blood vessel segmentation are able to accurately recognize blood vessel features in retinal images.

Non-invasive evaluation of vascular architecture of focal liver lesions by micro vascular imaging.

To explore the value of vascular architecture detected by micro vascular imaging (MVI) in preoperative diagnosis of focal liver lesions (FLLs). In this retrospective study, patients with surgery and histopathologically proved or radiologically confirmed FLLs were included. Vascular architecture of FLLs were acquired by color Doppler flow imaging (CDFI) and MVI on LOGIQ™ E20 ultrasound machine (C1-6 convex array probes). Alder semiquantitative analysis (grade 0-3) and morphologic features of blood vessels (pattern a-f) were used to assess the blood flow within the FLLs. Interobserver agreement for evaluating blood flow of FLLs was analyzed. Using Adler's grading or morphologic patterns as diagnostic criteria for malignant FLLs, the diagnostic efficiency was analyzed and compared. From October 2021 and February 2022, 50 patients diagnosed with 40 malignant FLLs and 10 benign FLLs were finally included. The Kappa value within two observers for evaluating the blood flow of FLLs was 0.78 for MVI and 0.55 for CDFI. According to Alder semiquantitative analysis, more high-level blood flow signals (grade 2-3) were detected by MVI than CDFI (P < 0.05). Based on high-level blood flow signals (grade 2-3) and hypervascular supply patterns (pattern e and f), the diagnostic accuracy for malignant FLLs were 76% and 68% for MVI, 56% and 38% for CDFI, respectively. MVI is superior to CDFI in evaluating vascular architecture of FLLs. The high-level flow signals and hypervascular pattern detected by MVI have a useful and complementary value in preoperative non-invasive identification of malignant FLLs.

Glaucoma multi-classification using the novel syndrome mechanism-based dual-channel network

Glaucoma is the first irreversible blinding eye disease in the world, so early detection and diagnosis are the key to the treatment of glaucoma. Glaucoma can be divided into normal, mild, moderate, and severe according to the severity of the disease. To diagnose the severity of glaucoma more efficiently and accurately, this paper proposes a multi-classification method using the novel Glaucoma Syndrome Mechanism-based Dual-Channel network (GSM-DCN). First, glaucoma anatomy, i.e., the optic disc-optic cup (OD-OC), tissue, and blood vessel features are extracted according to the clinical knowledge. Then, combined with the glaucoma anatomy features and the glaucoma syndrome mechanism, the GSM-DCN is constructed and trained. Finally, the GSM-DCN is linked to Softmax to realize a multi-classification model of glaucoma. The proposed method is verified on the clinical dataset of Dalian NO.3 People's Hospital and public Drishti-GS1 dataset and the corresponding accuracy can reach 99% and 98.9%, respectively. The proposed method can reduce the possibility of early misdiagnosis and missed diagnosis of glaucoma, help doctors make more accurate judgment, design personalized treatment plan, and prevent patients from further impaired visual function.

A Minimalistic, Synthetic Cell‐Inspired Metamaterial for Enabling Reversible Strain‐Stiffening

AbstractStrain‐stiffening, i.e. the nonlinear stiffening of a material in response to a strain, is an intrinsic feature of many biological systems, including skin, blood vessels, and single cells. To avoid a mismatch in mechanical properties, synthetic materials in contact with such biological systems should also be strain‐stiffening. Conventional strain‐stiffening materials are either highly dependent on the applied strain‐rate, or only available for a limited stiffness regime. Both aspects limit the applicability of these materials. In contrast, living cells employ a dynamic strain‐stiffening mechanism that is based on the cross‐linking of cytoskeletal fibers in response to external stress. This strain‐stiffening of the cytoskeleton is mimicked in a mechanical metamaterial by a minimalistic structure consisting of parallel slats connected to backbones. Herein, it is demonstrated experimentally that the structures can be adapted such that the strain required for stiffening, the final stiffness, as well as the degree of stiffening can be tuned, particularly by combining several strain‐stiffening elements. These properties make the structure promising for the development of devices that should resemble the mechanical properties of human soft tissues, e.g., skin‐integrated flexible electronics and blood vessel grafts.

Diabetic Retinopathy and Diabetic Macular Edema Detection Using Ensemble Based Convolutional Neural Networks

Diabetic retinopathy (DR) and diabetic macular edema (DME) are forms of eye illness caused by diabetes that affects the blood vessels in the eyes, with the ground occupied by lesions of varied extent determining the disease burden. This is among the most common cause of visual impairment in the working population. Various factors have been discovered to play an important role in a person's growth of this condition. Among the essential elements at the top of the list are anxiety and long-term diabetes. If not detected early, this illness might result in permanent eyesight loss. The damage can be reduced or avoided if it is recognized ahead of time. Unfortunately, due to the time and arduous nature of the diagnosing process, it is harder to identify the prevalence of this condition. Skilled doctors manually review digital color images to look for damage produced by vascular anomalies, the most common complication of diabetic retinopathy. Even though this procedure is reasonably accurate, it is quite pricey. The delays highlight the necessity for diagnosis to be automated, which will have a considerable positive significant impact on the health sector. The use of AI in diagnosing the disease has yielded promising and dependable findings in recent years, which is the impetus for this publication. This article used ensemble convolutional neural network (ECNN) to diagnose DR and DME automatically, with accurate results of 99 percent. This result was achieved using preprocessing, blood vessel segmentation, feature extraction, and classification. For contrast enhancement, the Harris hawks optimization (HHO) technique is presented. Finally, the experiments were conducted for two kinds of datasets: IDRiR and Messidor for accuracy, precision, recall, F-score, computational time, and error rate.

MF2ResU-Net: a multi-feature fusion deep learning architecture for retinal blood vessel segmentation

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

Changes in arterial blood vessels and VEGF and Ang-1 expression in pregnant and non-pregnant yak uterine caruncle.

We investigated the structural features of arterial blood vessels in yak uterine caruncle and the effects of the expression of vascular regulation-related factors on angiogenesis in pregnant and non-pregnant yak uterus. Three-dimensional specimens of the uterine artery of non-pregnant and pregnant yaks were produced to observe and measure the distribution characteristics and number of arterial vessels in the uterus and caruncle in the two periods. The uterine caruncle structure was observed and analysed by haematoxylin-eosin staining. The expression features of vascular endothelial growth factor (VEGF) and angiopoietin-1 (Ang-1) in the uterine caruncle were detected with immunohistochemistry, quantitative real-time PCR (qRT-PCR) and western blotting. The length and number of blood vessels in the caruncle were increased, the degree of curvature was decreased, and the folding was more complicated during pregnancy as compared with that during non-pregnancy. The immunohistochemical results demonstrated that VEGF and Ang-1 were mainly expressed strongly in the mucosal epithelial cytoplasm. The glandular lumen of the uterine gland, lymphocytes and the media and adventitia of blood vessels are widely distributed, and they are all positive. VEGF and Ang-1 mRNA and protein levels were highest in pregnancy, followed by that in the luteal phase and in the follicular phase, and three stages were significantly different (p < .05). These findings provide an anatomical reference and theoretical basis for improving the diagnosis and treatment of yak reproductive disorders and other diseases in high-altitude and low-oxygen environments.

Intelligent Identification of Early Esophageal Cancer by Band-Selective Hyperspectral Imaging.

Simple SummaryEarly esophageal cancer detection is crucial for patient survival; however, even skilled endoscopists find it challenging to identify the cancer cells in the early stages. In order to categorize and identify esophageal cancer using a single shot multi-box detector, this research presents a novel approach integrating hyperspectral imaging by band selection and a deep learning diagnostic model. Based on the pathological characteristics of esophageal cancer, the pictures were categorized into three stages: normal, dysplasia, and squamous cell carcinoma. The findings revealed that mAP in WLIs, NBIs, and HSI pictures each achieved 80%, 85%, and 84%, respectively. The findings of this investigation demonstrated that HSI contains a greater number of spectral characteristics than white-light imaging, which increases accuracy by roughly 5% and complies with NBI predictions.In this study, the combination of hyperspectral imaging (HSI) technology and band selection was coupled with color reproduction. The white-light images (WLIs) were simulated as narrow-band endoscopic images (NBIs). As a result, the blood vessel features in the endoscopic image became more noticeable, and the prediction performance was improved. In addition, a single-shot multi-box detector model for predicting the stage and location of esophageal cancer was developed to evaluate the results. A total of 1780 esophageal cancer images, including 845 WLIs and 935 NBIs, were used in this study. The images were divided into three stages based on the pathological features of esophageal cancer: normal, dysplasia, and squamous cell carcinoma. The results showed that the mean average precision (mAP) reached 80% in WLIs, 85% in NBIs, and 84% in HSI images. This study′s results showed that HSI has more spectral features than white-light imagery, and it improves accuracy by about 5% and matches the results of NBI predictions.

MTPA_Unet: Multi-Scale Transformer-Position Attention Retinal Vessel Segmentation Network Joint Transformer and CNN.

Retinal vessel segmentation is extremely important for risk prediction and treatment of many major diseases. Therefore, accurate segmentation of blood vessel features from retinal images can help assist physicians in diagnosis and treatment. Convolutional neural networks are good at extracting local feature information, but the convolutional block receptive field is limited. Transformer, on the other hand, performs well in modeling long-distance dependencies. Therefore, in this paper, a new network model MTPA_Unet is designed from the perspective of extracting connections between local detailed features and making complements using long-distance dependency information, which is applied to the retinal vessel segmentation task. MTPA_Unet uses multi-resolution image input to enable the network to extract information at different levels. The proposed TPA module not only captures long-distance dependencies, but also focuses on the location information of the vessel pixels to facilitate capillary segmentation. The Transformer is combined with the convolutional neural network in a serial approach, and the original MSA module is replaced by the TPA module to achieve finer segmentation. Finally, the network model is evaluated and analyzed on three recognized retinal image datasets DRIVE, CHASE DB1, and STARE. The evaluation metrics were 0.9718, 0.9762, and 0.9773 for accuracy; 0.8410, 0.8437, and 0.8938 for sensitivity; and 0.8318, 0.8164, and 0.8557 for Dice coefficient. Compared with existing retinal image segmentation methods, the proposed method in this paper achieved better vessel segmentation in all of the publicly available fundus datasets tested performance and results.

Echoanatomical Features of the Major Cervical Blood Vessels of the Juvenile Green Sea Turtle (Chelonia mydas)

Although ultrasonographic examination of the blood vessels of sea turtles has been a helpful tool in the clinical setting, there is a paucity of data on the normal cervical echoanatomy of green turtles (Chelonia mydas); such information could be valuable for conservation-focused efforts at rehabilitation facilities. We studied the echoanatomical features of the major blood vessels of the neck of juvenile green turtles by gross dissection of 5 deceased turtles and by ultrasonographic examination of 11 healthy animals. The external jugular and the vertebral veins were superficial (< 1.5 cm) and presented an echogenic and turbulent pattern of blood flow in B-mode examination; carotid arteries lied deeply within the neck (> 1.5 cm) and exhibited a laminar blood flow characterized by a parabolic velocity profile as determined by Doppler sonography.

Cerebral Arterial Stenosis Detection Based on a Retained Two-Stage Detection Algorithm

Stroke is one of the fatal diseases worldwide, and its primary mechanism is produced by cerebrovascular stenosis, blockages, or embolisms. Computer-aided diagnosis can assist clinical practitioners in identifying cerebrovascular anomalies, elucidating the precise lesions’ location in the patients, and providing guidance for clinical therapy. Due to different portions of the cerebrovascular possessing diverse morphological properties and the limited narrow area, the detection effect is unsatisfactory. A retrained two-stage algorithm for detecting cerebral arterial stenosis in CTA images is proposed to solve these problems by further fusing image features and improving the quality of regions of interest. In Faster R-CNN and Libra R-CNN, the backbone network was Resnet50, with deformable convolutional and nonlocal neural networks introduced in the third, fourth, and fifth stages of the backbone network. Deformable convolutional networks learned offsets to extract morphological features of blood vessels in different tomographic planes. Nonlocal neural networks fused global information and extracted global features from location information of feature maps. A cascade detector refined object classification and bounding box regression before prediction. The experimental results show that the retained algorithm increases mAP by 7.3% and 7.5%, respectively, compared with Faster R-CNN and Libra R-CNN. Deformable convolutional networks, nonlocal neural networks, and cascade detectors are incorporated into further feature fusion; thus, semantic information about the cerebrovascular structure is learned, demonstrating more accurate stenotic region detection and demonstrating generalizability across different two-stage algorithms.

Vascular bifurcation influences the protein corona composition on nanoparticles and impacts their cellular uptake.

The protein corona (PC) that forms on nanoparticles (NPs) after in vivo injection influences their biodistribution, pharmacokinetics, and cell interaction. Although injected NPs traverse vascular networks, the impact of vascular features on the protein corona composition is mainly unexplored. Using an in vitro flow model that introduces bifurcations, a common feature of blood vessels, we show that vessels are not passive bystanders in the formation of the PC but that their features play active roles in defining the PC on NPs. The addition of bifurcation significantly increased the amount of proteins associated with NP. The bifurcation's introduction also changed the PC's composition on the NPs and affected the NP interactions with cells. Correlation analysis and modeling showed that these changes in the PC are mediated by both the branching and diameter reduction associated with vessel bifurcation and the resulting change in flow rate. The results indicate that blood vessel structures play an active part in the information of the PC, and their role should be studied critically for a better understanding of the PC and its biological implications.

Effect of hypoxia-inducible factors in tumor infiltrating macrophage on tumor growth

Tumor blood vessel structure is different from normal blood vessel features in terms of short lumen diameter, serpentine course and poor tight junction formation. These phenomena lead to form specific tissue environment, so called tumor microenvironments (TME). The TME polarizes tumor-infiltrating macrophages towards tumor supportive phenotype. We have previously reported that prolyl-hydroxylase inhibitor (PHDi) improved blood flow, hypoxia and TME in tumor tissues. The PHDi action mechanism is PHD inhibition, resulting in increasing hypoxia-inducing factors (HIFs) expression level. But the detail of its mechanism is unclear. In this study, we investigated the effect of HIFs in tumor infiltrating macrophage on tumor growth of PHD inhibitors on tumor progression.

Predicting the risk of rupture for vertebral aneurysm based on geometric features of blood vessels.

A significant proportion of the adult population worldwide suffers from cerebral aneurysms. If left untreated, aneurysms may rupture and lead to fatal massive internal bleeding. On the other hand, treatment of aneurysms also involve significant risks. It is desirable, therefore, to have an objective tool that can be used to predict the risk of rupture and assist in surgical decision for operating on the aneurysms. Currently, such decisions are made mostly based on medical expertise of the healthcare team. In this paper, we investigate the possibility of using machine learning algorithms to predict rupture risk of vertebral artery fusiform aneurysms based on geometric features of the blood vessels surrounding but excluding the aneurysm. For each of the aneurysm images (12 ruptured and 25 unruptured), the vessel is segmented into distal and proximal parts by cross-sectional area and 382 non-aneurysm-related geometric features extracted. The decision tree model using two of the features (standard deviation of eccentricity of proximal vessel, and diameter at the distal endpoint) achieved 83.8% classification accuracy. Additionally, with support vector machine and logistic regression, we also achieved 83.8% accuracy with another set of two features (ratio of mean curvature between distal and proximal parts, and diameter at the distal endpoint). Combining the aforementioned three features with integration of curvature of proximal vessel and also ratio of mean cross-sectional area between distal and proximal parts, these models achieve an impressive 94.6% accuracy. These results strongly suggest the usefulness of geometric features in predicting the risk of rupture.

Label-Free Detection of the Architectural Feature of Blood Vessels in Glioblastoma Based on Multiphoton Microscopy

Glioblastoma (GBM) is a highly angiogenesis malignant tumor with a significant heterogeneity of vascular morphology. The vascular patterns could be served as an indicator of vascular morphological complexity that associated with postoperative prognosis of patients with GBM. Here, multiphoton microscopy (MPM), based on second harmonic generation (SHG) and two-photon excited fluorescence (TPEF), is applied for detecting the architectural feature of blood vessels from ex vivo, unfixed, and unstained human GBM specimens. Combined with the image processing algorithms, the morphology, location, orientation, alignment, and density of vascular collagen are qualitatively and quantitatively visualized, revealing the presented method not only contribute to differentiate GBM from normal brain tissue, but also provide important indicators of different vascular patterns, which may serve as a reference to the prognosis more accurately. Therefore, these results can provide prognosis-related histopathological diagnosis of GBM, holding a translational potential to be used as a label-free, quick, and on-site imaging tool for clinicians to determine the extent of excision involving brain functional areas.

Automatic Artery/Vein Classification Using a Vessel-Constraint Network for Multicenter Fundus Images.

Retinal blood vessel morphological abnormalities are generally associated with cardiovascular, cerebrovascular, and systemic diseases, automatic artery/vein (A/V) classification is particularly important for medical image analysis and clinical decision making. However, the current method still has some limitations in A/V classification, especially the blood vessel edge and end error problems caused by the single scale and the blurred boundary of the A/V. To alleviate these problems, in this work, we propose a vessel-constraint network (VC-Net) that utilizes the information of vessel distribution and edge to enhance A/V classification, which is a high-precision A/V classification model based on data fusion. Particularly, the VC-Net introduces a vessel-constraint (VC) module that combines local and global vessel information to generate a weight map to constrain the A/V features, which suppresses the background-prone features and enhances the edge and end features of blood vessels. In addition, the VC-Net employs a multiscale feature (MSF) module to extract blood vessel information with different scales to improve the feature extraction capability and robustness of the model. And the VC-Net can get vessel segmentation results simultaneously. The proposed method is tested on publicly available fundus image datasets with different scales, namely, DRIVE, LES, and HRF, and validated on two newly created multicenter datasets: Tongren and Kailuan. We achieve a balance accuracy of 0.9554 and F1 scores of 0.7616 and 0.7971 for the arteries and veins, respectively, on the DRIVE dataset. The experimental results prove that the proposed model achieves competitive performance in A/V classification and vessel segmentation tasks compared with state-of-the-art methods. Finally, we test the Kailuan dataset with other trained fusion datasets, the results also show good robustness. To promote research in this area, the Tongren dataset and source code will be made publicly available. The dataset and code will be made available at https://github.com/huawang123/VC-Net.