Search

The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model’s generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels.

Standard manual analysis of IVUS to study the impact of anti-atherosclerotic therapies on the coronary vessel wall is done by a core laboratory (CL), the ground truth (GT). Automatic segmentation of IVUS with a machine learning (ML) algorithm has the potential to replace manual readings with an unbiased and reproducible method. The aim is to determine if results from a CL can be replicated with ML methods. This is a post-hoc, comparative analysis of the IBIS-4 (Integrated Biomarkers and Imaging Study-4) study (NCT00962416). The GT baseline and 13-month follow-up measurements of lumen and vessel area and percent atheroma volume (PAV) after statin induction were repeated by the ML algorithm. The primary endpoint was change in PAV. PAV as measured by GT was 43.95 % at baseline and 43.02 % at follow-up with a change of −0.90 % (p = 0.007) while the ML algorithm measured 43.69 % and 42.41 % for baseline and follow-up, respectively, with a change of −1.28 % (p < 0.001). Along the most diseased 10 mm segments, GT-PAV was 52.31 % at baseline and 49.42 % at follow-up, with a change of −2.94 % (p < 0.001). The same segments measured by the ML algorithm resulted in PAV of 51.55 % at baseline and 47.81 % at follow-up with a change of −3.74 % (p < 0.001). PAV, the most used endpoint in clinical trials, analyzed by the CL is closely replicated by the ML algorithm. ML automatic segmentation of lumen, vessel and plaque effectively reproduces GT and may be used in future clinical trials as the standard. • Automated intravascular ultrasound segmentation can reproduce manual readings. • A validated machine learning algorithm replicates results from a core laboratory. • Use of automated methods are warranted in the catheterization laboratory. [ABSTRACT FROM AUTHOR]

Retinopathy of prematurity (ROP), sometimes known as Terry syndrome, is an ophthalmic condition that affects premature babies. It is the main cause of childhood blindness and morbidity of vision throughout life. ROP frequently coexists with a disease stage known as Plus disease, which is marked by severe tortuosity and dilated retinal blood vessels. The goal of this research is to create a diagnostic technique that can discriminate between infants with Plus disease from healthy subjects. Blood vascular tortuosity is used as a prognostic indicator for the diagnosis. We examine the quantification of retinal blood vessel tortuosity and propose a computer-aided diagnosis system that can be used as a tool for ROP identification. Deep neural networks are used in the proposed approach to segment retinal blood vessels, which is followed by the prediction of tortuous vessel pixels in the segmented vessel map. Digital fundus images obtained from Retcam3 TM is used for screening. We use a proprietary data set of 289 infant retinal images (89 with Plus disease and 200 healthy) from Narayana Nethralaya in Bangalore, India, to illustrate the efficacy of our methodology. The findings of this study demonstrate the reliability of the proposed method as a computer-aided diagnostic tool that can help medical professionals make an early diagnosis of ROP. [ABSTRACT FROM AUTHOR]

Vessel segmentation in digital subtraction angiography (DSA) is of great significance for the diagnosis, evaluation and detection of cerebral diseases. Manual segmentation is relatively time-consuming and subjective, so that automatic cerebrovascular segmentation technology has good application value in the treatment of cerebrovascular diseases. The traditional segmentation algorithm performs poorly because of the complexity of cerebrovascular structure, large-scale changes, and the impact of noise such as artifacts in DSA. In this work, using depth learning method and attention mechanism, we propose a spatial multi-scale attention U improved network (SMAU-Net) for vessel segmentation of DSA images. The network mainly consists of three parts: multi-scale spatial attention module, feature aggregate module, and detail supervision module. Using various attention mechanisms to pay attention to scale, space and channel information, the semantic, edge information and thin vessel features are enhanced. We applied the proposed method to the benchmark retinal vessel dataset CHASE and DSAC (cerebral DSA imaging dataset made in our laboratory). The experimental results show that the proposed SMAU-Net achieves the F1 score of 86.32% and the precision of 90.04%, which is superior to other models and is an improvement of 1.98 and 5.71% over the baseline U-Net. The experiment also proves that the method can be extended to various vascular segmentation tasks and has good visual diagnosis quality. [ABSTRACT FROM AUTHOR]

Quantitative analysis of intracranial vessel segments typically requires the identification of the vessels' centerlines, and a path-finding algorithm can be used to automatically detect vessel segments' centerlines. This study compared the performance of path-finding algorithms for vessel labeling. Three-dimensional (3D) time-of-flight magnetic resonance angiography (MRA) images from the publicly available dataset were considered for this study. After manual annotations of the endpoints of each vessel segment, three path-finding methods were compared: (Method 1) depth-first search algorithm, (Method 2) Dijkstra's algorithm, and (Method 3) A* algorithm. The rate of correctly found paths was quantified and compared among the three methods in each segment of the circle of Willis arteries. In the analysis of 840 vessel segments, Method 2 showed the highest accuracy (97.1%) of correctly found paths, while Method 1 and 3 showed an accuracy of 83.5% and 96.1%, respectively. The AComm artery was highly inaccurately identified in Method 1, with an accuracy of 43.2%. Incorrect paths by Method 2 were noted in the R-ICA, L-ICA, and R-PCA-P1 segments. The Dijkstra and A* algorithms showed similar accuracy in path-finding, and they were comparable in the speed of path-finding in the circle of Willis arterial segments. [ABSTRACT FROM AUTHOR]

Coronary angiography (CAG) is the "gold standard" for diagnosing coronary artery disease (CAD). However, due to the limitation of current imaging methods, the CAG image has low resolution and poor contrast with a lot of artifacts and noise, which makes it difficult for blood vessels segmentation. In this paper, we propose a DBCU-Net for automatic segmentation of CAG images, which is an extension of U-Net, DenseNet with bi-directional ConvLSTM(BConvLSTM). The main contribution of our network is that instead of convolution in the feature extraction of U-Net, we incorporate dense connectivity and the bi-directional ConvLSTM to highlight salient features. We conduct our experiment on our private dataset, and achieve average Accuracy, Precision, Recall and F1-score for coronary artery segmentation of 0.985, 0.913, 0.847 and 0.879 respectively. [ABSTRACT FROM AUTHOR]

Objective. The goal of this study is to develop a robust semi-weakly supervised learning strategy for vessel segmentation in laser speckle contrast imaging (LSCI), addressing the challenges associated with the low signal-to-noise ratio, small vessel size, and irregular vascular aberration in diseased regions, while improving the performance and robustness of the segmentation method. Approach. For the training dataset, the healthy vascular images denoted as normal-vessel samples were manually labeled, while the diseased LSCI images involving tumor or embolism were denoted as abnormal-vessel samples and annotated as pseudo labels by the traditional semantic segmentation methods. In the training phase, the pseudo labels were constantly updated to improve the segmentation accuracy based on DeepLabv3+. Objective evaluation was conducted on the normal-vessel test set, while subjective evaluation was performed on the abnormal-vessel test set. Main results. The proposed method achieved an IOU of 0.8671, a Dice of 0.9288, and a mean relative percentage difference (mRPD) with supervised learning of 0.5% in the objective evaluation. In the subjective evaluation, our method significantly outperformed other methods in main vessel segmentation, tiny vessel segmentation, and blood vessel connection. Additionally, our method exhibited robustness when abnormal-vessel style noise was added to normal-vessel samples using a style translation network. Significance. The proposed semi-weakly supervised learning strategy demonstrates high efficiency and excellent robustness for vascular segmentation in LSCI, providing a potential tool for assessing the morphological and structural features of vessels in clinical applications. [ABSTRACT FROM AUTHOR]

The main cause of eye disorders and visual loss in diabetics is diabetic retinopathy (DR). Patients with diabetes frequently have DR as a result of damage to retinal blood vessels. Therefore, the detachment of the retinal blood vessels is essential to the diagnosis of DR. If the diagnosis is made in the early stages, we can avoid vision loss or blindness issues. A 50% reduction in the probability of vision loss would result from an early diagnosis and initial investigation. Basic preprocessing, segmentation of blood arteries utilizing primary curvatures (maximum) and the ISODATA algorithm with the aid of image processing techniques, and labeling of related components make up the suggested method in this study. This study made use of the DRIVE (digital retinal images for vessel extraction) and STARE (structured analysis of the retina) datasets. Performance metrics including accuracy, specificity, and sensitivity were chosen in order to show the effectiveness of the methodology. The segmentation of blood arteries using the proposed framework in this study achieves higher accuracy than the previous ones. [ABSTRACT FROM AUTHOR]

The non-invasive measurement of hemoglobin oxygen saturation (SO2) in retinal vessels is based on spectrophotometry and the absorption spectral characteristics of the tissue. The dual-wavelength retinal images are simultaneously captured via retinal oximetry. SO2 is calculated by processing a series of images and by calculating the optic density ratio of two images. However, existing SO2 research is focused on the thick vessels in the high-clarity region of retinal images. However, the thin vessels in the low-clarity region could provide significant information for the detection and diagnosis of neovascular diseases. To this end, we proposed a novel hybrid vessel segmentation algorithm. Firstly, a median filter was employed for image denoising. Secondly, high- and low-clarity region segmentation was carried out based on a clarity histogram. The vessels in the high-clarity areas were segmented after implementing a Gaussian filter, a matched filter, and morphological segmentation. Additionally, the vessels in the low-clarity areas were segmented using a guided filter, matched filtering, and dynamic threshold segmentation. Finally, the results were obtained through image merger and morphological operations. The experimental results and analysis show that the proposed method can effectively segment thick and thin vessels and can extend the measuring range of dual-wavelength retinal oximetry. [ABSTRACT FROM AUTHOR]

Fetoscopic laser photocoagulation is used to treat twin-to-twin transfusion syndrome; however, this procedure is hindered because of difficulty in visualising the intraoperative surgical environment due to limited surgical field-of-view, unusual placenta position, limited manoeuvrability of the fetoscope and poor visibility due to fluid turbidity and occlusions. Fetoscopic video mosaicking can create an expanded field-of-view image of the fetoscopic intraoperative environment, which could support the surgeons in localising the vascular anastomoses during the fetoscopic procedure. However, classical handcrafted feature matching methods fail on in vivo fetoscopic videos. An existing state-of-the-art method on fetoscopic mosaicking relies on vessel presence and fails when vessels are not present in the view. We propose a vessel-guided hybrid fetoscopic mosaicking framework that mutually benefits from a placental vessel-based registration and a deep learning-based dense matching method to optimise the overall performance. A selection mechanism is implemented based on vessels' appearance consistency and photometric error minimisation for choosing the best pairwise transformation. Using the extended fetoscopy placenta dataset, we experimentally show the robustness of the proposed framework, over the state-of-the-art methods, even in vessel-free, low-textured, or low illumination non-planar fetoscopic views. [ABSTRACT FROM AUTHOR]

X-ray angiography is considered the standard imaging sensory system for diagnosing coronary artery diseases. For automated, accurate diagnosis of such diseases, coronary vessels’ detection from the captured low quality and noisy angiography images is challenging. It is essential to detect the main branch of the coronary artery, to resolve such limitations along with the problems due to the sudden changes in the lumen diameter, and the abrupt changes in local artery direction. Accordingly, this paper solved these limitations by proposing a computer-aided detection system for the right coronary artery (RCA) extraction, where geometric shape features with catheter localization and geodesic distance transform in the angiography images through two parts. In part 1, the captured image was initially preprocessed for contrast enhancement using singular value decomposition-based contrast adjustment, followed by generating the vesselness map using Jerman filter, and for further segmentation the K-means was introduced. Afterward, in part 2, the geometric shape features of the RCA, as well as the skeleton gradient transform, and the start/end points were determined to extract the main blood vessel of the RCA. The analysis of the skeletonize image was performed using Geodesic distance transform to examine all branches starting from the predetermined start point and cover the branching till the predefined end points. A ranking matrix, and the inverse of skeletonization were finally carried out to get the actual main branch. The performance of the proposed system was then evaluated using different evaluation metrics on the angiography images....

Optical Coherence Tomography (OCT) is a widely used 3D imaging technology in ophthalmology. Segmentation of retinal layers in OCT is important for diagnosis and evaluation of various retinal and systemic diseases. While 2D segmentation algorithms have been developed, they do not fully utilize contextual information and suffer from inconsistency in 3D. We propose neural networks to combine motion correction and segmentation in 3D. The proposed segmentation network utilizes 3D convolution and a novel graph pyramid structure with graph-inspired building blocks. We also collected one of the largest OCT segmentation dataset with manually corrected segmentation covering both normal examples and various diseases. The experimental results on three datasets with multiple instruments and various diseases show the proposed method can achieve improved segmentation accuracy compared with commercial softwares and conventional or deep learning methods in literature. Specifically, the proposed method reduced the average error from 38.47% to 11.43% compared to clinically available commercial software for severe deformations caused by diseases. The diagnosis and evaluation of diseases with large deformation such as DME, wet AMD and CRVO would greatly benefit from the improved accuracy, which impacts tens of millions of patients.

Retinal fundus images contain highly informative geometrical features for detecting diabetic retinopathy (DR), including vessels, especially thin and low-contrast vessels, which are predominant features for accurately diagnosing diabetic retinopathy. Automatic segmentation methods have been developed based on deep convolutional neural networks to replace manual labeling. These methods have shown acceptable performance in fundus vessel segmentation. The UNet model is a well-known architecture of deep neural networks often used for vessel segmentation tasks and has achieved significant performance. However, segmentation tasks remain challenging due to multiple convolutions, down-sampling operations, and inadequate feature fusion in the encoder-decoder architecture. Also, traditional convolution increases the number of multiplications while performing convolution operations. These challenges lead to the loss of information related to thin and low-contrast vessels, eventually affecting the segmentation performance. To tackle this issue, we propose incorporating depthwise parallel attention in the existing UNet framework (DPA-UNet) to achieve accurate vessel segmentation. This approach entails the integration of a depthwise convolution block in the downsampling path and a parallel attention mechanism in the upsampling path of UNet. The primary benefit of depthwise convolution and global information embedding (GIE) is the ability to capture intricate information characteristics across channels. This helps to minimize the information degradation caused by conventional convolution and downsampling techniques. A parallel attention network is proposed in the upsampling path of the existing UNet to optimize the channel and spatial information acquired from the encoder-decoder. Extensive experiments are conducted on three publicly available datasets, namely DRIVE, STARE, and CHASE_DB1, to validate the performance of the proposed model. The findings indicate that the UNET model with depthwise parallel attention achieved a competitive performance with fewer network parameters in segmenting retinal vessels.

We present a fully automated method for carotid artery (CA) outer wall segmentation in black blood MRI using partially annotated data and compare it to the state-of-the-art reference model. Our model was trained and tested on multicentric data of patients (106 and 23 patients, respectively) with a carotid plaque and was validated on different MR sequences (24 patients) as well as data that were acquired with MRI systems of a different vendor (34 patients). A 3D nnU-Net was trained on pre-contrast T1w turbo spin echo (TSE) MR images. A CA centerline sliding window approach was chosen to refine the nnU-Net segmentation using an additionally trained 2D U-Net to increase agreement with manual annotations. To improve segmentation performance in areas with semantically and visually challenging voxels, Monte-Carlo dropout was used. To increase generalizability, data were augmented with intensity transformations. Our method achieves state-of-the-art results yielding a Dice similarity coefficient (DSC) of 91.7% (interquartile range (IQR) 3.3%) and volumetric intraclass correlation (ICC) with ground truth of 0.90 on the development domain data and a DSC of 91.1% (IQR 7.2%) and volumetric ICC with ground truth of 0.83 on the external domain data outperforming top-ranked methods for open-source CA segmentation. The uncertainty-based approach increases the interpretability of the proposed method by providing an uncertainty map together with the segmentation.

Diseases of coronary artery are deliberated as one of the most common heart diseases leading to death worldwide. For early detection of such disease, the X-ray angiography is a benchmark imaging modality for diagnosing such illness. The acquired X-ray angiography images usually suffer from low quality and the presence of noise. Therefore, for developing a computer-aided diagnosis (CAD) system, vessel enhancement and segmentation play significant role. In this paper, an optimized adapter filter based on Frangi filter was proposed for superior segmentation of the angiography images using genetic algorithm (GA). The original angiography image is initially preprocessed to enhance its contrast followed by generating the vesselness map using the proposed optimized Frangi filter. Then, a segmentation technique is applied to extract only the artery vessels, where the proposed system for extracting only the main vessel was evaluated. The experimental results on angiography images established the superiority of the vessel regions extraction showing 98.58% accuracy compared to the state-of-the-art.

Abstract Background Image-domain motion correction of black-blood contrast T2-weighted fetal cardiovascular magnetic resonance imaging (CMR) using slice-to-volume registration (SVR) provides high-resolution three-dimensional (3D) images of the fetal heart providing excellent 3D visualisation of vascular anomalies [1]. However, 3D segmentation of these datasets, important for both clinical reporting and the application of advanced analysis techniques is currently a time-consuming process requiring manual input with potential for inter-user variability. Methods In this work, we present novel 3D fetal CMR population-averaged atlases of normal and abnormal fetal cardiovascular anatomy. The atlases are created using motion-corrected 3D reconstructed volumes of 86 third trimester fetuses (gestational age range 29-34 weeks) including: 28 healthy controls, 20 cases with postnatally confirmed neonatal coarctation of the aorta (CoA) and 38 vascular rings (21 right aortic arch (RAA), 17 double aortic arch (DAA)). We used only high image quality datasets with isolated anomalies and without any other deviations in the cardiovascular anatomy.In addition, we implemented and evaluated atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label segmentation of fetal cardiac vessels. We used images from CoA, RAA and DAA cohorts including: 42 cases for training (14 from each cohort), 3 for validation and 6 for testing. In addition, the potential limitations of the network were investigated on unseen datasets including 3 early gestational age (22 weeks) and 3 low SNR cases. Results We created four atlases representing the average anatomy of the normal fetal heart, postnatally confirmed neonatal CoA, RAA and DAA. Visual inspection was undertaken to verify expected anatomy per subgroup. The results of the multi-label cardiac vessel UNETR segmentation showed 100 $$\%$$ % per-vessel detection rate for both normal and abnormal aortic arch anatomy. Conclusions This work introduces the first set of 3D black-blood T2-weighted CMR atlases of normal and abnormal fetal cardiovascular anatomy including detailed segmentation of the major cardiovascular structures. Additionally, we demonstrated the general feasibility of using deep learning for multi-label vessel segmentation of 3D fetal CMR images.

Detection of blood vessels in retinal images is an important step in any computer-aided pathological system for the early screening and detection of eye-related ailments such as retinal detachment, diabetic retinopathy, and macular degeneration. Propriety of the vessel enhancement process, as a pre-processing step, has been well established in medical corpus, for enhanced accuracy of vessel segmentation. Algorithms for retinal image extraction are still not qualitatively sufficient to be appropriate for diagnostics. This paper presents an effective and robust approach for retinal vessel enhancement that overcome prevailing deficiencies, using Morphological Closing based Dynamic Mode Decomposition (MC-DMD). The proffered algorithm exploits the power of mathematical morphology for the generation of input channel to the Dynamic Mode Decompostion (DMD) system, decomposing the vessel and non-vessel features of retinal images. We confirmed the effectiveness of the proposed enhancement method on three publicly available retinal image datasets: DRIVE, STARE and HRF, across nine existing vessel enhancement methods in terms of Receiver Operating Characteristic (ROC) curve and Area Under the ROC Curve (AUC). In addition, segmentation on final vessel map is performed and validated by enhanced performance in comparison with eight conventional vessel segmentation algorithms in terms of Sensitivity (SEN), Specificity (SP), Accuracy (ACC).

Background: Ultra-Wide-Field (UWF) fundus imaging is an essential diagnostic tool for identifying ophthalmologic diseases, as it captures detailed retinal structures within a wider field of view (FOV). However, the presence of eyelashes along the edge of the eyelids can cast shadows and obscure the view of fundus imaging, which hinders reliable interpretation and subsequent screening of fundus diseases. Despite its limitations, there are currently no effective methods or datasets available for removing eyelash artifacts from UWF fundus images. This research aims to develop an effective approach for eyelash artifact removal and thus improve the visual quality of UWF fundus images for accurate analysis and diagnosis.Methods: To address this issue, we first constructed two UWF fundus datasets: the paired synthetic eyelashes (PSE) dataset and the unpaired real eyelashes (uPRE) dataset. Then we proposed a deep learning architecture called Joint Conditional Generative Adversarial Networks (JcGAN) to remove eyelash artifacts from UWF fundus images. JcGAN employs a shared generator with two discriminators for joint learning of both real and synthetic eyelash artifacts. Furthermore, we designed a background refinement module that refines background information and is trained with the generator in an end-to-end manner.Results: Experimental results on both PSE and uPRE datasets demonstrate the superiority of the proposed JcGAN over several state-of-the-art deep learning approaches. Compared with the best existing method, JcGAN improves PSNR and SSIM by 4.82% and 0.23%, respectively. In addition, we also verified that eyelash artifact removal via JcGAN could significantly improve vessel segmentation performance in UWF fundus images. Assessment via vessel segmentation illustrates that the sensitivity, Dice coefficient and area under curve (AUC) of ResU-Net have respectively increased by 3.64%, 1.54%, and 1.43% after eyelash artifact removal using JcGAN.Conclusion: The proposed JcGAN effectively removes eyelash artifacts in UWF images, resulting in improved visibility of retinal vessels. Our method can facilitate better processing and analysis of retinal vessels and has the potential to improve diagnostic outcomes.

Some ocular and cardiovascular diseases can be detected through the increased tortuosity of retinal blood vessels. Objective tortuosity measures can be obtained from digital image analysis of a retinography. This study tested a set of local tortuosity indices under a change in the frame center (macula, optic disc) of the eye fundus image. We illustrate the effects of such a change on 40 pairs of vessels evaluated with eight tortuosity indices. We show that the frame center change caused significant differences in the mean values of the vast majority of the tortuosity indices analyzed. The index defined as the ratio of the curvature to the arc length of a vessel segment proved to be the most robust in relation to a frame center change. Experimental results obtained from the analysis of clinical images are provided and discussed. [ABSTRACT FROM AUTHOR]

Development of energy-efficient and high-performance bioreactors requires progress in methods for assessing the key parameters of the biosynthesis process. With a wide variety of approaches and methods for determining the phase contact area in gas–liquid flows, the question of obtaining its accurate quantitative estimation remains open. Particularly challenging are the issues of getting information about the mass transfer coefficients instantly, as well as the development of predictive capabilities for the implementation of effective flow control in continuous fermentation both on the laboratory and industrial scales. Motivated by the opportunity to explore the possibility of applying classical and non-classical computer vision methods to the results of high-precision video records of bubble flows obtained during the experiment in the bioreactor vessel, we obtained a number of results presented in the paper. Characteristics of the bioreactor's bubble flow were estimated first by classical computer vision (CCV) methods including an elliptic regression approach for single bubble boundaries selection and clustering, image transformation through a set of filters and developing an algorithm for separation of the overlapping bubbles. The application of the developed method for the entire video filming makes it possible to obtain parameter distributions and set dropout thresholds in order to obtain better estimates due to averaging. The developed CCV methodology was also tested and verified on a collected and labeled manual dataset. An onwards deep neural network (NN) approach was also applied, for instance the segmentation task, and has demonstrated certain advantages in terms of high segmentation resolution, while the classical one tends to be more speedy. Thus, in the current manuscript both advantages and disadvantages of the classical computer vision method (CCV) and neural network approach (NN) are discussed based on evaluation of bubbles' number and their area defined. An approach to mass transfer coefficient estimation methodology in virtue of obtained results is also represented. [ABSTRACT FROM AUTHOR]

As a core technique to quantitatively assess the stenosis severity of coronary arteries, quantitative coronary analysis (QCA) is urgently supposed to become more automated and intelligent, especially for regions lacking expertise and technology. The existing QCA methods highly depend on manual operation, which is time-consuming and subject to personal experience. This study innovatively proposes a fully automatic QCA workflow based on artificial intelligence (AI-QCA), which can quickly and accurately make a quantitative assessment of stenosis severity. The whole AI-QCA workflow mainly consists of three parts: the boundary-aware segmentation on the coronary angiogram (CAG) images, the AI-enabled coronary artery tree construction, and the diameter fitting and stenosis detection. Experiments show that the precision, recall, and F1 score of the segmentation, evaluated on 1322 CAGs, are 0.866, 0.897, and 0.879, respectively. Furthermore, the RMSE between diameter stenosis assessed by AI-QCA and manual QCA served by senior experts, evaluated on 249 CAGs, is 0.064, and the Pearson coefficient is 0.765. Meanwhile, the operation time can be reduced from tens of minutes to several seconds by AI-QCA. As a conclusion, the proposed AI-QCA is able to quickly quantify stenosis parameters as accurately as senior experts, which is significant for the intelligent diagnosis and treatment of coronary artery disease. [ABSTRACT FROM AUTHOR]

Glaucoma, hypertension, obesity, diabetes, etc. are the widely spread severe diseases nowadays. Glaucoma, hypertension, and diabetes are the main cause of vision loss, whereas diabetes, obesity, and hypertension are the basis of several other highly dangerous diseases. Blood vessels of a retina contain information about these critical diseases. Health professionals use this information to detect and diagnose these diseases. Hence, it is essential to segment retinal blood vessels. Many researchers have proposed different matched filter methods to segment retinal blood vessels, but their matched filter kernels are not appropriate to vessel intensity profile due to which performances of these methods are relatively low. Also, the quality of retinal images directly affects the accuracy of segmentation. Therefore, retinal images must be of good quality. Existing methods for retinal image enhancement are less efficient. The proposed method introduces the Multiscale switching morphological operator (MSMO) with Wald probability distribution function-based new matched filter for better enhancement and segmentation of retinal vessels in this paper. The proposed method is tested on two known datasets: DRIVE and STARE. The average value of the precision, specificity, accuracy, MSE and MAD of the proposed method are 83.74%, 98.80%, 95.58%, 0.0442, 0.0366 for DRIVE and 71.24%, 97.67%, 94.89%, 0.0511, 0.015 for STARE dataset. Results demonstrate significant improvement in the performance of the proposed method over existing state-of-the-art methods. The causes of improved performance are enhanced retinal images due to using a better pre-processing method and close matching of Wald matched filter kernel with vessel intensity profile. [ABSTRACT FROM AUTHOR]

Segmentation of retinal vessel images is critical to the diagnosis of retinopathy. Recently, convolutional neural networks have shown significant ability to extract the blood vessel structure. However, it remains challenging to refined segmentation for the capillaries and the edges of retinal vessels due to thickness inconsistencies and blurry boundaries. In this paper, we propose a novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss (SPNet) to address the above problems. Specifically, we introduce a decoder-sharing mechanism to capture multi-scale semantic information, where feature maps at diverse scales are decoded through a sequence of weight-sharing decoder modules. Also, to strengthen characterization on the capillaries and the edges of blood vessels, we define a residual pyramid architecture which decomposes the spatial information in the decoding phase. A pyramid-like loss function is designed to compensate possible segmentation errors progressively. Experimental results on public benchmarks show that the proposed method outperforms the backbone network and most state-of-the-art methods, especially in the regions of the capillaries and the vessel contours. In addition, performances on cross-datasets verify that SPNet shows stronger generalization ability. [ABSTRACT FROM AUTHOR]

Computer-assisted technologies have made significant progress in fetoscopic laser surgery, including placental vessel segmentation. However, the intra- and inter-procedure variabilities in the state-of-the-art segmentation methods remain a significant hurdle. To address this, we investigated the use of conditional generative adversarial networks (cGANs) for fetoscopic image segmentation and compared their performance with the benchmark U-Net technique for placental vessel segmentation. Two deep-learning models, U-Net and pix2pix (a popular cGAN model), were trained and evaluated using a publicly available dataset and an internal validation set. The overall results showed that the pix2pix model outperformed the U-Net model, with a Dice score of 0.80 [0.70; 0.86] versus 0.75 [0.0.60; 0.84] (p-value < 0.01) and an Intersection over Union (IoU) score of 0.70 [0.61; 0.77] compared to 0.66 [0.53; 0.75] (p-value < 0.01), respectively. The internal validation dataset further validated the superiority of the pix2pix model, achieving Dice and IoU scores of 0.68 [0.53; 0.79] and 0.59 [0.49; 0.69] (p-value < 0.01), respectively, while the U-Net model obtained scores of 0.53 [0.49; 0.64] and 0.49 [0.17; 0.56], respectively. This study successfully compared U-Net and pix2pix models for placental vessel segmentation in fetoscopic images, demonstrating improved results with the cGAN-based approach. However, the challenge of achieving generalizability still needs to be addressed.

Background: Image-domain motion correction of black-blood contrast T2-weighted fetal cardiovascular magnetic resonance imaging (CMR) using slice-to-volume registration (SVR) provides high-resolution three-dimensional (3D) images of the fetal heart providing excellent 3D visualisation of vascular anomalies [1]. However, 3D segmentation of these datasets, important for both clinical reporting and the application of advanced analysis techniques is currently a time-consuming process requiring manual input with potential for inter-user variability. Methods: In this work, we present novel 3D fetal CMR population-averaged atlases of normal and abnormal fetal cardiovascular anatomy. The atlases are created using motion-corrected 3D reconstructed volumes of 86 third trimester fetuses (gestational age range 29-34 weeks) including: 28 healthy controls, 20 cases with postnatally confirmed neonatal coarctation of the aorta (CoA) and 38 vascular rings (21 right aortic arch (RAA), 17 double aortic arch (DAA)). We used only high image quality datasets with isolated anomalies and without any other deviations in the cardiovascular anatomy.In addition, we implemented and evaluated atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label segmentation of fetal cardiac vessels. We used images from CoA, RAA and DAA cohorts including: 42 cases for training (14 from each cohort), 3 for validation and 6 for testing. In addition, the potential limitations of the network were investigated on unseen datasets including 3 early gestational age (22 weeks) and 3 low SNR cases. Results: We created four atlases representing the average anatomy of the normal fetal heart, postnatally confirmed neonatal CoA, RAA and DAA. Visual inspection was undertaken to verify expected anatomy per subgroup. The results of the multi-label cardiac vessel UNETR segmentation showed 100 % per-vessel detection rate for both normal and abnormal aortic arch anatomy. Conclusions: This work introduces the first set of 3D black-blood T2-weighted CMR atlases of normal and abnormal fetal cardiovascular anatomy including detailed segmentation of the major cardiovascular structures. Additionally, we demonstrated the general feasibility of using deep learning for multi-label vessel segmentation of 3D fetal CMR images. [ABSTRACT FROM AUTHOR]

As an important basis of clinical diagnosis, the morphology of retinal vessels is very useful for the early diagnosis of some eye diseases. In recent years, with the rapid development of deep learning technology, automatic segmentation methods based on it have made considerable progresses in the field of retinal blood vessel segmentation. However, due to the complexity of vessel structure and the poor quality of some images, retinal vessel segmentation, especially the segmentation of Capillaries, is still a challenging task. In this work, we propose a new retinal blood vessel segmentation method, called multi-feature segmentation, based on collaborative patches. First, we design a new collaborative patch training method which effectively compensates for the pixel information loss in the patch extraction through information transmission between collaborative patches. Additionally, the collaborative patch training strategy can simultaneously have the characteristics of low occupancy, easy structure and high accuracy. Then, we design a multi-feature network to gather a variety of information features. The hierarchical network structure, together with the integration of the adaptive coordinate attention module and the gated self-attention module, enables these rich information features to be used for segmentation. Finally, we evaluate the proposed method on two public datasets, namely DRIVE and STARE, and compare the results of our method with those of other nine advanced methods. The results show that our method outperforms other existing methods. [ABSTRACT FROM AUTHOR]

Optical coherence tomography angiography (OCTA) is an imaging modality that can be used for analyzing retinal vasculature. Quantitative assessment of en face OCTA images requires accurate segmentation of the capillaries. Using deep learning approaches for this task faces two major challenges. First, acquiring sufficient manual delineations for training can take hundreds of hours. Second, OCTA images suffer from numerous contrast-related artifacts that are currently inherent to the modality and vary dramatically across scanners. We propose to solve both problems by learning a disentanglement of an anatomy component and a local contrast component from paired OCTA scans. With the contrast removed from the anatomy component, a deep learning model that takes the anatomy component as input can learn to segment vessels with a limited portion of the training images being manually labeled. Our method demonstrates state-of-the-art performance for OCTA vessel segmentation. [ABSTRACT FROM AUTHOR]

A frequent and sometimes sight-threatening consequence of diabetes is diabetic retinopathy. In order to diagnose and track diabetic retinopathy, retinal blood vessels must be accurately identified early on and segmented. The improvements in vessel segmentation methods for the identification of diabetic retinopathy are summarised in this abstract. Due to the intricate structure and diversity of blood vessels, as well as the presence of noise and artefacts, vascular segmentation in retinal pictures is a difficult process. In order to overcome these difficulties and increase the precision of vessel segmentation, a number of approaches have been developed. Feature extraction, classification, post-processing, and picture pre-processing are frequently combined in these methods. Recent research have demonstrated encouraging outcomes in vascular segmentation using a suggested framework utilising hybrid models. To extract pertinent information from retinal pictures, the framework uses pre-processing techniques such cropping, colour space conversion, and contrast augmentation. Gabor filtering and texture analysis are two techniques for feature extraction that effectively capture specific vessel properties. Vessel and non-vessel pixels are distinguished using classification techniques like K-means clustering and ensemble classifiers. The vessel segmentation findings are refined using post-processing techniques including morphological operations and linked component analysis. The STARE dataset and other benchmark datasets used for this approach evaluation showed great accuracy, specificity, and sensitivity. However, there are still issues with establishing high specificity and good sensitivity in vessel segmentation. More investigation is required to enhance vascular abnormality identification and lessen false-positive and false-negative mistakes. The improvements in vascular segmentation techniques help to identify and monitor diabetic retinopathy early, allowing for prompt therapies to avert vision loss. The suggested framework and hybrid models have the potential to improve vessel segmentation's precision and effectiveness. The integration of deep learning methodologies and the creation of reliable, automated systems for healthcare applications may be future research priorities. [ABSTRACT FROM AUTHOR]

Morphological and functional changes in retinal vessels are indicators of a variety of chronic diseases, such as diabetes, stroke, and hypertension. However, without a large number of high-quality annotations, existing deep learning-based medical image segmentation approaches may degrade their performance dramatically on the retinal vessel segmentation task. To reduce the demand of high-quality annotations and make full use of massive unlabeled data, we propose a self-supervised multi-task strategy to extract curvilinear vessel features for the retinal vessel segmentation task. Specifically, we use a dense network to extract more vessel features across different layers/slices, which is elaborately designed for hardware to train and test efficiently. Then, we combine three general pre-training tasks (i.e., intensity transformation, random pixel filling, in-painting and out-painting) in an aggregated way to learn rich hierarchical representations of curvilinear retinal vessel structures. Furthermore, a vector classification task module is introduced as another pre-training task to obtain more spatial features. Finally, to make the segmentation network pay more attention to curvilinear structures, a novel dynamic loss is proposed to learn robust vessel details from unlabeled fundus images. These four pre-training tasks greatly reduce the reliance on labeled data. Moreover, our network can learn the retinal vessel features effectively in the pre-training process, which leads to better performance in the target multi-modal segmentation task. Experimental results show that our method provides a promising direction for the retinal vessel segmentation task. Compared with other state-of-the-art supervised deep learning-based methods applied, our method requires less labeled data and achieves comparable segmentation accuracy. For instance, we match the accuracy of the traditional supervised learning methods on DRIVE and Vampire datasets without needing any labeled ground truth image. With elaborately training, we gain the 0.96 accuracy on DRIVE dataset. [ABSTRACT FROM AUTHOR]

The morphological features of vasculature in diseased tissue differ significantly from those in normal tissue. Therefore, vasculature quantification is crucial for disease diagnosis and staging. Ultrasound microvessel imaging (UMI) with ultrafast ultrasound acquisitions has been determined to have potential in clinical applications given its superior sensitivity in blood flow detection. However, the presence of spatial-dependent noise caused by a low imaging signal-to-noise ratio and incoherent clutter artifacts caused by moving hyperechoic scatterers degrades the performance of UMI and the reliability of vascular quantification. To tackle these issues, we proposed an improved UMI technique along with an adaptive vessel segmentation workflow for robust vessel identification and vascular feature quantification. A previously proposed sub-aperture cross-correlation technique and a normalized cross-correlation technique were applied to equalize the spatially dependent noise level and suppress the incoherent clutter artifact. A square operator and non-local means filter were then used to better separate the blood flow signal from residual background noise. On the de-noised ultrasound microvessel image, an automatic and adaptive vessel segmentation method was developed based on the different spatial patterns of blood flow signal and background noise. The proposed workflow was applied to a CIRS phantom, to a Doppler flow phantom and to an inflammatory bowel, kidney and liver, to validate its feasibility. Results revealed that automatic adaptive, and robust vessel identification performance can be achieved using the proposed method without the subjectivity caused by radiologists/operators. [ABSTRACT FROM AUTHOR]

Automatic vessel structure segmentation is essential for an automatic disease diagnosis system. The task is challenging due to vessels' different shapes and sizes across populations. This paper proposes a multiscale network with dual attention to segment various retinal blood vessels. The network injects a spatial attention module and channel attention module on a feature map, whose size is one-eighth of the input size. The network also uses multiscale input to receive multi-level information, and the network uses the multiscale output to gain more supervision. The proposed method is tested on two publicly available datasets: DRIVE and CHASEDB1. The accuracy, AUC, sensitivity, and specificity on the DRIVE dataset are 0.9615, 0.9866, 0.7709, and 0.9847, respectively. On the CHASEDB1 dataset, the metrics are 0.9800, 0.9892, 0.8215, and 0.9877, respectively. The ablative study further shows effectiveness for each part of the network. Multiscale and dual attention mechanism both improve performance. The proposed architecture is simple and effective. The inference time is 12 ms on a GPU and has potential for real-world applications. The code will be made publicly available. [ABSTRACT FROM AUTHOR]

Purpose: Coronary artery segmentation in coronary computed tomography angiography (CTA) images plays a crucial role in diagnosing cardiovascular diseases. However, due to the complexity of coronary CTA images and coronary structure, it is difficult to automatically segment coronary arteries accurately and efficiently from numerous coronary CTA images. Method: In this study, an automatic method based on symmetrical radiation filter (SRF) and D-means is presented. The SRF, which is applied to the three orthogonal planes, is designed to filter the suspicious vessel tissue according to the features of gradient changes on vascular boundaries to segment coronary arteries accurately and reduce computational cost. Additionally, the D-means local clustering is proposed to be embedded into vessel segmentation to eliminate noise impact in coronary CTA images. Results: The results of the proposed method were compared against the manual delineations in 210 coronary CTA data sets. The average values of true positive, false positive, Jaccard measure, and Dice coefficient were 0.9541 ± 0.0651 , 0.0812 ± 0.1024 , 0.8894 ± 0.1214 , and 0.9318 ± 0.0833 , respectively. Moreover, comparing the delineated data sets and public data sets showed that the proposed method is better than the related methods. Conclusion: The experimental results indicate that the proposed method can perform complete, robust, and accurate segmentation of coronary arteries with low computational cost. Therefore, the proposed method is proven effective in vessel segmentation of coronary CTA images without extensive training data and can meet clinical applications. [ABSTRACT FROM AUTHOR]

A retinal vessel analysis is a procedure that can be used as an assessment of risks to the eye. This work proposes an unsupervised multimodal approach that improves the response of the Frangi filter, enabling automatic vessel segmentation. We propose a filter that computes pixel-level vessel continuity while introducing a local tolerance heuristic to fill in vessel discontinuities produced by the Frangi response. This proposal, called the local-sensitive connectivity filter (LS-CF), is compared against a naive connectivity filter to the baseline thresholded Frangi filter response and to the naive connectivity filter response in combination with the morphological closing and to the current approaches in the literature. The proposal was able to achieve competitive results in a variety of multimodal datasets. It was robust enough to outperform all the state-of-the-art approaches in the literature for the OSIRIX angiographic dataset in terms of accuracy and 4 out of 5 works in the case of the IOSTAR dataset while also outperforming several works in the case of the DRIVE and STARE datasets and 6 out of 10 in the CHASE-DB dataset. For the CHASE-DB, it also outperformed all the state-of-the-art unsupervised methods. [ABSTRACT FROM AUTHOR]

The accurate vessel segmentation for retinal image is the most conducive to early diagnosis of various eye-related diseases. Most deep learning models are used to segment the vessel by green channel grey image and random sampling of whole image that lead to insufficient training samples and low accuracy probably. To address this issue, a novel retinal vessel segmentation model based on deep learning is proposed, which is called Multichannel U-Net (M-UNet) combined with multi-scale equalization sampling for extracting vessel networks. The multi-scale equalization sampling patches are used to splice an image as new data. And the M-UNet structure is utilized to train the retinal vessel segmentation model. The input of the model is the three channel image replacing the grey image. The DRIVE and STARE database are used to evaluate the performance. Experimental results indicate that the proposed method can obtain better vessel networks, especially for the extraction of peripheral vascular structure. The average accuracy of DRIVE is 0.9716, sensitivity is 0.8168, specificity is 0.9860, and Area Under Curve (AUC) is up to 0.9843. The performances are more competitive than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Automatic optical coherence tomography angiography (OCTA) vessel segmentation is of great significance to retinal disease diagnoses. Due to the complex vascular structure, however, various existing factors make the segmentation task challenging. This paper reports a novel end‐to‐end three‐stage channel and position attention (CPA) module integrated graph reasoning convolutional neural network (CGNet) for retinal OCTA vessel segmentation. Specifically, in the coarse stage, both CPA and graph reasoning network (GRN) modules are integrated in between a U‐shaped neural network encoder and decoder to acquire vessel confidence maps. After being directed into a fine stage, such confidence maps are concatenated with the original image and the generated fine image map as a 3‐channel image to refine retinal micro‐vasculatures. Finally, both the fine and refined images are fused at the refining stage as the segmentation results. Experiments with different public datasets are conducted to verify the efficacy of the proposed CGNet. Results show that by employing the end‐to‐end training scheme and the integrated CPA and GRN modules, CGNet achieves 94.29% and 85.62% in area under the ROC curve (AUC) for the two different datasets, outperforming the state‐of‐the‐art existing methods with both improved operability and reduced complexity in different cases. Code is available at https://github.com/GE-123-cpu/CGnet-for-vessel-segmentation. [ABSTRACT FROM AUTHOR]