Search

Segmentation of hepatic vessels from 3D CT images is necessary for accurate diagnosis and preoper-ative 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 neu-ral 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.

This paper substantially advances upon state-of-the-art to enhance liver vessels segmentation accuracy by leveraging advantages of synthetic PET-CT (SPET-CT) images in addition to computed tomography angiography (CTA) volumes. Our setup makes a hybrid solution of modified GAN-cAED combining synthetic ability of generative adversarial network (GAN) to deliver SPET-CT images with generative ability of convolutional autoencoder (cAED) network in terms of latent learning to more refined segmentation of major liver vessels. We improve time complexity through a novel concept of controlled segmentation by introducing a threshold metric to stop segmentation up-to a desired level. The innovative concept of controlled vessel segmentation with a stopping criterion via variant threshold levels will help surgeons to avoid unintentional major blood vessels cutting, reducing the risk of excessive blood loss. Clinically, such solutions offer computer-aided liver surgeries and drug treatment evaluation in a CTA-only environment, shorten the requirement of radioactive and expensive fused PET-CT images.

In this section, a various levelled picture matting method is utilized to extract veins from fundus pictures. All the more explicitly, a various levelled methodology is joined into the picture matting strategy for vein apportioning. For the most part, the matting strategy requires a client indicated tri map, which isolates the info picture into three districts: the frontal area, foundation, and obscure areas. Be that as it may, producing a client indicated tri map is very tuff work for vessel parcelling undertakings. In this task, we propose a technique that creates tri map consequently by using area highlights of veins. At that point, we apply a various levelled picture tangling strategy to separate the vessel components in the obscure districts. The suggested technique has less count time and performs better than numerous other regulated and solo strategies. The datasets CHASE_DB1, STARE and DRIVE are adopted as these datasets are available openly. By applying these three datasets on pictures produces fixed time of 50.71, 15.74 and 10.72 s with optimized parcelling exactness 93.9%, 94.6% and 95.1%, respectively.

Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.

High-precision segmentation of fundus vessels is a fundamental step in the diagnosis and treatment of fundus diseases, in which both thick and thin vessels are important features for symptom detection. With the rapid development of artificial intelligence, the deep convolutional neural network (DCNN) has been widely applied into image analysis of fundus vessels. Nevertheless, due to the imbalanced ratio between thick and thin vessels, the existing segmentation methods are weak in the task of microvessel extraction from fundus images. To address this problem, this paper proposes a new hybrid deep image segmentation method for fundus vessels that consists of a multitask segmentation network and a fusion network. For the proposed method, a multitask segmentation network is developed to precisely segment both thick vessels and thin vessels from fundus images separately. In addition, an effective loss function is designed to adapt to the two different vessel segmentation tasks and ultimately solve the imbalanced ratio between these two vessels. Furthermore, an improved U-net network model is proposed to serve as the basic segmentation network to ensure the segmentation performance of the multitask segmentation network. Together with these networks, a fusion network is also proposed to fuse these two kinds of blood vessels to obtain the fusion images as the final segmentation results of fundus vessels. The proposed segmentation method is validated on many different public data sets of fundus images, such as DRIVE, STARE and CHASE_DB1. Experimental results show that the proposed method obtains a better segmentation performance on fundus images and acquires a higher recall, F_1 value, and accuracy than other advanced segmentation methods.

Purpose: Registration of Laparoscopic Ultrasound (LUS) to a pre-operative scan such as Computed Tomography (CT) using blood vessel information has been proposed as a method to enable image-guidance for laparoscopic liver resection. Currently, there are solutions for this problem that can potentially enable clinical translation by bypassing the need for a manual initialisation and tracking information. However, no reliable framework for the segmentation of vessels in 2D untracked LUS images has been presented. Methods: We propose the use of 2D UNet for the segmentation of liver vessels in 2D LUS images. We integrate these results in a previously developed registration method, and show the feasibility of a fully automatic initialisation to the LUS to CT registration problem without a tracking device. Results: We validate our segmentation using LUS data from 6 patients. We test multiple models by placing patient datasets into different combinations of training, testing and hold-out, and obtain mean Dice scores ranging from 0.543 to 0.706. Using these segmentations, we obtain registration accuracies between 6.3 and 16.6 mm in 50% of cases. Conclusions: We demonstrate the first instance of deep learning (DL) for the segmentation of liver vessels in LUS. Our results show the feasibility of UNet in detecting multiple vessel instances in 2D LUS images, and potentially automating a LUS to CT registration pipeline.

Objective: The objective is to provide a precise segmentation technique based on ACRF which can handle the variations between major and minor vessels and reduces the interference present in the model due to over fitting and can provide a high-quality reconstructed image. Therefore, a robust method with statistical properties needs to be presented to enhance the performance of the model. Moreover, a statistical framework is required to classify images precisely. Methods: Adaptive Conditional Random Field (ACRF) model to detect DR disease in early stages. Here, major vessel potentials and minor vessel potential features are extracted which in precise segmentation of vessel and non-vessel regions. This feature enhances the efficiency of the model. These major vessel and minor vessel potential features rebuild the retinal vasculature parts precisely and help to capture the contextual information present in the ground truth and label images. This method utilizes an ACRF model to reduce interference and computation complexity. Here, two efficient features are extracted to segment fundus images efficiently such as major vessel potentials and minor vessel potentials. The proposed ACRF model can provide the design patterns for both input images and labels with the help of major vessel potentials, unlike state-of-art-techniques which provide patterns for only labels and model the contextual information only in labels which is very essential while performing vessel segmentation Results: The performance results are tested on the DRIVE dataset. Experimental results verify the superiority of the proposed vessel segmentation technique based on the ACRF model in terms of accuracy, sensitivity, specificity, and F1measure and segmentation quality. Conclusion: A highly efficient vessel segmentation technique is evaluated to describe major and minor vessel regions efficiently based on the ACRF to recognize DR in early stages and to ensure an effective diagnosis using eye fundus images. The segmentation process decomposes input images into RGB components through histogram labels based on the proposed ACRF model. Here, the Gabor filtering approach is used for pre-processing and predicting parameters. The proposed segmentation method can provide the smooth boundaries of minor and major vessel regions. The proposed ACRF model can provide the design patterns for both input images and labels with the help of major vessel potentials, unlike state-of-art-techniques which provide patterns for only labels and model the contextual information only in labels.

Objectives The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels. Methods The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the tri-DWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Rate-based Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy. Results The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB. Conclusions The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.

This paper aims to develop a technique of vessel segmentation in retinal images. Interpreting the segmented vessels is necessary for the automatic detection of the severe stage of the diabetic retinopathy. Thus, it is important to have the technique for segmenting vessels in an automatic way with high performance, for the sake of further analysis. In this paper, the proposed method is developed based on the double layer combining supervised and non-supervised learning aspects. The first layer is to detect the initial seeds of vessels using the supervised learning. It learns based on three types of features including green intensity, line operators, and Gabor filters. Then, the support vector machine (SVM) is applied as the classification tool. In the second layer, the segmentation results from the first layer is further revised and completed using the non-supervised learning. The morphological operations with the watershed technique are applied on the results obtained from the first layer, to remain with the segmented pixels with high confidential to be vessels. Then, these pixels are used as the initial seeds of foreground in the iterative graph cut. As the result, the more completed and comprehensive foreground (i.e. vessels) can be obtained. The proposed method is evaluated using two well-known datasets including DRIVE and STARE. The experimental results show the promising performance of the proposed method when compared with other existing methods in the literature.

Conventional machine learning-based methods have been effective in assisting physicians in making accurate decisions and utilized in computer-aided diagnosis for more than 30 years. Recently, deep learning-based methods, and convolutional neural networks in particular, have rapidly become preferred options in medical image analysis because of their state-of-the-art performance. However, the performances of conventional and deep learning-based methods cannot be compared reliably because of their evaluations on different datasets. Hence, we developed both conventional and deep learning-based methods for lung vessel segmentation and chest radiograph registration, and subsequently compared their performances on the same datasets. The results strongly indicated the superiority of deep learning-based methods over their conventional counterparts.

Automatic fovea localization is a challenging issue. In this article, we focus on the study of fovea localization and propose a robust fovea localization method. We propose concentric circular sectional symmetry measure (CCSSM) for symmetry axis detection, and region of interest (ROI) determination, which is a global feature descriptor robust against local feature changes, to solve the lesion interference issue, i.e., fovea visibility interference from lesions, using both structure features and morphological features. We propose the index of convexity and concavity (ICC) as the convexity-concavity measure of the surface and provide a quantitative evaluation tool for ophthalmologists to learn whether the occurrence of lesion within the ROI. We propose the weighted gradient accumulation map, which is insensitive to local intensity changes and can overcome the influence of noise and contamination, to perform refined localization. The advantages of the proposed method lies in two aspects. First, the accuracy and robustness can be achieved without typical sophisticated manner, i.e., blood vessel segmentation and parabola fitting. Second, the lesion interference is considered in our plan of fovea localization. Our proposed symmetry-based method is innovative in the solution of fovea detection, and it is simple, practical, and controllable. Experiment results show that the proposed method can resist the interference of unbalanced illumination and lesions, and achieve high accuracy rate in five datasets. Compared to the state-of-the-art methods, high robustness and accuracy of the proposed method guarantees its reliability.

Objective: To facilitate the analysis and diagnosis of X-ray coronary angiography in interventional surgery, it is necessary to extract vessel from X-ray coronary angiography. However, vessel images of angiography suffer from low quality with large artefacts, which challenges the existing vascular technology. Methods: In this paper, we propose a avessel framework to detect vessels and segment vessels in angiographic vessel data. In this framework, we develop a new matrix decomposition model with gradient sparse in the tensor representation. Then, the energy function with the input of the hierarchical vessel is used in vessel detection and vessel segmentation. Results: Through experiments conducted on angiographic data, we have demonstrated the good performance of the proposed method in removing background structure. Conclusion: We evaluated our method for vessel detection and segmentation in different clinical settings, including LAO/RAO with cranial and caudal angulation, and showed its competitive results compared with eight state-of-the-art methods in terms of extensive qualitative and quantitative evaluation. Significance: Our method can remove a large number of background artefacts and obtain a better vascular structure, which has contributed to the clinical diagnosis of coronary artery diseases.

Analysis of microcirculation is an important clinical and research task. Functional analysis of the microcirculation allows researchers to understand how blood flowing in a tissues’ smallest vessels affects disease progression, organ function, and overall health. Current methods of manual analysis of microcirculation are tedious and time-consuming, limiting the quick turnover of results. There has been limited research on automating functional analysis of microcirculation. As such, in this paper, we propose a two-step machine-learning-based algorithm to functionally assess microcirculation videos. The first step uses a modified vessel segmentation algorithm to extract the location of vessel-like structures. While the second step uses a 3D-CNN to assess whether the vessel-like structures contained flowing blood. To our knowledge, this is the first application of machine learning for functional analysis of microcirculation. We use real-world labelled microcirculation videos to train and test our algorithm and assess its performance. More precisely, we demonstrate that our two-step algorithm can efficiently analyze real data with high accuracy (90%).

Biomedical imaging has helped the medical practitioners to facilitate treatments faster and more accurate than conventional methods. Automated technologies suffice the default preprocessing and ide...

Background and objective: The analysis of retinal vessels in fundus images is vital in the diagnosis of retinal diseases and early diagnosis of chronic vascular diseases and diabetes. Automatic vessel segmentation relies on costly expert annotations that may have limitations in the level of detail. We develop an automatic method to generate highly-accurate vessel segmentation including fine-scale vessels. Methods: We present a new framework for fine-scale vessel segmentation from fundus images through registration and segmentation of corresponding fluorescein angiography (FA) images. We first register and aggregate the extracted vessels highlighted from the fluorescent dye in the FA frames. This FA vessel mask is then registered to the fundus image based on an initial fundus vessel mask. Post-processing is performed to refine the final vessel mask. Registration of the FA frames, and registration of FA vessel mask to the fundus image, are performed by similar coarse-to-fine hierarchical frameworks comprising both projective and deformable registration. Two convolutional neural networks with identical network structures, both trained on public datasets but with different configurations, are used for vessel segmentation of both the FA frames and the fundus images. Results: Qualitative examples support the robustness and accuracy of the proposed method. Quantitative evaluations, including the area-under-curve (AUC) of the receiver operating characteristic (ROC) curve are presented. Although fair comparisons cannot be made due to a lack of similar methods and adequate public datasets, we demonstrate that the proposed method with an AUC ROC of 0.979, outperforms a state-of-the-art automatic vessel segmentation method trained on publicly available datasets at 0.956. Conclusions: The proposed method generates accurate vessel segmentation results containing filamentary vessels that are virtually indiscernible to the naked eye in color retinal fundus images.

The structure of blood vessels play a crucial role in diagnoses of the various vision threatening diseases including Glaucoma and Diabetic Retinopathy (DR). The correct segmentation of retinal blood vessels is a crucial step in the study of retinal fundus images. We proposed a simple unsupervised approach by using a combination of Hessian based approach and intensity transformation approach. We have applied CLAHE for enhancing the contrast of the retinal fundus images. An enhanced version of PSO algorithm is applied for contextual region tuning of CLAHE. Morphological filter and Wiener filter are used to de-noise the enhanced image. The eigenvalues are obtained from the Hessian matrix at two different scales to extract thick and thin vessel enhanced images separately. The intensity transformation approach is separately applied to the enhanced image to maximize the vessel details. Global Otsu thresholding is applied on intensity transformed image and thick vessel enhanced image whereas ISODATA local thresholding is applied on thin vessel enhanced image. Finally, a simple post-processing step based on the region parameters such as area, eccentricity, and solidity is used. The region parameters are obtained for each connected component in input binary images. The threshold values of region parameters are empirically investigated and applied to each of the three binary images to remove the non-vessel components. The thresholded images are combined by applying logical OR operator, which resulted in the final segmented binary image. We assessed our developed framework on the open-access CHASE_DB1 and DRIVE datasets, achieving a sensitivity of 0.7776 and 0.7851, and an accuracy of 0.9505 and 0.9559 respectively. These results outperform several state-of-the-art unsupervised methods. The reduced computational complexity and significantly improved evaluation metrics advocates for its use in the automated diagnostic systems for retinal image analysis.

The segmentation of blood vessels from retinal images is an important and challenging task in medical analysis and diagnosis. This paper proposes a new architecture of the U-Net network for retinal blood vessel segmentation. Adding dense block to U-Net network makes each layer's input come from the all previous layer's output which improves the segmentation accuracy of small blood vessels. The effectiveness of the proposed method has been evaluated on two public datasets (DRIVE and CHASE_DB1). The obtained results (DRIVE: Acc = 0.9559, AUC = 0.9793, CHASE_DB1: Acc = 0.9488, AUC = 0.9785) demonstrate the better performance of the proposed method compared to the state-of-the-art methods. Also, the results show that our method achieves better results for the segmentation of small blood vessels and can be helpful to evaluate related ophthalmic diseases.

Laser speckle contrast imaging (LSCI) is a full-field, high spatiotemporal resolution and low-cost optical technique for measuring blood flow, which has been successfully used for neurovascular imaging. However, due to the low signal–noise ratio and the relatively small sizes, segmenting the cerebral vessels in LSCI has always been a technical challenge. Recently, deep learning has shown its advantages in vascular segmentation. Nonetheless, ground truth by manual labeling is usually required for training the network, which makes it difficult to implement in practice. In this manuscript, we proposed a deep learning-based method for real-time cerebral vessel segmentation of LSCI without ground truth labels, which could be further integrated into intraoperative blood vessel imaging system. Synthetic LSCI images were obtained with a synthesis network from LSCI images and public labeled dataset of Digital Retinal Images for Vessel Extraction, which were then used to train the segmentation network. Using matching strategies to reduce the size discrepancy between retinal images and laser speckle contrast images, we could further significantly improve image synthesis and segmentation performance. In the testing LSCI images of rodent cerebral vessels, the proposed method resulted in a dice similarity coefficient of over 75%.

Adaptive optics—optical coherence tomography (AO-OCT) is a non-invasive technique for imaging retinal vascular and structural features at cellular-level resolution. Whereas retinal blood vessel density is an important biomarker for ocular diseases, particularly glaucoma, automated blood vessel segmentation tools in AO-OCT have not yet been explored. One reason for this is that AO-OCT allows for variable input axial dimensions, which are not well accommodated by 2D-2D or 3D-3D segmentation tools. We propose a novel bidirectional long short-term memory (LSTM)-based network for 3D-2D segmentation of blood vessels within AO-OCT volumes. This technique incorporates inter-slice connectivity and allows for variable input slice numbers. We compare this proposed model to a standard 2D UNet segmentation network considering only volume projections. Furthermore, we expanded the proposed LSTM-based network with an additional UNet to evaluate how it refines network performance. We trained, validated, and tested these architectures in 177 AO-OCT volumes collected from 18 control and glaucoma subjects. The LSTM-UNet has statistically significant improvement (p &lt, 0.05) in AUC (0.88) and recall (0.80) compared to UNet alone (0.83 and 0.70, respectively). LSTM-based approaches had longer evaluation times than the UNet alone. This study shows that a bidirectional convolutional LSTM module improves standard automated vessel segmentation in AO-OCT volumes, although with higher time cost.

Presented at the 4th XoveTIC Conference, A Coruña, Spain, 7–8 October 2021. [Abstract] The analysis of the retinal vasculature represents a crucial stage in the diagnosis of several diseases. An exhaustive analysis involves segmenting the retinal vessels and classifying them into veins and arteries. In this work, we present an accurate approach, based on deep neural networks, for the joint segmentation and classification of the retinal veins and arteries from color fundus images. The presented approach decomposes this joint task into three related subtasks: the segmentation of arteries, veins and the whole vascular tree. The experiments performed show that our method achieves competitive results in the discrimination of arteries and veins, while clearly enhancing the segmentation of the different structures. Moreover, unlike other approaches, our method allows for the straightforward detection of vessel crossings, and preserves the continuity of the arterial and venous vascular trees at these locations. This work was funded by Instituto de Salud Carlos III, Government of Spain, and the European Regional Development Fund (ERDF) of the European Union (EU) through the DTS18/00136 research project; Ministerio de Ciencia e Innovación, Government of Spain, through the RTI2018-095894-B-I00 and PID2019-108435RB-I00 research projects; Axencia Galega de Innovación (GAIN), Xunta de Galicia, ref. IN845D 2020/38; Xunta de Galicia and European Social Fund (ESF) of the EU through the predoctoral grant contracts ED481A-2017/328 and ED481A 2021/140; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva, grant ref. ED431C 2020/24; CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, is funded by Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%) Xunta de Galicia; IN845D 2020/38 Xunta de Galicia; ED481A-2017/328 Xunta de Galicia; ED481A 2021/140 Xunta de Galicia; ED431C 2020/24 Xunta de Galicia; ED431G 2019/01

PURPOSE: To automate the segmentation of the peripheral arteries and veins in the lower extremities based on ferumoxytol-enhanced MR angiography (FE-MRA). METHODS: Our automated pipeline has 2 sequential stages. In the first stage, we used a 3D U-Net with local attention gates, which was trained based on a combination of the Focal Tversky loss with region mutual loss under a deep supervision mechanism to segment the vasculature from the high-resolution FE-MRA datasets. In the second stage, we used time-resolved images to separate the arteries from the veins. Because the ultimate segmentation quality of the arteries and veins relies on the performance of the first stage, we thoroughly evaluated the different aspects of the segmentation network and compared its performance in blood vessel segmentation with currently accepted state-of-the-art networks, including Volumetric-Net, DeepVesselNet-FCN, and Uception. RESULTS: We achieved a competitive F1 = 0.8087 and recall = 0.8410 for blood vessel segmentation compared with F1 = (0.7604, 0.7573, 0.7651) and recall = (0.7791, 0.7570, 0.7774) obtained with Volumetric-Net, DeepVesselNet-FCN, and Uception. For the artery and vein separation stage, we achieved F1 = (0.8274/0.7863) in the calf region, which is the most challenging region in peripheral arteries and veins segmentation. CONCLUSION: Our pipeline is capable of fully automatic vessel segmentation based on FE-MRA without need for human interaction in

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.

In recent years, automated retinal vessel segmentation has become especially essential for the early detection of some ophthalmological and cardiovascular diseases. In this paper, we have presented a new retinal vessel segmentation method via discriminative dictionary learning using fusion of multiple features, which is able to capture both thick and thin vessel structures. In the training stage, we employ six different enhancement algorithms to obtain multiple complementary features that contain rich vascular information. Then, the manually annotated ground-truth vessels are classified into thick or thin vessels as the label information, and the label consistent KSVD based framework is applied to train the dictionary for vessel segmentation. In the testing stage, comprehensive experiments are conducted on three datasets to measure segmentation performance with eight representative evaluation metrics. The average sensitivity reaches 0.7915, 0.7560 and 0.7202 respectively, suggesting that our method can segment tiny vascular structures well.

For selective internal radiation therapy (SIRT) the calculation of the 3D distribution of spheres based on individual blood flow properties is still an open and relevant research question. The purpose of this work is to develop and analyze a new treatment planning method for SIRT to calculate the absorbed dose distribution. For this intention, flow dynamics of the SIRT-spheres inside the blood vessels was simulated. The challenge is treatment planning solely using high-resolution imaging data available before treatment. The resolution required to reliably predict the sphere distribution and hence the dose was investigated. For this purpose, arteries of the liver were segmented from a contrast-enhanced angiographic CT. Due to the limited resolution of the given CT, smaller vessels were generated via a vessel model. A combined 1D/3D-flow simulation model was implemented to simulate the final 3D distribution of spheres and dose. Results were evaluated against experimental data from Y90-PET. Analysis showed that the resolution of the vessels within the angiographic CT of about 0.5mm should be improved to a limit of about 150μm to reach a reliable prediction.

Retina is the interior part of human's eye, has a vital role in vision. The digital image captured by fundus camera is very useful to analyze the abnormalities in retina especially in retinal blood vessels. To get information of blood vessels through fundus retinal image, a precise and accurate vessels segmentation image is required. This segmented blood vessel image is most beneficial to detect retinal diseases. Many automated techniques are widely used for retinal vessels segmentation which is a primary element of computerized diagnostic systems for retinal diseases. The automatic vessels segmentation may lead to more challenging task in the presence of lesions and abnormalities. This paper briefly describes the various publicly available retinal image databases and various machine learning techniques. State of the art exhibited that researchers have proposed several vessel segmentation methods based on supervised and supervised techniques and evaluated their results mostly on publicly datasets such as digital retinal images for vessel extraction and structured analysis of the retina. A comprehensive review of existing supervised and unsupervised vessel segmentation techniques or algorithms is presented which describes the philosophy of each algorithm. This review will be useful for readers in their future research.

In medical imaging practice, vascular enhancement filtering has been widely performed before vessel segmentation and centerline detection, which provides important pathological information and holds great significance for vessel quantification. In the literature, numerous well known vesselness filtering approaches have been developed. For example, some techniques explore the Hessian matrix of the original images and construct the vessel filter based on the eigenvalues of the Hessian matrix. In this work we develop a hybrid technique for fast and accurate vascular enhancement filter, which contains two main steps: vesselness diffusion and improved vesselness filter based on the eigenvalues ratio. This novel approach is quantitatively and qualitatively tested on the public 2D retinal datasets and 3D synthetic vascular structure models. Experimental results demonstrate that the proposed filter outperforms other existing approaches for curvilinear structure enhancement from noisy images. Moreover, the novel approach is further evaluated on real patient Coronary Computed Tomography Angiography (CCTA) datasets with ground truth regions labelled by professional cardiologist. Our method is proven to produce more accurate coronary artery segmentation results. Given the accuracy and efficiency, the proposed vesselness filter can be further used in medical practice for vascular structures enhancement before vessel segmentation and quantification.

Deep learning methods have been successfully applied in medical image classification, segmentation and detection tasks. The U-Net architecture has been widely applied for these tasks. In this paper, we propose a U-Net variant for improved vessel segmentation in retinal fundus images. Firstly, we design a minimal U-Net (Mi-UNet) architecture, which drastically reduces the parameter count to 0.07M compared to 31.03M for the conventional U-Net. Moreover, based on Mi-UNet, we propose Salient U-Net (S-UNet), a bridge-style U-Net architecture with a saliency mechanism and with only 0.21M parameters. S-UNet uses a cascading technique that employs the foreground features of one net block as the foreground attention information of the next net block. This cascading leads to enhanced input images, inheritance of the learning experience of previous net blocks, and hence effective solution of the data imbalance problem. S-UNet was tested on two benchmark datasets, DRIVE and CHASE_DB1, with image sizes of 584 × 565 and 960 × 999, respectively. S-UNet was tested on the TONGREN clinical dataset with image sizes of 1880 × 2816. The experimental results show superior performance in comparison to other state-of-theart methods. Especially, for whole-image input from the DRIVE dataset, S-UNet achieved a Matthews correlation coefficient (MCC), an area under curve (AUC), and an F1 score of 0.8055, 0.9821, and 0.8303, respectively. The corresponding scores for the CHASE_DB1 dataset were 0.8065, 0.9867, and 0.8242, respectively. Moreover, our model shows an excellent performance on the TONGREN clinical dataset. In addition, S-UNet segments images of low, medium, and high resolutions in just 33ms, 91ms and 0.49s, respectively. This shows the real-time applicability of the proposed model.

The blood vessels are the primary anatomical structure that can be visible in retinal images. The segmentation of retinal blood vessels has been accepted worldwide for the diagnosis of both cardiovascular (CVD) and retinal diseases. Thus, it requires an appropriate vessel segmentation method for automatic detection of retinal diseases such as diabetic retinopathy and cataract. The detection of retinal diseases using computer-aided diagnosis (CAD) can help people to avoid the risks of visual impairment and save medical resources. This survey presents a comparative analysis of various machine learning and deep learning-based methods for automated blood vessel segmentation in retinal images. This paper briefly describes fundus photography, publicly available retinal databases, pre-processing and post-processing techniques for retinal vessels segmentation. A comprehensive review of the state of the art supervised and unsupervised blood vessel segmentation methodologies are presented in this paper. The objective of this study is to establish a professional structure to familiarize an individual with up-to-date vessel segmentation techniques. Moreover, we compared these approaches to the dataset, evaluation metrics, pre-processing and post-processing steps, feature extraction, segmentation methods, and induced results.

In recent years, retinal vessel segmentation technology has become an important component for disease screening and diagnosing in clinical medicine. However, retinal vessel segmentation is a challenging task due to complex distribution of blood vessels, relatively low contrast between target and background, and potential presence of illumination and pathologies. In this paper, we propose an automatic retinal vessel segmentation network using deep supervision and smoothness regularization, which integrates holistically-nested edge detector (HED) and global smoothness regularization from conditional random fields. It is an end-to-end and pixel-to-pixel deep convolutional network, can perform better results than HED-based methods and the methods where CRF inference is applied as a post-processing method. With co-constraints between pixels, the proposed DSSRN obtains better results. Finally, we show that our proposed method obtains the state-of-the-art vessel segmentation performance on all three benchmarks, DRIVE, STARE, and CHASE_DB1.

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.

Purpose With the recent development of deep learning technologies, various neural networks have been proposed for fundus retinal vessel segmentation. Among them, the U-Net is regarded as one of the most successful architectures. In this work, we start with simplification of the U-Net, and explore the performance of few-parameter networks on this task. Methods We firstly modify the model with popular functional blocks and additional resolution levels, then we switch to exploring the limits for compression of the network architecture. Experiments are designed to simplify the network structure, decrease the number of trainable parameters, and reduce the amount of training data. Performance evaluation is carried out on four public databases, namely DRIVE, STARE, HRF and CHASE_DB1. In addition, the generalization ability of the few-parameter networks are compared against the state-of-the-art segmentation network. Results We demonstrate that the additive variants do not significantly improve the segmentation performance. The performance of the models are not severely harmed unless they are harshly degenerated: one level, or one filter in the input convolutional layer, or trained with one image. We also demonstrate that few-parameter networks have strong generalization ability. Conclusion It is counter-intuitive that the U-Net produces reasonably good segmentation predictions until reaching the mentioned limits. Our work has two main contributions. On the one hand, the importance of different elements of the U-Net is evaluated, and the minimal U-Net which is capable of the task is presented. On the other hand, our work demonstrates that retinal vessel segmentation can be tackled by surprisingly simple configurations of U-Net reaching almost state-of-the-art performance. We also show that the simple configurations have better generalization ability than state-of-the-art models with high model complexity. These observations seem to be in contradiction to the current trend of continued increase in model complexity and capacity for the task under consideration.

Background: The distribution of pulmonary vessels in computed tomography images is important for diagnosing disease, formulating surgical plans and pulmonary research. However, there are many challenges of pulmonary vascular segmentation due to its characteristics of narrow and long pipes, discrete distribution and tree-like structure. With the development of deep learning and medical image processing, an automatic, accurate and fast segmentation algorithm of pulmonary blood vessels becomes possible. Methods: Based on the International Symposium on Image Computing and Digital Medicine 2020 challenge pulmonary vascular segmentation task, this paper objectively evaluates the performance of 12 different algorithms in chest computed tomography and computed tomography angiography. First, we present the annotated reference dataset including computed tomography and computed tomography angiography. Second, by analyzing the advantages and disadvantages of each team’s algorithm from 12 different institution, the reasons for some defects and improvements are summarized. Finally, we discuss the ways and methods to improve the results. Results: These methods were compared with the ground truth by the numerical results and the intuitive results from computed tomography and computed tomography angiography images. Most methods do an admirable job in pulmonary vascular extraction, with dice coefficients ranging from 0.70 to 0.85, and the dice coefficient for the top three methods are about 0.80. Conclusions: These results show that the methods which consider spatial information, fuse multi-scale feature map, or have an excellent post-processing are significant for further improving the accuracy of pulmonary vascular segmentation. Keywords: segmentation; pulmonary; vessel; U-Net; network; CT images; CTA

The quantification of blood flow velocity in the human conjunctiva is clinically essential for assessing microvascular hemodynamics. Since the conjunctival microvessel is imaged in several seconds, eye motion during image acquisition causes motion artifacts limiting the accuracy of image segmentation performance and measurement of the blood flow velocity. In this paper, we introduce a novel customized optical imaging system for human conjunctiva with deep learning-based segmentation and motion correction. The image segmentation process is performed by the Attention-UNet structure to achieve high-performance segmentation results in conjunctiva images with motion blur. Motion correction processes with two steps—registration and template matching—are used to correct for large displacements and fine movements. The image displacement values decrease to 4–7 μm during registration (first step) and less than 1 μm during template matching (second step). With the corrected images, the blood flow velocity is calculated for selected vessels considering temporal signal variances and vessel lengths. These methods for resolving motion artifacts contribute insights into studies quantifying the hemodynamics of the conjunctiva, as well as other tissues.

From diagnosing neovascular diseases to detecting white matter lesions, accurate tiny vessel segmentation in fundus images is critical. Promising results for accurate vessel segmentation have been known. However, their effectiveness in segmenting tiny vessels is still limited. In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation. To achieve this, we propose a new deep convolutional neural network (CNN) which divides vessel segmentation into two separate objectives. Specifically, we consider the overall accurate vessel segmentation and tiny vessel segmentation as two individual objectives. Then, by exploiting the objective-dependent (homoscedastic) uncertainty, we enable the network to learn both objectives simultaneously. Further, to improve the individual objectives, we propose: (a) a vessel weight map based auxiliary loss for enhancing tiny vessel connectivity (i.e., improving tiny vessel segmentation), and (b) an enhanced encoder-decoder architecture for improved localization (i.e., for accurate vessel segmentation). Using 3 public retinal vessel segmentation datasets (CHASE_DB1, DRIVE, and STARE), we verify the superiority of our proposed framework in segmenting tiny vessels (8.3% average improvement in sensitivity) while achieving better area under the receiver operating characteristic curve (AUC) compared to state-of-the-art methods., Comment: ISBI 2021

Accurate segmentation of pulmonary blood vessels from CT images is of great significance for lung disease detection and segmentation of other lung structures. Manual segmentation is difficult to accurately segment vascular tissue for various reasons. Therefore, in view of the existing problems and shortcomings of the existing lung vessel segmentation method, a more efficient lung vessel segmentation algorithm is proposed, that is, the multi-template fast marching method (MSFM algorithm). Firstly, it used the hole filling and maximum inter-class variance algorithm for preprocess. In the process, the lung parenchyma is extracted from the chest CT, and then the lung blood vessels are extracted in the lung parenchymal area using the MSFM algorithm. In the extraction process, the threshold and gradient are used to limit the progress of the process and the lung blood vessels are more accurately segmented. Through experimental verification, the accuracy of lung blood vessel segmentation based on MSFM algorithm is improved.

The segmentation of liver blood vessels is of major importance as it is essential for formulating diagnoses, planning and delivering treatments, as well as evaluating the results of clinical procedures. Different imaging techniques are available for application in clinical practice, so the segmentation methods should take into account the characteristics of the imaging technique. Based on the literature, this review paper presents the most advanced and effective methods of liver vessel segmentation, as well as their performance according to the metrics used. This paper includes results available for four imaging methods, namely: computed tomography (CT), computed tomography angiography (CTA), magnetic resonance (MR), and ultrasonography (USG). The publicly available datasets used in research are also presented. This paper may help researchers gain better insight into the available materials and methods, making it easier to develop new, more effective solutions, as well as to improve existing approaches. This article analyzes in detail various segmentation methods, which can be divided into three groups: active contours, tracking-based, and machine learning techniques. For each group of methods, their theoretical and practical characteristics are discussed, and the pros and cons are highlighted. The most advanced and promising approaches are also suggested. However, we conclude that liver vasculature segmentation is still an open problem, because of the various deficiencies and constraints researchers need to address and try to eliminate from the solutions used.

Vessel segmentation from X-ray angiography (XRA) images is an important task in the clinical diagnosis of coronary artery disease. The main challenge lies in how to extract continuous and completed vessel masks from XRA images with poor quality and high complexity. Previous state-of-the-art methods are mostly based on hand-crafted features or pixel-wise segmentation and ignore geometric features, thereby resulting in breaks and absence of vessel structure in segmentation masks. In this paper, we propose a geometric feature embedding segmentation network for vessel segmentation in XRA images. This network joins direction- and centerline-related prediction tasks with mask segmentation, which enforces the network to learn the geometric features of vessel connectivity. Besides, a novel joint loss function is proposed to facilitate the joint training of these three tasks. We conduct ablation experiments on XRA images to demonstrate that the two auxiliary tasks can improve the connectivity and completeness of vessel segmentation. We also evaluate our method on XRA images and achieve the value of 85.00±3.66% for vessel segmentation, indicating that our method outperforms the other state-of-the-art methods.

Retinal photomontages, which are constructed by aligning and integrating multiple fundus images, are useful in diagnosing retinal diseases affecting peripheral retina. We present a novel framework for constructing retinal photomontages that fully leverage recent deep learning methods. Deep learning based object detection is used to define the order of image registration and blending. Deep learning based vessel segmentation is used to enhance image texture to improve registration performance within a two step image registration framework comprising rigid and non-rigid registration. Experimental evaluation demonstrates the robustness of our montage construction method with an increased amount of successfully integrated images as well as reduction of image artifacts.

The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images.

[Abstract] Background and objectives: The study of the retinal vasculature represents a fundamental stage in the screening and diagnosis of many high-incidence diseases, both systemic and ophthalmic. A complete retinal vascular analysis requires the segmentation of the vascular tree along with the classification of the blood vessels into arteries and veins. Early automatic methods approach these complementary segmentation and classification tasks in two sequential stages. However, currently, these two tasks are approached as a joint semantic segmentation, because the classification results highly depend on the effectiveness of the vessel segmentation. In that regard, we propose a novel approach for the simultaneous segmentation and classification of the retinal arteries and veins from eye fundus images. Methods: We propose a novel method that, unlike previous approaches, and thanks to the proposal of a novel loss, decomposes the joint task into three segmentation problems targeting arteries, veins and the whole vascular tree. This configuration allows to handle vessel crossings intuitively and directly provides accurate segmentation masks of the different target vascular trees. Results: The provided ablation study on the public Retinal Images vessel Tree Extraction (RITE) dataset demonstrates that the proposed method provides a satisfactory performance, particularly in the segmentation of the different structures. Furthermore, the comparison with the state of the art shows that our method achieves highly competitive results in the artery/vein classification, while significantly improving the vascular segmentation. Conclusions: The proposed multi-segmentation method allows to detect more vessels and better segment the different structures, while achieving a competitive classification performance. Also, in these terms, our approach outperforms the approaches of various reference works. Moreover, in contrast with previous approaches, the proposed method allows to directly detect the vessel crossings, as well as preserving the continuity of both arteries and veins at these complex locations. This work is supported by Instituto de Salud Carlos III, Government of Spain, and the European Regional Development Fund (ERDF) of the European Union (EU) through the DTS18/00136 research project; Ministerio de Ciencia e Innovación, Government of Spain, through the RTI2018-095894-B-I00 and PID2019-108435RB-I00 research projects; Xunta de Galicia and the European Social Fund (ESF) of the EU through the predoctoral grant contract ref. ED481A-2017/328; Consellería de Cultura, Educación e Universidade, Xunta de Galicia, through Grupos de Referencia Competitiva, grant ref. ED431C 2020/24. CITIC, Centro de Investigación de Galicia ref. ED431G 2019/01, receives financial support from Consellería de Educación, Universidade e Formación Profesional, Xunta de Galicia, through the ERDF (80%) and Secretaría Xeral de Universidades (20%) Xunta de Galicia; ED481A-2017/328 Xunta de Galicia; ED431C 2020/24 Xunta de Galicia; ED431G 2019/01

International audience; The accurate knowledge of vascular network geometry is crucial for many clinical applications such as cardiovascular disease diagnosis and surgery planning. Vessel enhancement algorithms are often a key step to improve the robustness of vessel segmentation. A wide variety of enhancement filters exists in the literature, but they are often difficult to compare as the applications and datasets differ from a paper to another and the code is rarely available. In this article, we compare seven vessel enhancement filters covering the last twenty years literature in a unique common framework. We focus our study on the liver vascular network which is under-represented in the literature. The evaluation is made from three points of view: in the whole liver, in the vessel neighborhood and near the bifurcations. The study is performed on two publicly available datasets: the Ircad dataset (CT images) and the VascuSynth dataset adapted for MRI simulation. We discuss the strengths and weaknesses of each method in the hepatic context. In addition, the benchmark framework including a C++ implementation of each compared method is provided. An online demonstration ensures the reproducibility of the results without requiring any additional software.

Manually segmenting the hepatic vessels from Computer Tomography (CT) is far more expertise-demanding and laborious than other structures due to the low-contrast and complex morphology of vessels, resulting in the extreme lack of high-quality labeled data. Without sufficient high-quality annotations, the usual data-driven learning-based approaches struggle with deficient training. On the other hand, directly introducing additional data with low-quality annotations may confuse the network, leading to undesirable performance degradation. To address this issue, we propose a novel mean-teacher-assisted confident learning framework to robustly exploit the noisy labeled data for the challenging hepatic vessel segmentation task. Specifically, with the adapted confident learning assisted by a third party, i.e., the weight-averaged teacher model, the noisy labels in the additional low-quality dataset can be transformed from ‘encumbrance’ to ‘treasure’ via progressive pixel-wise soft-correction, thus providing productive guidance. Extensive experiments using two public datasets demonstrate the superiority of the proposed framework as well as the effectiveness of each component.

Optical coherence tomography angiography (OCTA) is a non-invasive imaging method that can visualize the finest vascular networks in the human retina. OCTA image analysis has been successfully applied to the investigation of retinal vascular diseases of the eye and other systemic conditions that may manifest in the eye. To characterize and distinguish OCTA images from different pathologies, it is important to identify quantitative metrics and phenotypes that have high reproducibility and are not overly susceptible to the effects of imaging artifacts. This paper demonstrates the reproducibility of several recently demonstrated candidate OCTA quantitative metrics: mean curvature and tortuosity of the whole, foveal, superior, nasal, inferior, and temporal regions; foveal and parafoveal vessel skeleton density; and finally, foveal avascular zone area and acircularity index. This paper also highlights the importance of vessel segmentation choice on reproducibility using two different segmentation methods: optimally oriented flux and Frangi filter.

Analysis of images with deep learning and machine learning has recently show more accuracy in medical image processing. The paper review the major machine learning methods is used for the extraction of retinal fundus image. It describes how hardware has been modified according to time for retinal eye segmentation that device is helpful for the environment and also useful for humans The algorithms used for image extraction, clear and noise-free Images of different color scales are used to improve image quality. The paper gives a review of how researchers and scientists have been trying different methods to improve vessel segmentation in the future.