Vessel Detection Method Research Articles

Vessel Detection with SDGSAT-1 Nighttime Light Images

The Sustainable Development Goals Science Satellite-1 (SDGSAT-1) Glimmer Imager for Urbanization (GIU) data is very sensitive to low radiation and capable of detecting weak light sources from vessels at night while significantly improving the spatial resolution compared to similar products. Most existing methods fail to use the relevant characteristics of vessels effectively, and it is difficult to deal with the complex shape of vessels in high-resolution Nighttime Light (NTL) data, resulting in unsatisfactory detection results. Considering the overall sparse distribution of vessels and the light source diffusion phenomenon, a novel vessel detection method is proposed in this paper, utilizing the high spatial resolution of the SDGSAT-1. More specifically, noise separation is completed based on a local contrast-weighted RPCA. Then, artificial light sources are detected based on a density clustering algorithm, and an inter-cluster merging method is utilized to realize vessel detection further. We selected three research areas, namely, the Bohai Sea, the East China Sea, and the Gulf of Mexico, to establish a vessel dataset and applied the algorithm to the dataset. The results show that the total detection accuracy and the recall rate of the detection algorithm in our dataset are 96.84% and 96.67%, which is significantly better performance than other methods used for comparison in the experiment. The algorithm overcomes the dataset’s complex target shapes and noise conditions and achieves good results, which proves the applicability of the algorithm.

Deteksi Kapal Penangkapan Ikan Menggunakan data Visible Infrared Imaging Radiometer Suite (VIIRS) dan data Vessel Monitoring System (VMS) di Wilayah Pengelolaan Perikanan Negara Republik Indonesia

The small pelagic fisheries are one of the most important fish resources for the Indonesian economy. One of the problems for the fisheries industry in Indonesia's is overfishing, along with advances in fishing technology that result in catching activities that exceed sustainable fishing rates and are not offset by good management. This research aims to analyze the integrated distribution of fishing vessels from VIIRS vessel detection data and VMS data in Indonesia's fisheries management areas. To support management efforts, studies on the distribution of vessels that are operating in Indonesian waters need to be known definitively. Currently, the monitoring of the distribution of fishing vessels in the Indonesian area is carried out using a vessel monitoring system. Apart from VMS, detection of fishing vessels can be done by utilizing remote sensing data from both active and passive sensors, namely through the Suomi National Polar-orbiting Partnership satellite which has a visible infrared imaging radiometer suite. This instrument has a day/night band capable of recording lights on the earth's surface, including fishing boats that use the light as a fishing aid. The fishing vessel detection method uses a combination of VBD data from VIIRS satellite imagery and fishing vessel VMS data. Based on the result, VMS matching with VBD is 26.04%, and based on the combination of VIIRS and VMS data, it is known that the area with the most ship distribution is in WPP-712

Passive Acoustic Detection of Vessel Activity by Low-Energy Wireless Sensors

This paper presents the development of a low-energy passive acoustic vessel detector to work as part of a wireless underwater monitoring network. The vessel detection method is based on a low-energy implementation of Detection of Envelope Modulation On Noise (DEMON). Vessels produce a broad spectrum modulated noise during propeller cavitation, which the DEMON method aims to extract for the purposes of automated detection. The vessel detector design has different approaches with mixtures of analogue and digital processing, as well as continuous and duty-cycled sampling/processing. The detector re-purposes an existing acoustic modem platform to achieve a low-cost and long-deployment wireless sensor network. This integrated communication platform enables the detector to switch between detection/communication mode seamlessly within software. The vessel detector was deployed at depth for a total of 84 days in the North Sea, providing a large data set, which the results are based on. Open sea field trial results have shown detection of single and multiple vessels with a 94% corroboration rate with local Automatic Identification System (AIS) data. Results showed that additional information about the detected vessel such as the number of propeller blades can be extracted solely based on the detection data. The attention to energy efficiency led to an average power consumption of 11.4 mW, enabling long term deployments of up to 6 months using only four alkaline C cells. Additional battery packs and a modified enclosure could enable a longer deployment duration. As the detector was still deployed during the first UK lockdown, the impact of COVID-19 on North Sea fishing activity was captured. Future work includes deploying this technology en masse to operate as part of a network. This could afford the possibility of adding vessel tracking to the abilities of the vessel detection technology when deployed as a network of sensor nodes.

Coronary vessel detection methods for organ-mounted robots.

HeartLander is a tethered robot walker that utilizes suction to adhere to the beating heart. HeartLander can be used for minimally invasive administration of cardiac medications or ablation of tissue. In order to administer injections safely, HeartLander must avoid coronary vasculature. Doppler ultrasound signals were recorded using a custom-made cardiac phantom and used to classify different coronary vessel properties. The classification was performed by two machine learning algorithms, the support vector machines and a deep convolutional neural network. These algorithms were then validated in animal trials. Accuracy of identifying vessels above turbulent flow reached greater than 92% in phantom trials and greater than 98% in animal trials. Through the use of two machine learning algorithms, HeartLander has shown the ability to identify different sized vasculature proximally above turbulent flow. These results indicate that it is feasible to use Doppler ultrasound to identify and avoid coronary vasculature during cardiac interventions using HeartLander.

Comparative Study of Vessel Detection Methods for Contrast Enhanced Computed Tomography: Effects of Convolutional Neural Network Architecture and Patch Size

Comparative Study of Vessel Detection Methods for Contrast Enhanced Computed Tomography: Effects of Convolutional Neural Network Architecture and Patch Size

A Novel Deep Learning Pipeline for Retinal Vessel Detection In Fluorescein Angiography.

While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks (DNNs) that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus FA images. Binary vessels maps are first detected from CF images with a pre-trained neural network and then are geometrically registered with and transferred to FA images via robust parametric chamfer alignment to a preliminary FA vessel detection obtained with an unsupervised technique. Using the transferred vessels as initial ground truth labels for deep learning, the human-in-the-loop approach progressively improves the quality of the ground truth labeling by iterating between deep-learning and labeling. The approach significantly reduces manual labeling effort while increasing engagement. We highlight several important considerations for the proposed methodology and validate the performance on three datasets. Experimental results demonstrate that the proposed pipeline significantly reduces the annotation effort and the resulting deep learning methods outperform prior existing FA vessel detection methods by a significant margin. A new public dataset, RECOVERY-FA19, is introduced that includes high-resolution ultra-widefield images and accurately labeled ground truth binary vessel maps.

A two-dimensional feasibility study of deep learning-based feature detection and characterization directly from CT sinograms.

Machine Learning, especially deep learning, has been used in typical x-ray computed tomography (CT) applications, including image reconstruction, image enhancement, imagedomain feature detection and imagedomain feature characterization. To our knowledge, this is the first study on machine learning for feature detection and analysis directly based on CT projection data. Specifically, we present neural network methods for blood vessel detection and characterization in the sinogram domain avoiding any partial volume, beam hardening, or motion artifacts introduced during reconstruction. First, we estimate sinogramdomain vessel maps using a residual encoder-decoder convolutional neural network (REDCNN). Next, we estimate the vessel centerline and we extract the vessel-only sinogram from the original sinogram, eliminating any background information. Finally, we use a fully connected neural network to estimate the vessel lumen cross-sectional area from the vessel-only sinogram. We trained and tested the proposed methods using CatSim simulations, real CT measurements of vessel phantoms, and clinical data from the NIH CT image database. We achieved encouraging initial results showing the feasibility of CT analysis in the sinogram domain. In principle, sinogramdomain analysis should be possible for many other and more complicated clinical CT analysis tasks. Further studies are needed for this sinogramdomain analysis approach to become practical for clinical applications.

A Long Short-Term Memory Network for Vessel Reconstruction Based on Laser Doppler Flowmetry via a Steerable Needle

Hemorrhage is one risk of percutaneous intervention in the brain that can be life-threatening. Steerable needles can avoid blood vessels thanks to their ability to follow curvilinear paths, although knowledge of vessel pose is required. To achieve this, we present the deployment of laser Doppler flowmetry (LDF) sensors as an in-situ vessel detection method for steerable needles. Since the perfusion value from an LDF system does not provide positional information directly, we propose the use of a machine learning technique based on a Long Short-term Memory (LSTM) network to perform vessel reconstruction online. Firstly, the LSTM is used to predict the diameter and position of an approaching vessel based on successive measurements of a single LDF probe. Secondly, a “no-go” area is predicted based on the measurement from four LDF probes embedded within a steerable needle, which accounts for the full vessel pose. The network was trained using simulation data and tested on experimental data, with 75% diameter prediction accuracy and 0.27 mm positional Root Mean Square (RMS) Error for the single probe network, and 77% vessel volume overlap for the 4-probe setup.

Vessel Detection and Tracking Method Based on Video Surveillance.

Ship detection and tracking is a basic task in any vessel traffic monitored area, whether marine or inland. It has a major impact on navigational safety and thus different systems and technologies are used to determine the best possible methods of detecting and identifying sailing units. Video monitoring is present in almost all of them, but it is usually operated manually and is used as a backup system. This is because of the difficulties in implementing an efficient and universal automatic detection method that would work in quickly alternating environmental conditions for all kind of sailing units—from kayaks to seagoing merchant vessels. This paper presents a method that allows the detection and tracking of ships using the video streams of existing monitoring systems for ports and rivers. The method and the results of experiments on three sets of data using cameras with different characteristics, settings, and scene locations are presented. The experiments were carried out in variable light and weather conditions, and a wide range of unit types were used as detection objectives. The results confirm the usability of the proposed solution; however, some minor issues were encountered in the presence of ships wakes or highly unfavourable weather conditions.

Retinal blood vessel segmentation based on heuristic image analysis

Automatic analysis of retinal fundus images is becoming increasingly present today, and diseases such as diabetic retinopathy and age-related macular degeneration are getting a higher chance of being discovered in the early stages of their development. In order to focus on discovering those diseases, researchers commonly preprocess retinal fundus images in order to detect the retinal landmarks - blood vessels, fovea and the optic disk. A large number of methods for the automatic detection of retinal blood vessels from retinal fundus images already exists, but many of them are using unnecessarily complicated approaches. In this paper we demonstrate that a reliable retinal blood vessel segmentation can be achieved with a cascade of very simple image processing methods. The proposed method puts higher emphasis on high specificity (i.e. high probability that the segmented pixels actually belong to retinal blood vessels and are not false positive detections) rather than on high sensitivity. The proposed method is based on heuristically determined parametric edge detection and shape analysis, and is evaluated on the publicly available DRIVE and STARE datasets on which it achieved the average accuracy of 96.33% and 96.10%, respectively.

Coronary artery segmentation in X-ray angiograms using gabor filters and differential evolution

Segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis, since it can help cardiologists in diagnosing and monitoring vascular abnormalities. Due to the main disadvantages of the X-ray angiograms are the nonuniform illumination, and the weak contrast between blood vessels and image background, different vessel enhancement methods have been introduced. In this paper, a novel method for blood vessel enhancement based on Gabor filters tuned using the optimization strategy of Differential evolution (DE) is proposed. Because the Gabor filters are governed by three different parameters, the optimal selection of those parameters is highly desirable in order to maximize the vessel detection rate while reducing the computational cost of the training stage. To obtain the optimal set of parameters for the Gabor filters, the area (Az) under the receiver operating characteristics curve is used as objective function. In the experimental results, the proposed method achieves an Az=0.9388 in a training set of 40 images, and for a test set of 40 images it obtains the highest performance with an Az=0.9538 compared with six state-of-the-art vessel detection methods. Finally, the proposed method achieves an accuracy of 0.9423 for vessel segmentation using the test set. In addition, the experimental results have also shown that the proposed method can be highly suitable for clinical decision support in terms of computational time and vessel segmentation performance.

Fast Vessel Detection in Gaofen-3 SAR Images with Ultrafine Strip-Map Mode.

This study aims to detect vessels with lengths ranging from about 70 to 300 m, in Gaofen-3 (GF-3) SAR images with ultrafine strip-map (UFS) mode as fast as possible. Based on the analysis of the characteristics of vessels in GF-3 SAR imagery, an effective vessel detection method is proposed in this paper. Firstly, the iterative constant false alarm rate (CFAR) method is employed to detect the potential ship pixels. Secondly, the mean-shift operation is applied on each potential ship pixel to identify the candidate target region. During the mean-shift process, we maintain a selection matrix recording which pixels can be taken, and these pixels are called as the valid points of the candidate target. The norm regression is used to extract the principal axis and detect the valid points. Finally, two kinds of false alarms, the bright line and the azimuth ambiguity, are removed by comparing the valid area of the candidate target with a pre-defined value and computing the displacement between the true target and the corresponding replicas respectively. Experimental results on three GF-3 SAR images with UFS mode demonstrate the effectiveness and efficiency of the proposed method.

Abstract WP67: VESCA: Semi-Automated Segmentation of Cerebral Vasculature in Angiograms

Background: Imaging the cerebrovasculature using digital subtraction angiography (DSA) is a critical step in the diagnosis and treatment of acute stroke. Interpretation and scoring of these DSA images is usually performed by visual review, introducing inter-reader variability that causes inconsistency in clinical trials. Recently, methods have been introduced to automatically quantify various metrics in DSA images, such as revascularization and blush score, and vessel extraction algorithms are often used as part of these methods. However, the results of those algorithms have not been thoroughly evaluated against manually determined groundtruth extraction results, due to a lack of tools for determining the ground truths. Methods: We present a dedicated software tool, VESCA (Vessel Segmentation for Cerebral Angiograms), for manually determining the groundtruths of DSA images to better evaluate vessel detection methods. VESCA interface allows the user to view and segment DSA images, producing a segmented, binary representation of the vasculature. The segmentation process is semi-automated thanks to the livewire segmentation technique, whereby user-selected points along vessel boundaries are automatically connected via the lowest cost path. Results: We have segmented angiograms from a database of 115 biplane DSA, resulting in a set of binary representations of the vessels. We are constructing a web-based system through which other researchers may access the database, and through which they may use the software to contribute segmented images. Conclusion: VESCA is simple to operate and requires minimal instruction. We anticipate that it will facilitate the development and improvement of automatic methods for quantitative DSA image analysis.

Automatic segmentation of coronary arteries using Gabor filters and thresholding based on multiobjective optimization

Abstract This paper presents a new method consisting of two stages for automatic detection and segmentation of coronary arteries in X-ray angiograms. In the first stage, multiscale Gabor filters are used to detect vessel structures in the angiograms. The results of multiscale Gabor filtering are compared with those obtained by applying multiscale methods based on the top-hat operator, Hessian matrix, and Gaussian matched filters. The performance of the vessel-detection methods is evaluated through the area ( A z ) under the receiver operating characteristic (ROC) curve. In the second stage, coronary arteries are segmented by binarizing the magnitude response of Gabor filters using a new thresholding method based on multiobjective optimization, which is compared with seven thresholding methods. Measures of sensitivity, specificity, accuracy, and positive predictive value are used to analyze the segmentation methods, by comparing the results to the ground-truth markings of the vessels drawn by a specialist. Finally, the proposed method is compared with seven state-of-the-art vessel segmentation methods. The result of vessel detection using multiscale Gabor filters demonstrated high accuracy with A z = 0.961 with a training set of 40 angiograms and A z = 0.952 with an independent test set of 40 angiograms. The results of vessel segmentation with the multiobjective thresholding method provided an average accuracy of 0.881 with the test set of angiograms.

Computer-aided diagnosis of plus disease in retinal fundus images of preterm infants via measurement of vessel tortuosity.

An increase in retinal vessel tortuosity can be indicative of the presence of various diseases including retinopathy of prematurity (ROP). Accurate detection and measurement of such changes could help in computer-aided diagnosis of plus disease, which warrants treatment of ROP. We present image processing methods for detection and segmentation of retinal vessels, quantification of vessel tortuosity, and diagnostic-decision-making criteria that incorporate the clinical definition of plus-diagnosis. The obtained results using 110 retinal fundus images of preterm infants (91 without plus and 19 with plus) provide high sensitivity = 0.89 (17/19) and excellent specificity = 0.95 (86/91) in the diagnosis of plus disease.

NEAR REAL-TIME AUTOMATIC MARINE VESSEL DETECTION ON OPTICAL SATELLITE IMAGES

Abstract. Vessel monitoring and surveillance is important for maritime safety and security, environment protection and border control. Ship monitoring systems based on Synthetic-aperture Radar (SAR) satellite images are operational. On SAR images the ships made of metal with sharp edges appear as bright dots and edges, therefore they can be well distinguished from the water. Since the radar is independent from the sun light and can acquire images also by cloudy weather and rain, it provides a reliable service. Vessel detection from spaceborne optical images (VDSOI) can extend the SAR based systems by providing more frequent revisit times and overcoming some drawbacks of the SAR images (e.g. lower spatial resolution, difficult human interpretation). Optical satellite images (OSI) can have a higher spatial resolution thus enabling the detection of smaller vessels and enhancing the vessel type classification. The human interpretation of an optical image is also easier than as of SAR image. In this paper I present a rapid automatic vessel detection method which uses pattern recognition methods, originally developed in the computer vision field. In the first step I train a binary classifier from image samples of vessels and background. The classifier uses simple features which can be calculated very fast. For the detection the classifier is slided along the image in various directions and scales. The detector has a cascade structure which rejects most of the background in the early stages which leads to faster execution. The detections are grouped together to avoid multiple detections. Finally the position, size(i.e. length and width) and heading of the vessels is extracted from the contours of the vessel. The presented method is parallelized, thus it runs fast (in minutes for 16000 × 16000 pixels image) on a multicore computer, enabling near real-time applications, e.g. one hour from image acquisition to end user.

In Situ Root System Architecture Extraction from Magnetic Resonance Imaging for Water Uptake Modeling

An automated method for root system architecture reconstruction from three‐dimensional volume data sets obtained from magnetic resonance imaging (MRI) was developed and validated with a three‐dimensional semimanual reconstruction using virtual reality and a two‐dimensional reconstruction using SmartRoot. It was tested on the basis of an MRI image of a 25‐d‐old lupin (Lupinus albus L.) grown in natural sand with a resolution of 0.39 by 0.39 by 1.1 mm. The automated reconstruction algorithm was inspired by methods for blood vessel detection in MRI images. It describes the root system by a hierarchical network of nodes, which are connected by segments of defined length and thickness, and also allows the calculation of root parameter profiles such as root length, surface, and apex density The obtained root system architecture (RSA) varied in number of branches, segments, and connectivity of the segments but did not vary in the average diameter of the segments (0.137 cm for semimanual and 0.143 cm for automatic RSA), total root surface (127 cm2 for semimanual and 124 cm2 for automatic RSA), total root length (293 cm for semimanual and 282 cm for automatic RSA), and total root volume (4.7 cm3 for semimanual and 4.7 cm3 for automatic RSA). The difference in performance of the automated and semimanual reconstructions was checked by using the root system as input for water uptake modeling with the Doussan model. Both systems worked well and allowed for continuous water flow. Slight differences in the connectivity appeared to be leading to locally different water flow velocities, which were 30% smaller for the semimanual method.

Effects of angico extract (Anadenanthera colubrina var. cebil) in cutaneous wound healing in rats

To study the effects of the angico extract (Anadenanthera colubrina var. cebil) on the healing of rat skin. Twenty adult rats were divided into four groups of five animals each, the G4, G7, G14 and G21, which corresponds to the respective postoperative days. Each group received two incisions on skin and subcutaneous tissue in the right and left antimere of the thoracic region, separated by a distance of 2 cm. The right lesion was treated daily with saline and the left with the angico alcoholic extract (5%). At the end of each experimental period, animals were euthanized and fragments of the wound area, together with the edges were removed, fixed in 10% formaldehyde solution and processed for paraffin embedding. In the histological sections with 5 µm of thickness, were carried out immunohistochemical methods for detection of blood vessels (VEGF) and stained with hematoxylin and eosin for morphological analysis. Statistical analysis was done by ANOVA and Tukey test (p<0.05). Morphological analysis showed larger fibroblasts and a higher concentration of collagen fibers in days 7 and 14 in wounds treated with the angico extract. Morphometric analysis demonstrated a significant increase in the number of blood vessels in both the seventh and 14th days (p<0.01) in wounds treated with the angico extract. The angico alcoholic extract (Anadenanthera colubrina var. cebil) induces the acceleration of wound healing in skin wounds of rats.

A VTK-based, CUDA-optimized Non-Parametric Vessel Detection Method

We present a VTK-based implementation of our non-parametric vessel detection method that identifies vascular structures using a polar neighborhood profile. To accelerate the computationally intensive parts of the algorithm, we leverage the hardware capabilities in commodity graphics hardware using Compute Unified Device Architecture (CUDA). We present the results of our performance analysis and provide source code and examples to validate the reproducibility of our results.

Effective visualization of complex vascular structures using a non-parametric vessel detection method

The effective visualization of vascular structures is critical for diagnosis, surgical planning as well as treatment evaluation. In recent work, we have developed an algorithm for vessel detection that examines the intensity profile around each voxel in an angiographic image and determines the likelihood that any given voxel belongs to a vessel; we term this the "vesselness coefficient" of the voxel. Our results show that our algorithm works particularly well for visualizing branch points in vessels. Compared to standard Hessian based techniques, which are fine-tuned to identify long cylindrical structures, our technique identifies branches and connections with other vessels. Using our computed vesselness coefficient, we explore a set of techniques for visualizing vasculature. Visualizing vessels is particularly challenging because not only is their position in space important for clinicians but it is also important to be able to resolve their spatial relationship. We applied visualization techniques that provide shape cues as well as depth cues to allow the viewer to differentiate between vessels that are closer from those that are farther. We use our computed vesselness coefficient to effectively visualize vasculature in both clinical neurovascular x-ray computed tomography based angiography images, as well as images from three different animal studies. We conducted a formal user evaluation of our visualization techniques with the help of radiologists, surgeons, and other expert users. Results indicate that experts preferred distance color blending and tone shading for conveying depth over standard visualization techniques.