Thin Vessels Research Articles

Dermoscopy of Gottron's papules and other inflammatory dermatoses involving the dorsa of the hands.

Several inflammatory dermatoses, including dermatomyositis (DM), may present as erythematous papules or plaques on the dorsal aspects of the hands over the joints. Limited skin involvement in these entities may pose a diagnostic challenge. (Video)dermoscopy is being utilized more frequently to aid in the differential diagnosis of inflammatory skin conditions. To describe the dermoscopic findings in Gottron's papules and compare them with dermoscopic features of other dermatoses involving the dorsal aspects of the hands. Videodermoscopic images from patients presenting with erythematous papules or plaques on the dorsal surface of the hands were retrospectively analysed for the presence of standardized dermoscopic parameters. Dermoscopic images from patients with DM (n = 12), psoriasis (n = 19), chronic dermatitis (n = 16), mycosis fungoides (n = 7), lichen planus (n = 5) and pityriasis rubra pilaris (n = 3) were included. Gottron's papules were characterized by pleomorphic vessels (dotted vessels accompanied by thick or thin linear vessels with branches or linear curved vessels) in 66.7% of cases, arranged in an unspecified pattern (91.7%), and accompanied by white or pink structureless areas (75.0%). Psoriatic plaques were characterized by dotted vessels arranged in a uniform pattern (94.7%). Vessels arranged in a ring pattern were nearly exclusively observed in psoriasis, while yellow structureless areas and erosions were more frequently present in chronic dermatitis. White lines, corresponding to Wickham striae, were specific for lichen planus. Videodermoscopy might be of value in differentiating Gottron's papules from other dermatoses involving dorsa of the hands.

Retinal Vessel Extraction via Assisted Multi-Channel Feature Map and U-Net.

Early detection of vessels from fundus images can effectively prevent the permanent retinal damages caused by retinopathies such as glaucoma, hyperextension, and diabetes. Concerning the red color of both retinal vessels and background and the vessel's morphological variations, the current vessel detection methodologies fail to segment thin vessels and discriminate them in the regions where permanent retinopathies mainly occur. This research aims to suggest a novel approach to take the benefit of both traditional template-matching methods with recent deep learning (DL) solutions. These two methods are combined in which the response of a Cauchy matched filter is used to replace the noisy red channel of the fundus images. Consequently, a U-shaped fully connected convolutional neural network (U-net) is employed to train end-to-end segmentation of pixels into vessel and background classes. Each preprocessed image is divided into several patches to provide enough training images and speed up the training per each instance. The DRIVE public database has been analyzed to test the proposed method, and metrics such as Accuracy, Precision, Sensitivity and Specificity have been measured for evaluation. The evaluation indicates that the average extraction accuracy of the proposed model is 0.9640 on the employed dataset.

3D Graph-Connectivity Constrained Network for Hepatic Vessel Segmentation.

Segmentation of hepatic vessels from 3D CT images is necessary for accurate diagnosis and preoperative planning for liver cancer. However, due to the low contrast and high noises of CT images, automatic hepatic vessel segmentation is a challenging task. Hepatic vessels are connected branches containing thick and thin blood vessels, showing an important structural characteristic or a prior: the connectivity of blood vessels. However, this is rarely applied in existing methods. In this paper, we segment hepatic vessels from 3D CT images by utilizing the connectivity prior. To this end, a graph neural network (GNN) used to describe the connectivity prior of hepatic vessels is integrated into a general convolutional neural network (CNN). Specifically, a graph attention network (GAT) is first used to model the graphical connectivity information of hepatic vessels, which can be trained with the vascular connectivity graph constructed directly from the ground truths. Second, the GAT is integrated with a lightweight 3D U-Net by an efficient mechanism called the plug-in mode, in which the GAT is incorporated into the U-Net as a multi-task branch and is only used to supervise the training procedure of the U-Net with the connectivity prior. The GAT will not be used in the inference stage, and thus will not increase the hardware and time costs of the inference stage compared with the U-Net. Therefore, hepatic vessel segmentation can be well improved in an efficient mode. Extensive experiments on two public datasets show that the proposed method is superior to related works in accuracy and connectivity of hepatic vessel segmentation.

Glioblastoma, IDH-Wild Type With FGFR3-TACC3 Fusion: When Morphology May Reliably Predict the Molecular Profile of a Tumor. A Case Report and Literature Review.

It has been reported that in-frame FGFR3-TACC3 fusions confer to glioblastomas, IDH-wild type (GBMs, IDHwt) some unusual morphologic features, including monomorphous rounded cells with ovoid nuclei, nuclear palisading, endocrinoid network of “chicken-wire” vessels, microcalcifications and desmoplastic stroma, whose observation may predict the molecular profile of the tumor. We herein present a case of recurrent GBMs, IDHwt, exhibiting some of the above-mentioned morphological features and a molecularly-proven FGFR3-TACC3 fusion. A 56-year-old man presented to our hospital for a recurrent GBM, IDHwt, surgically treated at another center. Histologically, the tumor, in addition to the conventional GBM morphology, exhibited the following peculiar morphologic features: (1) monomorphous neoplastic cells with rounded nuclei and scant pale cytoplasm; (2) thin capillary-like vessels with “chicken-wire” pattern; (3) nuclear palisading; (4) formation of vague perivascular pseudorosettes; (5) spindled tumor cells embedded in a loose, myxoid background. Based on this unusual morphology, molecular analyses were performed and an FGFR3 exon17-TACC3 exon 10 fusion was found. The present case contributes to widening the morphologic spectrum of FGFR3-TACC3-fused GBM, IDHwt and emphasizes that pathologists, in the presence of a GBM, IDHwt with unconventional morphology, should promptly search for this fusion gene.

Bridge-Net: Context-involved U-net with patch-based loss weight mapping for retinal blood vessel segmentation

Retinal blood vessel segmentation in fundus images plays an important role in the early diagnosis and treatment of retinal diseases. In recent years, the segmentation methods based on deep neural networks have attracted the attention of experts and scholars. However, due to the complexity of the distribution of blood vessels in fundus images and the imbalance between blood vessels and background, retinal blood vessel segmentation remains challenging. In this paper, we present a retinal blood vessel segmentation method using deep neural networks. Firstly, we propose a novel deep network architecture named Bridge-net to make use of the context of the retinal blood vessels efficiently. Specifically, the architecture incorporates a recurrent neural network (RNN) into a convolutional neural network (CNN) to deliver the context and then to produce the probability map of the retinal blood vessels. Secondly, we propose a patch-based loss weight mapping by considering the distributions of different types of blood vessels to correct the imbalance, since there are large morphological differences between thick and thin blood vessels. Finally, we evaluate our method on three publicly datasets STARE, DRIVE, and CHASE_DB1, and compare the results to eighteen state-of-the-art approaches. We also compare our method with some existing approaches on a high-resolution dataset, i.e., HRF. The results show that our method achieves better/comparable performances when compared to the existing approaches. The results on various datasets also verify the effectiveness and stability of the proposed method.

An active contour model using matched filter and Hessian matrix for retinal vessels segmentation

Medical image analysis, especially of the retina, plays an important role in diagnostic decision support tools. The properties of retinal blood vessels are used for disease diagnoses such as diabetes, glaucoma, and hypertension. There are some challenges in the utilization of retinal blood vessel patterns such as low contrast and intensity inhomogeneities. Thus, an automatic algorithm for vessel extraction is required. Active contour is a strong method for edge extraction. However, it cannot extract thin vessels and ridges very well. In this research, we propose an improved active contour method that uses discrete wavelet transform for energy minimization to solve this problem. The minimization formula terminates segmentation into two regions, foreground and background. We found out that foreground pixels are more important than background. Therefore, we change the minimization formulation in such a way that gives more weight to the foreground. The contour edge has orientation in each region. The wavelet terms in the minimization formula help to detect edge direction in horizontal, vertical, and diagonal orientations. Since bright and dark lesions do not have direction, these terms can decrease false vessel detection. The second part of the innovation is called the optimization process, which works instead of reinitialization. Sometimes, the evolution in the iterated process destroys the stability of the evolution. To prevent the destruction of the stability of evolution, we used an optimization process formula whose task is to keep contour on the edges of the image. The performance of the proposed algorithms is compared and analyzed on five databases. The values achieved are 94.3%, 73.36%, and 97.41% for accuracy, sensitivity, and specificity, respectively, on the DRIVE dataset, and the proposed algorithm is comparable to the state-of-the-art approaches.

A Critical Review of Dhamani Sharir in the Modern Perspective

Ayurveda is a treasure trove of information developed and discovered by our forefathers. To fully comprehend and apply the concept of dhamani sharir, we must first understand Sharira. For students of any system of medicine, understanding of Rachana Sharira (anatomy) is required. Srotas, Siras, and Dhamani are terms from the Vedas. The terms Siras and Dhamani is referred to blood vessels in general. However, according to commentators, Dhamani is a thick blood vessel connecting to the heart, and sira is a thin blood vessel. According to Sushruta, ten Dhamani spread upward, ten downward, and four sideward emerging from the nabhi According to Charak, hridaya produces ten Dhamani. Dhamanis (arteries) described in Ayurveda represent a tubular channel taking origin from the Hridaya(heart) and possess the characteristics of pulsation and circulation of Rasa (lymph chyle or plasma) and Rakta (blood) throughout the body. The up-coursing Dhamani prefers to maintain the body's integrity by performing particular body functions such as sound, touch, taste, smell, sneezing, laughter, speech, and so on. The Dhamanis that come down establish a pathway for Vata, urine, excrement, semen, and contained food to flow downward. The Tiryaggami-Dhamani can be taken as the cutaneous or peripheral vessels supplying the superficial and deep layers of the skin. This essay will assist in learning more about Dhamanis through ancient science.

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

The accurate segmentation of retinal vessels is a challenging task due to the presence of various pathologies as well as the low-contrast of thin vessels and non-uniform illumination. In recent years, encoder-decoder networks have achieved outstanding performance in retinal vessel segmentation at the cost of high computational complexity. To address the aforementioned challenges and to reduce the computational complexity, we propose a lightweight convolutional neural network (CNN)-based encoder-decoder deep learning model for accurate retinal vessels segmentation. The proposed deep learning model consists of encoder-decoder architecture along with bottleneck layers that consist of depth-wise squeezing, followed by full-convolution, and finally depth-wise stretching. The inspiration for the proposed model is taken from the recently developed Anam-Net model, which was tested on CT images for COVID-19 identification. For our lightweight model, we used a stack of two 3 × 3 convolution layers (without spatial pooling in between) instead of a single 3 × 3 convolution layer as proposed in Anam-Net to increase the receptive field and to reduce the trainable parameters. The proposed method includes fewer filters in all convolutional layers than the original Anam-Net and does not have an increasing number of filters for decreasing resolution. These modifications do not compromise on the segmentation accuracy, but they do make the architecture significantly lighter in terms of the number of trainable parameters and computation time. The proposed architecture has comparatively fewer parameters (1.01M) than Anam-Net (4.47M), U-Net (31.05M), SegNet (29.50M), and most of the other recent works. The proposed model does not require any problem-specific pre- or post-processing, nor does it rely on handcrafted features. In addition, the attribute of being efficient in terms of segmentation accuracy as well as lightweight makes the proposed method a suitable candidate to be used in the screening platforms at the point of care. We evaluated our proposed model on open-access datasets namely, DRIVE, STARE, and CHASE_DB. The experimental results show that the proposed model outperforms several state-of-the-art methods, such as U-Net and its variants, fully convolutional network (FCN), SegNet, CCNet, ResWNet, residual connection-based encoder-decoder network (RCED-Net), and scale-space approx. network (SSANet) in terms of {dice coefficient, sensitivity (SN), accuracy (ACC), and the area under the ROC curve (AUC)} with the scores of {0.8184, 0.8561, 0.9669, and 0.9868} on the DRIVE dataset, the scores of {0.8233, 0.8581, 0.9726, and 0.9901} on the STARE dataset, and the scores of {0.8138, 0.8604, 0.9752, and 0.9906} on the CHASE_DB dataset. Additionally, we perform cross-training experiments on the DRIVE and STARE datasets. The result of this experiment indicates the generalization ability and robustness of the proposed model.

Learning based multi-scale feature fusion for retinal blood vessels segmentation

Many eye-related diseases will lead to blindness or worse when it is lack of treatment in the early stages of the disease. Retinal vessel is important for doctors to detect eye diseases, even though the increase of some thin vessels may also mean the occurrence of certain diseases. Therefore, automatic retinal vessel segmentation is of great help to doctors in diagnosing diseases. In this paper, an automatic vessel segmentation method is proposed for retinal image, which is based on support vector machine combining multi-scale feature fusion model and B-COSFIRE filter response. Firstly, the inverted green channel image is enhanced by B-COSFIRE filter to strengthen bar-like vessel structures. Then the features are extracted by means of line operator in a multiresolution way, namely that each filtered image is down-sampled to cover a wider area, hence each sampled pixels can obtain not only the global but also local information. Then the final obtained features from three scales together along the depth direction are combined to train the SVM model. Finally, we use the classifier model to predict blood vessels. The proposed algorithm is evaluated on the public available fundus images datasets (DRIVE: Precision = 0.8657, Se = 0.7088, Sp = 0.9660 and ACC = 0.9900; STARE: Precision = 0.8782, Se = 0.6189, Sp = 0.9908 and ACC = 0.9494). The experiment results show that our proposed algorithm has effects on retinal vessels segmentation.

Gyrus Rectus Cavernoma Masquerading as an Intracranial Aneurysm: A Case Report and Review of Literature

A cerebral cavernous malformation [CCM] is a cluster of abnormally thin and dilated blood vessels. In rare instances, diagnosis can be clouded by the possibility of an intracranial aneurysm. In this paper, we report a case of CCM that was initially misdiagnosed as intracranial aneurysm. We conduct a review of the literature on similar cases.

Pyramid-Net: Intra-layer Pyramid-Scale Feature Aggregation Network for Retinal Vessel Segmentation.

Retinal vessel segmentation plays an important role in the diagnosis of eye-related diseases and biomarkers discovery. Existing works perform multi-scale feature aggregation in an inter-layer manner, namely inter-layer feature aggregation. However, such an approach only fuses features at either a lower scale or a higher scale, which may result in a limited segmentation performance, especially on thin vessels. This discovery motivates us to fuse multi-scale features in each layer, intra-layer feature aggregation, to mitigate the problem. Therefore, in this paper, we propose Pyramid-Net for accurate retinal vessel segmentation, which features intra-layer pyramid-scale aggregation blocks (IPABs). At each layer, IPABs generate two associated branches at a higher scale and a lower scale, respectively, and the two with the main branch at the current scale operate in a pyramid-scale manner. Three further enhancements including pyramid inputs enhancement, deep pyramid supervision, and pyramid skip connections are proposed to boost the performance. We have evaluated Pyramid-Net on three public retinal fundus photography datasets (DRIVE, STARE, and CHASE-DB1). The experimental results show that Pyramid-Net can effectively improve the segmentation performance especially on thin vessels, and outperforms the current state-of-the-art methods on all the adopted three datasets. In addition, our method is more efficient than existing methods with a large reduction in computational cost. We have released the source code at https://github.com/JerRuy/Pyramid-Net.

Hybrid UNet Architecture based on Residual Learning of Fundus Images for Retinal Vessel Segmentation

This paper deals with the new segmentation techniques for retinal blood vessels on fundus images. This technique aims at extracting thin vessels to reduce the intensity difference between thick and thin vessels. This paper proposes the modified UNet model by incorporating ResNet blocks into it which includes structured prediction. In this work we generate the visualization of blood vessels from retinal fundus image for two loss functions namely cross entropy loss and Dice loss where the network classifies several pixels simultaneously. The results shows higher accuracy by considering a much more expressive UNet algorithm and outperforms the past algorithms for Retinal Vessel Segmentation. The benefits of this approach will be demonstrated empirically.

Deep Att-ResGAN: A Retinal Vessel Segmentation Network for Color Fundus Images

Retinal vessel segmentation plays a significant role in the diagnosis and treatment of ophthalmological diseases. Recent studies have proved that deep learning can effectively segment the retinal vessel structure. However, the existing methods have difficulty in segmenting thin vessels, especially when the original image contains lesions. Based on generative adversarial network (GAN), this paper proposes a deep network with residual module and attention module (Deep Att-ResGAN). The network consists of four identical subnetworks. The output of each subnetwork is imported to the next subnetwork as contextual features that guide the segmentation. Firstly, the problems of the original image, namely, low contrast, uneven illumination, and data insufficiency, were solved through image enhancement and preprocessing. Next, an improved U-Net was adopted to serve as the generator, which stacks the residual and attention modules. These modules optimize the weight of the generator, and enhance the generalizability of the network. Further, the segmentation was refined iteratively by the discriminator, which contributes to the performance of vessel segmentation. Finally, comparative experiments were carried out on two public datasets: Digital Retinal Images for Vessel Extraction (DRIVE) and Structured Analysis of the Retina (STARE). The experimental results show that Deep Att-ResGAN outperformed the equivalent models like U-Net and GAN in most metrics. Our network achieved accuracy of 0.9565 and F1 of 0.829 on DRIVE, and accuracy of 0.9690 and F1 of 0.841 on STARE.

A Hybrid Method to Enhance Thick and Thin Vessels for Blood Vessel Segmentation.

Retinal blood vessels have been presented to contribute confirmation with regard to tortuosity, branching angles, or change in diameter as a result of ophthalmic disease. Although many enhancement filters are extensively utilized, the Jerman filter responds quite effectively at vessels, edges, and bifurcations and improves the visualization of structures. In contrast, curvelet transform is specifically designed to associate scale with orientation and can be used to recover from noisy data by curvelet shrinkage. This paper describes a method to improve the performance of curvelet transform further. A distinctive fusion of curvelet transform and the Jerman filter is presented for retinal blood vessel segmentation. Mean-C thresholding is employed for the segmentation purpose. The suggested method achieves average accuracies of 0.9600 and 0.9559 for DRIVE and CHASE_DB1, respectively. Simulation results establish a better performance and faster implementation of the suggested scheme in comparison with similar approaches seen in the literature.

EP.FRI.988Life threatening recurrent bleeding gastric fundus Dieulafoy lesion: A case report

Abstract Introduction Dieulafoy lesion is a rare but significant cause of upper gastrointestinal tract (GIT) bleeding. Over 75% of Dieulafoy lesions are located in the stomach and they tend to be responsible for recurrent upper GIT bleeding. Endoscopic therapy is the first line intervention to achieve haemostasis. Patient A 49-year old normally fit man known to have a gastric Dieulafoy lesion since 2008 presented with a history of collapse on the street and significant melaena. He was tachycardic, with a heart rate of 116, and hypotensive, blood pressure 109/68 mmHg on admission. He had significant upper GIT bleeding from the gastric fundus Dieulafoy lesion in April 2008, requiring a massive blood transfusion. At the time, the attempted endoscopic therapy was unsuccessful, resulting in an emergency surgery and under-running of the bleeding vessels. For the recent admission, he underwent an urgent therapeutic oesophagogastroduodenoscopy, with 3 endoscopic clips applied, but this failed to maintain haemostasis. Four units of packed red cell were transfused and he was transferred immediately to the operating theatre. He underwent an emergency laparotomy, adhesiolysis, gastrostomy and wedge resection of the bleeding gastric fundus Dieulafoy lesion using a linear cutter 75mm stapler. He had an uneventful post-operative recovery and was discharged home on day four after surgery. The histology of the wedged gastric specimen confirmed an area of gastric mucosa ulceration with a network of mixed dilated, thin and thick-walled tortuous vessels in the adjacent submucosal layer. The histologic features are consistent with a bleeding gastric Dieulafoy lesion.

Multi-path cascaded U-net for vessel segmentation from fundus fluorescein angiography sequential images

Background and ObjectiveFundus fluorescein angiography (FFA) technique is widely used in the examination of retinal diseases. In analysis of FFA sequential images, accurate vessel segmentation is a prerequisite for quantification of vascular morphology. Current vessel segmentation methods concentrate mainly on color fundus images and they are limited in processing FFA sequential images with varying background and vessels. MethodsWe proposed a multi-path cascaded U-net (MCU-net) architecture for vessel segmentation in FFA sequential images, which is capable of integrating vessel features from different image modes to improve segmentation accuracy. Firstly, two modes of synthetic FFA images that enhance details of small vessels and large vessels are prepared, and are then used together with the raw FFA image as inputs of the MCU-net. By fusion of vessel features from the three modes of FFA images, a vascular probability map is generated as output of MCU-net. ResultsThe proposed MCU-net was trained and tested on the public Duke dataset and our own dataset for FFA sequential images as well as on the DRIVE dataset for color fundus images. Results show that MCU-net outperforms current state-of-the-art methods in terms of F1-score, sensitivity and accuracy, and is able of reserving details such as thin vessels and vascular connections. It also shows good robustness in processing FFA images captured at different perfusion stages. ConclusionsThe proposed method can segment vessels from FFA sequential images with high accuracy and shows good robustness to FFA images in different perfusion stages. This method has potential applications in quantitative analysis of vascular morphology in FFA sequential images.

An old problem in a new light: Elemental and lead isotopic analysis of Luristan Bronzes

The emergence and provenance of the Luristan Bronzes has been a subject of interest for many decades. This paper presents the results of elemental and lead isotopic analysis of a series of Luristan Bronzes discovered from recent excavations in the Sangtarashan sanctuary, as well as an extensive comparative study on technology and provenance of the Luristan Bronzes. This study was performed in order to better understand tin bronze production technology in the Luristan region during the Iron Age. It focuses on the artefacts themselves, as no mining or production evidence has been discovered in Luristan so far. For this purpose, 46 samples from different pieces of thin sheet vessels from Sangtarashan were analysed by inductively coupled plasma-optical emission spectroscopy (ICP-OES) for their elemental composition and by multi-collector inductively coupled plasma-mass spectroscopy (MC-ICP-MS) for their lead isotopic composition. The results of elemental analysis showed that tin bronze with variable tin content was used to produce these artefacts. The comparative study of the alloy composition also shows that tin bronze may have been the main material to produce ritual artefacts during the Iron Age of western Iran. Furthermore, the lead isotope ratios of the Sangtarashan artefacts partially overlap with those of different copper ore deposits on the Iranian Plateau, including deposits close to Luristan (such as Deh Hosein) and ore deposits further away, in central and eastern Iran. In fact, the results revealed that it is not possible at this stage in the research to identify one specific ore deposit or region as the source of copper for tin bronze metallurgy during the Iron Age of Luristan. Thus, the research suggests that ancient metalworkers apparently used different copper sources to produce the bronze artefacts specific to the region of Luristan in western Iran.

A Multichannel Deep Neural Network for Retina Vessel Segmentation via a Fusion Mechanism.

Changes in fundus blood vessels reflect the occurrence of eye diseases, and from this, we can explore other physical diseases that cause fundus lesions, such as diabetes and hypertension complication. However, the existing computational methods lack high efficiency and precision segmentation for the vascular ends and thin retina vessels. It is important to construct a reliable and quantitative automatic diagnostic method for improving the diagnosis efficiency. In this study, we propose a multichannel deep neural network for retina vessel segmentation. First, we apply U-net on original and thin (or thick) vessels for multi-objective optimization for purposively training thick and thin vessels. Then, we design a specific fusion mechanism for combining three kinds of prediction probability maps into a final binary segmentation map. Experiments show that our method can effectively improve the segmentation performances of thin blood vessels and vascular ends. It outperforms many current excellent vessel segmentation methods on three public datasets. In particular, it is pretty impressive that we achieve the best F1-score of 0.8247 on the DRIVE dataset and 0.8239 on the STARE dataset. The findings of this study have the potential for the application in an automated retinal image analysis, and it may provide a new, general, and high-performance computing framework for image segmentation.

Cavernous hemangioma of tongue - A rare case report

Hemangiomas are the developmental vascular abnormalities, out of which more than 50% occur in the head and neck region, especially on buccal mucosa, lips, tongue, and palate. Cavernous hemangiomas are characterised by irregular, deep, dermal blood-filled channels having tangles of thin walled cavernous vessels or sinusoids, separated by a scanty connective tissue stroma. The present case report is a case of cavernous hemangioma present on the tongue in a female patient.

Accurate Retinal Vessel Segmentation in Color Fundus Images via Fully Attention-Based Networks.

Automatic retinal vessel segmentation is important for the diagnosis and prevention of ophthalmic diseases. The existing deep learning retinal vessel segmentation models always treat each pixel equally. However, the multi-scale vessel structure is a vital factor affecting the segmentation results, especially in thin vessels. To address this crucial gap, we propose a novel Fully Attention-based Network (FANet) based on attention mechanisms to adaptively learn rich feature representation and aggregate the multi-scale information. Specifically, the framework consists of the image pre-processing procedure and the semantic segmentation networks. Green channel extraction (GE) and contrast limited adaptive histogram equalization (CLAHE) are employed as pre-processing to enhance the texture and contrast of retinal blood images. Besides, the network combines two types of attention modules with the U-Net. We propose a lightweight dual-direction attention block to model global dependencies and reduce intra-class inconsistencies, in which the weights of feature maps are updated based on the semantic correlation between pixels. The dual-direction attention block utilizes horizontal and vertical pooling operations to produce the attention map. In this way, the network aggregates global contextual information from semantic-closer regions or a series of pixels belonging to the same object category. Meanwhile, we adopt the selective kernel (SK) unit to replace the standard convolution for obtaining multi-scale features of different receptive field sizes generated by soft attention. Furthermore, we demonstrate that the proposed model can effectively identify irregular, noisy, and multi-scale retinal vessels. The abundant experiments on DRIVE, STARE, and CHASE_DB1 datasets show that our method achieves state-of-the-art performance.