Search

Retinal vessel segmentation has various applications in the biomedical field. This includes early disease detection, biometric authentication using retinal scans, classification and others. Many of these applications rely critically on an accurate and efficient segmentation technique. In the existing literature, a lot of work has been done to improve the accuracy of the segmentation task, but it relies heavily on the amount of data available for training as well as the quality of the images captured. Another gap is observed in terms of the resources used in these heavily trained algorithms. This paper aims to address these gaps by using a resource-efficient unsupervised technique and also increasing the accuracy of retinal vessel segmentation using the Fourier decomposition method (FDM) along with the Gabor transform for image signals. The proposed method has an accuracy of 97.39%, 97.62%, 95.34%, and 96.57% on DRIVE, STARE, CHASE_DB1, and HRF datasets, respectively. The sensitivities were found to be 88.36%, 88.51%, 90.37%, and 79.07%, respectively. A separate section makes a detailed comparison of the proposed method with several well-known methods and an analysis of the efficiency of the proposed method. The proposed method proves to be efficient in terms of time and resource requirements. [ABSTRACT FROM AUTHOR]

Liver vessel segmentation in computed tomography represents a highly challenging task due to the imbalanced distribution within the liver parenchyma, the small and branched vessels with decreased image contrast to surrounding tissue and in general, due to the scarcity of highresolution and -contrast images, which hampers the efficient training of deep learning-based approaches. This study applies two state-of-the-art networks, the fully convolutional nnUnet and the transformer-based VT-Unet to three publicly available datasets, 3DIRCADb, one task of the Medical Segmentation Decathlon (MSD) and the more recent LiVS dataset. The nnUnet achieved Dice scores of 0.761, 0.714, and 0.696 on the 3DIRCADb, LiVS, and MSD datasets, respectively. In contrast, the experiments with the VT-UNet resulted in Dice scores of 0.795, 0.713, and 0.610. These findings indicates good accordance of the performance of the nnUnet and the transformer-based VT-Unet, with differences regarding individual datasets. Both network variants show competitive performances regarding the current state-of-the-art, yet the need for large-scale and high-quality datasets becomes evident to further enhance the accuracy of liver vessel segmentation.

Abstract To solve the issue of diagnosis accuracy of diabetic retinopathy (DR) and reduce the workload of ophthalmologists, in this paper we propose a prior-guided attention fusion Transformer for multi-lesion segmentation of DR. An attention fusion module is proposed to improve the key generator to integrate self-attention and cross-attention and reduce the introduction of noise. The self-attention focuses on lesions themselves, capturing the correlation of lesions at a global scale, while the cross-attention, using pre-trained vessel masks as prior knowledge, utilizes the correlation between lesions and vessels to reduce the ambiguity of lesion detection caused by complex fundus structures. A shift block is introduced to expand association areas between lesions and vessels further and to enhance the sensitivity of the model to small-scale structures. To dynamically adjust the model’s perception of features at different scales, we propose the scale-adaptive attention to adaptively learn fusion weights of feature maps at different scales in the decoder, capturing features and details more effectively. The experimental results on two public datasets (DDR and IDRiD) demonstrate that our model outperforms other state-of-the-art models for multi-lesion segmentation.

Abstract This study introduces a novel self-supervised learning method for single-frame subtraction and vessel segmentation in coronary angiography, addressing the scarcity of annotated medical samples in AI applications. We pretrain a U-Net model on a large dataset of unannotated coronary angiograms using an image-to-image translation framework, then fine-tune it on a limited set of manually annotated samples. The pretrained model excels at comprehensive single-frame subtraction, outperforming existing DSA methods. Fine-tuning with just 40 samples yields a Dice coefficient of 0.828 for vessel segmentation. On the public XCAD dataset, our model sets a new state-of-the-art benchmark with a Dice coefficient of 0.755, surpassing both unsupervised and supervised learning approaches. This method achieves robust single-frame subtraction and demonstrates that combining pretraining with minimal fine-tuning enables accurate coronary vessel segmentation with limited manual annotations. We successfully apply this approach to assist physicians in visualizing potential vascular stenosis sites during coronary angiography. Code, dataset, and a live demo will be available available at: https://github.com/newfyu/DeepSA .

This study introduces a novel self-supervised learning method for single-frame subtraction and vessel segmentation in coronary angiography, addressing the scarcity of annotated medical samples in AI applications. We pretrain a U-Net model on a large dataset of unannotated coronary angiograms using an image-to-image translation framework, then fine-tune it on a limited set of manually annotated samples. The pretrained model excels at comprehensive single-frame subtraction, outperforming existing DSA methods. Fine-tuning with just 40 samples yields a Dice coefficient of 0.828 for vessel segmentation. On the public XCAD dataset, our model sets a new state-of-the-art benchmark with a Dice coefficient of 0.755, surpassing both unsupervised and supervised learning approaches. This method achieves robust single-frame subtraction and demonstrates that combining pretraining with minimal fine-tuning enables accurate coronary vessel segmentation with limited manual annotations. We successfully apply this approach to assist physicians in visualizing potential vascular stenosis sites during coronary angiography. Code, dataset, and a live demo will be available available at: . [ABSTRACT FROM AUTHOR]

Patients with bicuspid aortic valve (BAV) commonly have associated aortic stenosis and aortopathy. The geometry of the aortic arch and BAV is not well defined quantitatively, which makes clinical classifications subjective or reliant on limited 2D measurements. The goal of this study was to characterize the 3D geometry of the aortic arch and BAV using objective and quantitative techniques. Pre-TAVR computed tomography angiogram (CTA) in patients with BAV and aortic stenosis (AS) were analyzed (n = 59) by assessing valve commissural angle, presence of a fused region, percent of fusion, and calcium volume. The ascending aorta and aortic arch were reconstructed from patient-specific imaging segmentation to generate a centerline and calculate maximum curvature and maximum area change for the ascending aorta and the descending aorta. Aortic valve commissural angle signified a bimodal distribution suggesting tricuspid-like (≤ 150°, 52.5% of patients) and bicuspid-like (> 150°, 47.5%) morphologies. Tricuspid like was further classified by partial (10.2%) or full (42.4%) fusion, and bicuspid like was further classified into valves with fused region (27.1%) or no fused region (20.3%). Qualitatively, the aortic arch was found to have complex patient-specific variations in its 3D shape with some showing extreme diameter changes and kinks. Quantitatively, subgroups were established using maximum curvature threshold of 0.04 and maximum area change of 30% independently for the ascending and descending aorta. These findings provide insight into the geometric structure of the aortic valve and aortic arch in patients presenting with BAV and AS where 3D characterization allows for quantitative classification of these complex anatomic structures. [ABSTRACT FROM AUTHOR]

Purpose: VESCL (pronounced 'vessel') is a novel vessel contouring library for computer-assisted 2D vessel contouring and segmentation. VESCL facilitates manual vessel segmentation in 2D medical images to generate gold-standard datasets for training, testing, and validating automatic vessel segmentation. Methods: VESCL is an open-source C++ library designed for easy integration into medical image processing systems. VESCL provides an intuitive interface for drawing variable-width parametric curves along vessels in 2D images. It includes highly optimized localized filtering to automatically fit drawn curves to the nearest vessel centerline and automatically determine the varying vessel width along each curve. To support a variety of segmentation paradigms, VESCL can export multiple segmentation representations including binary segmentations, occupancy maps, and distance fields. Results: VESCL provides sub-pixel resolution for vessel centerlines and vessel widths. It is optimized to segment small vessels with single- or sub-pixel widths that are visible to the human eye but hard to segment automatically via conventional filters. When tested on neurovascular digital subtraction angiography (DSA), VESCL's intuitive hand-drawn input with automatic curve fitting increased the speed of fully manual segmentation by 22× over conventional methods and by 3× over the best publicly available computer-assisted manual segmentation method. Accuracy was shown to be within the range of inter-operator variability of gold standard manually segmented data from a publicly available dataset of neurovascular DSA images as measured using Dice scores. Preliminary tests showed similar improvements for segmenting DSA of coronary arteries and RGB images of retinal arteries. Conclusion: VESCL is an open-source C++ library for contouring vessels in 2D images which can be used to reduce the tedious, labor-intensive process of manually generating gold-standard segmentations for training, testing, and comparing automatic segmentation methods. [ABSTRACT FROM AUTHOR]

Laser speckle contrast imaging (LSCI) is a noninvasive, label-free technique that allows real-time investigation of the microcirculation situation of biological tissue. High-quality microvascular segmentation is critical for analyzing and evaluating vascular morphology and blood flow dynamics. However, achieving high-quality vessel segmentation has always been a challenge due to the cost and complexity of label data acquisition and the irregular vascular morphology. In addition, supervised learning methods heavily rely on high-quality labels for accurate segmentation results, which often necessitate extensive labeling efforts. Here, we propose a novel approach LSWDP for high-performance real-time vessel segmentation that utilizes low-quality pseudo-labels for nonmatched training without relying on a substantial number of intricate labels and image pairing. Furthermore, we demonstrate that our method is more robust and effective in mitigating performance degradation than traditional segmentation approaches on diverse style data sets, even when confronted with unfamiliar data. Importantly, the dice similarity coefficient exceeded 85% in a rat experiment. Our study has the potential to efficiently segment and evaluate blood vessels in both normal and disease situations. This would greatly benefit future research in life and medicine. [ABSTRACT FROM AUTHOR]

Accurate segmentation of retinal vessels is crucial for the early diagnosis and treatment of eye diseases, for example, diabetic retinopathy, glaucoma, and macular degeneration. Due to the intricate structure of retinal vessels, it is essential to extract their features with precision for the semantic segmentation of medical images. In this study, an improved deep learning neural network was developed with a focus on feature extraction based on the U‐Net structure. The enhanced U‐Net combines the architecture of convolutional neural networks (CNNs) with SE blocks (squeeze‐and‐excitation blocks) to adaptively extract image features after each U‐Net encoder's convolution. This approach aids in suppressing nonvascular regions and highlighting features for specific segmentation tasks. The proposed method was trained and tested on the DRIVECHASE_DB1 and STARE datasets. As a result, the proposed model had an algorithmic accuracy, sensitivity, specificity, Dice coefficient (Dc), and Matthews correlation coefficient (MCC) of 95.62/0.9853/0.9652, 0.7751/0.7976/0.7773, 0.9832/0.8567/0.9865, 82.53/87.23/83.42, and 0.7823/0.7987/0.8345, respectively, outperforming previous methods, including UNet++, attention U‐Net, and ResUNet. The experimental results demonstrated that the proposed method improved the retinal vessel segmentation performance. [ABSTRACT FROM AUTHOR]

Abstract Background Segmenting liver vessels from contrast-enhanced computed tomography images is essential for diagnosing liver diseases, planning surgeries and delivering radiotherapy. Nevertheless, identifying vessels is a challenging task due to the tiny cross-sectional areas occupied by vessels, which has posed great challenges for vessel segmentation, such as limited features to be learned and difficult to construct high-quality as well as large-volume data. Methods We present an approach that only requires a few labeled vessels but delivers significantly improved results. Our model starts with vessel enhancement by fading out liver intensity and generates candidate vessels by a classifier fed with a large number of image filters. Afterwards, the initial segmentation is refined using Markov random fields. Results In experiments on the well-known dataset 3D-IRCADb, the averaged Dice coefficient is lifted to 0.63, and the mean sensitivity is increased to 0.71. These results are significantly better than those obtained from existing machine-learning approaches and comparable to those generated from deep-learning models. Conclusion Sophisticated integration of a large number of filters is able to pinpoint effective features from liver images that are sufficient to distinguish vessels from other liver tissues under a scarcity of large-volume labeled data. The study can shed light on medical image segmentation, especially for those without sufficient data.

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. [ABSTRACT FROM AUTHOR]

Vessel segmentation in fundus images is crucial for diagnosing eye diseases. The rapid development of deep learning has greatly improved segmentation accuracy. However, the scale of the retinal blood-vessel structure varies greatly, and there is a lot of noise unrelated to blood-vessel segmentation in fundus images, which increases the complexity and difficulty of the segmentation algorithm. Comprehensive consideration of factors like scale variation and noise suppression is imperative to enhance segmentation accuracy and stability. Therefore, we propose a retinal vessel segmentation method based on multi-scale feature extraction and decoupled representation. Specifically, we design a multi-scale feature extraction module at the skip connections, utilizing dilated convolutions to capture multi-scale features and further emphasizing crucial information through channel attention modules. Additionally, to separate useful spatial information from redundant information and enhance segmentation performance, we introduce an image reconstruction branch to assist in the segmentation task. The specific approach involves using a disentangled representation method to decouple the image into content and style, utilizing the content part for segmentation tasks. We conducted experiments on the DRIVE, STARE, and CHASE_DB1 datasets, and the results showed that our method outperformed others, achieving the highest accuracy across all three datasets (DRIVE:0.9690, CHASE_DB1:0.9757, and STARE:0.9765). [ABSTRACT FROM AUTHOR]

Background: Segmenting liver vessels from contrast-enhanced computed tomography images is essential for diagnosing liver diseases, planning surgeries and delivering radiotherapy. Nevertheless, identifying vessels is a challenging task due to the tiny cross-sectional areas occupied by vessels, which has posed great challenges for vessel segmentation, such as limited features to be learned and difficult to construct high-quality as well as large-volume data. Methods: We present an approach that only requires a few labeled vessels but delivers significantly improved results. Our model starts with vessel enhancement by fading out liver intensity and generates candidate vessels by a classifier fed with a large number of image filters. Afterwards, the initial segmentation is refined using Markov random fields. Results: In experiments on the well-known dataset 3D-IRCADb, the averaged Dice coefficient is lifted to 0.63, and the mean sensitivity is increased to 0.71. These results are significantly better than those obtained from existing machine-learning approaches and comparable to those generated from deep-learning models. Conclusion: Sophisticated integration of a large number of filters is able to pinpoint effective features from liver images that are sufficient to distinguish vessels from other liver tissues under a scarcity of large-volume labeled data. The study can shed light on medical image segmentation, especially for those without sufficient data. [ABSTRACT FROM AUTHOR]

Knowledge of input blood to the brain, which is represented as total cerebral blood flow (tCBF), is important in evaluating brain health. Phase-contrast (PC) magnetic resonance imaging (MRI) enables blood velocity mapping, allowing for noninvasive measurements of tCBF. In the procedure, manual selection of brain-feeding arteries is an essential step, but is time-consuming and often subjective. Thus, the purpose of this work was to develop and validate a deep learning (DL)-based technique for automated tCBF quantifications. To enhance the DL segmentation performance on arterial blood vessels, in the preprocessing step magnitude and phase images of PC MRI were multiplied several times. Thereafter, a U-Net was trained on 218 images for three-class segmentation. Network performance was evaluated in terms of the Dice coefficient and the intersection-over-union (IoU) on 40 test images, and additionally, on externally acquired 20 datasets. Finally, tCBF was calculated from the DL-predicted vessel segmentation maps, and its accuracy was statistically assessed with the correlation of determination (R2), the intraclass correlation coefficient (ICC), paired t-tests, and Bland-Altman analysis, in comparison to manually derived values. Overall, the DL segmentation network provided accurate labeling of arterial blood vessels for both internal (Dice=0.92, IoU=0.86) and external (Dice=0.90, IoU=0.82) tests. Furthermore, statistical analyses for tCBF estimates revealed good agreement between automated versus manual quantifications in both internal (R2=0.85, ICC=0.91, p=0.52) and external (R2=0.88, ICC=0.93, p=0.88) test groups. The results suggest feasibility of a simple and automated protocol for quantifying tCBF from neck PC MRI and deep learning. [ABSTRACT FROM AUTHOR]

Retinal vessel segmentation plays a vital role in the clinical diagnosis of ophthalmic diseases. Despite convolutional neural networks (CNNs) excelling in this task, challenges persist, such as restricted receptive fields and information loss from downsampling. To address these issues, we propose a new multi-fusion network with grouped attention (MAG-Net). First, we introduce a hybrid convolutional fusion module instead of the original encoding block to learn more feature information by expanding the receptive field. Additionally, the grouped attention enhancement module uses high-level features to guide low-level features and facilitates detailed information transmission through skip connections. Finally, the multi-scale feature fusion module aggregates features at different scales, effectively reducing information loss during decoder upsampling. To evaluate the performance of the MAG-Net, we conducted experiments on three widely used retinal datasets: DRIVE, CHASE and STARE. The results demonstrate remarkable segmentation accuracy, specificity and Dice coefficients. Specifically, the MAG-Net achieved segmentation accuracy values of 0.9708, 0.9773 and 0.9743, specificity values of 0.9836, 0.9875 and 0.9906 and Dice coefficients of 0.8576, 0.8069 and 0.8228, respectively. The experimental results demonstrate that our method outperforms existing segmentation methods exhibiting superior performance and segmentation outcomes.

A fetoscope is an optical endoscope, which is often applied in fetoscopic laser photocoagulation to treat twin-to-twin transfusion syndrome. In an operation, the clinician needs to observe the abnormal placental vessels through the endoscope, so as to guide the operation. However, low-quality imaging and narrow field of view of the fetoscope increase the difficulty of the operation. Introducing an accurate placental vessel segmentation of fetoscopic images can assist the fetoscopic laser photocoagulation and help identify the abnormal vessels. This study proposes a method to solve the above problems. A novel encoder-decoder network with a dual-path structure is proposed to segment the placental vessels in fetoscopic images. In particular, we introduce a channel attention mechanism and a continuous convolution structure to obtain multi-scale features with their weights. Moreover, a switching connection is inserted between the corresponding blocks of the two paths to strengthen their relationship. According to the results of a set of blood vessel segmentation experiments conducted on a public fetoscopic image dataset, our method has achieved higher scores than the current mainstream segmentation methods, raising the dice similarity coefficient, intersection over union, and pixel accuracy by 5.80%, 8.39% and 0.62%, respectively. [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.

Small cerebral blood vessels are largely inaccessible to existing clinical in vivo imaging technologies. This study aims to present a novel analysis pipeline for vessel density mapping of small cerebral blood vessels from high-resolution 3D black-blood MRI at 3T. Twenty-eight subjects (10 under 35 years old, 18 over 60 years old) were imaged with the T1-weighted turbo spin-echo with variable flip angles (T1w TSE-VFA) sequence optimized for black-blood small vessel imaging with iso-0.5 mm spatial resolution (interpolated from 0.51×0.51×0.64 mm3) at 3T. Hessian-based vessel segmentation methods (Jerman, Frangi and Sato filter) were evaluated by vessel landmarks and manual annotation of lenticulostriate arteries (LSAs). Using optimized vessel segmentation, large vessel pruning and non-linear registration, a semiautomatic pipeline was proposed for quantification of small vessel density across brain regions and further for localized detection of small vessel changes across populations. Voxel-level statistics was performed to compare vessel density between two age groups. Additionally, local vessel density of aged subjects was correlated with their corresponding gross cognitive and executive function (EF) scores using Montreal Cognitive Assessment (MoCA) and EF composite scores compiled with Item Response Theory (IRT). Jerman filter showed better performance for vessel segmentation than Frangi and Sato filter which was employed in our pipeline. Small cerebral blood vessels including small artery, arterioles, small veins, and venules on the order of a few hundred microns can be delineated using the proposed analysis pipeline on 3D black-blood MRI at 3T. The mean vessel density across brain regions was significantly higher in young subjects compared to aged subjects. In the aged subjects, localized vessel density was positively correlated with MoCA and IRT EF scores. The proposed pipeline is able to segment, quantify, and detect localized differences in vessel density of small cerebral blood vessels based on 3D high-resolution black-blood MRI. This framework may serve as a tool for localized detection of small vessel density changes in normal aging and cerebral small vessel disease.

Deep learning models have demonstrated substantial progress in medical image segmentation. However, these models require large datasets for training, which can prove to be clinically difficult. Medical imaging datasets exhibit domain shift problems due to different imaging techniques, scanners, and data privacy issues and, conventional deep neural networks lack generalization capabilities, as their effectiveness decreases with different data distributions. This paper presents a deep learning-based attention-adaptive instance normalization style transfer technique to address the challenges encountered when segmenting blood vessels. The proposed methodology combines adaptive instance normalization style transfer with a dense extreme inception network and convolution block attention module to achieve the best observed vessel segmentation performance. A simple yet effective method is proposed, and it improves the generalization performance of deep neural networks in vascular segmentation. The network is trained on natural images and tested on medical images, thereby overcoming the need for a large dataset or labelled ground truth to train for vessel segmentation. The proposed technique uses experimental results from five distinct medical datasets to demonstrate higher cross-domain generalization capabilities than the state-of-the-art baselines available in the current literature, and the segmentation performance is compared qualitatively and quantitatively with other models. The results demonstrate the feasibility of generalizing our approach to various datasets. This approach overcomes the constraints of traditional deep learning algorithms, which require enormous volumes of medical data along with manually-labelled ground truth. The predictions by the proposed approach are based on natural image training and can be reliably used to detect and identify cardiac and retinal abnormalities without prior medical imaging information. [ABSTRACT FROM AUTHOR]

Introduction: The accurate segmentation of retinal vessels is of utmost importance in the diagnosis of retinal diseases. However, the complex vessel structure often leads to poor segmentation performance, particularly in the case of microvessels. Methods: To address this issue, we propose a vessel segmentation method composed of preprocessing and a multi-scale feature attention network (MFAUNet). The preprocessing stage involves the application of gamma correction and contrast-limited adaptive histogram equalization to enhance image intensity and vessel contrast. The MFA-UNet incorporates the Multi-scale Fusion Self Attention Module(MSAM) that adjusts multi-scale features and establishes global dependencies, enabling the network to better preserve microvascular structures. Furthermore, the multi-branch decoding module based on deep supervision (MBDM) replaces the original output layer to achieve targeted segmentation of macrovessels and microvessels. Additionally, a parallel attention mechanism is embedded into the decoder to better exploit multi-scale features in skip paths. Results: The proposed MFA-UNet yields competitive performance, with dice scores of 82.79/83.51/84.17/78.60/81.75/84.04 and accuracies of 95.71/96.4/96.71/96.81/96.32/97.10 on the DRIVE, STARE, CHASEDB1, HRF, IOSTAR and FIVES datasets, respectively. Discussion: It is expected to provide reliable segmentation results in clinical diagnosis. [ABSTRACT FROM AUTHOR]

The automatic artery/vein (A/V) classification in retinal fundus images plays a significant role in detecting vascular abnormalities and could speed up the diagnosis of various systemic diseases. Deep-learning methods have been extensively employed in this task. However, due to the lack of annotated data and the serious data imbalance, the performance of the existing methods is constricted. To address these limitations, we propose a novel multi-channel multi-scale fusion network (MMF-Net) that employs the enhancement of vessel structural information to constrain the A/V classification. First, the newly designed multi-channel (MM) module could extract the vessel structure from the original fundus image by the frequency filters, increasing the proportion of blood vessel pixels and reducing the influence caused by the background pixels. Second, the MMF-Net introduces a multi-scale transformation (MT) module, which could efficiently extract the information from the multi-channel feature representations. Third, the MMF-Net utilizes a multi-feature fusion (MF) module to improve the robustness of A/V classification by splitting and reorganizing the pixel feature from different scales. We validate our results on several public benchmark datasets. The experimental results show that the proposed method could achieve the best result compared with the existing state-of-the-art methods, which demonstrate the superior performance of the MMF-Net. The highly optimized Python implementations of our method is released at: https://github.com/chenchouyu/MMF_Net. [ABSTRACT FROM AUTHOR]

Transformer-based methods have led to the revolutionizing of multiple computer vision tasks. Inspired by this, we propose a transformer-based network with a channel-enhanced attention module to explore contextual and spatial information in non-contrast (NC) and contrast-enhanced (CE) computed tomography (CT) images for pulmonary vessel segmentation and artery-vein separation. Our proposed network employs a 3D contextual transformer module in the encoder and decoder part and a double attention module in skip connection to effectively finish high-quality vessel and artery-vein segmentation. Extensive experiments are conducted on the in-house dataset and the ISICDM2021 challenge dataset. The in-house dataset includes 56 NC CT scans with vessel annotations and the challenge dataset consists of 14 NC and 14 CE CT scans with vessel and artery-vein annotations. For vessel segmentation, Dice is 0.840 for CE CT and 0.867 for NC CT. For artery-vein separation, the proposed method achieves a Dice of 0.758 of CE images and 0.602 of NC images. Quantitative and qualitative results demonstrated that the proposed method achieved high accuracy for pulmonary vessel segmentation and artery-vein separation. It provides useful support for further research associated with the vascular system in CT images. The code is available at https://github.com/wuyanan513/Pulmonary-Vessel-Segmentation-and-Artery-vein-Separation. [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. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR), a medical condition that impairs the blood vessels within the eye, is increasingly prevalent. Unchecked progression of DR can lead to significant visual impairment or total blindness. Traditional techniques for automatic DR detection, primarily reliant on computer vision systems, often fail to adequately encapsulate the inherent complexity of the disease, resulting in suboptimal categorization of DR stages, particularly the early ones. However, deep ensemble learning has emerged as a potent tool for the accurate detection and classification of DR using retinal images. In this study, deep ensemble models are proposed that initially segment the retinal image using the Canny operator and subsequently detect and classify all DR categories using the publicly available DRIVE dataset. Each model, crafted with subtle architectural distinctions or trained on distinct data subsets, was designed to capture varying disease attributes. A threshold was established to accurately categorize DR severity into mild, moderate, or severe cases. The results indicate a significant enhancement in the performance of both segmentation and DR detection through deep ensemble learning, compared to individual models. The ensemble approach effectively amalgamated the collective knowledge of the models, yielding superior accuracy, robustness to data variations, and improved generalization capabilities. This cost-effective computational method achieves an accuracy score of 98.65% in DR detection and classification. By synthesizing the predictions of multiple models, the ensemble captured a wider spectrum of disease patterns, thereby bolstering the system's overall effectiveness in DR diagnosis. The findings underscore the enhanced accuracy and robustness attained through the ensemble approach, surpassing the performance of individual models. [ABSTRACT FROM AUTHOR]

Vessel segmentation in fundus images is crucial for diagnosing eye diseases. The rapid development of deep learning has greatly improved segmentation accuracy. However, the scale of the retinal blood-vessel structure varies greatly, and there is a lot of noise unrelated to blood-vessel segmentation in fundus images, which increases the complexity and difficulty of the segmentation algorithm. Comprehensive consideration of factors like scale variation and noise suppression is imperative to enhance segmentation accuracy and stability. Therefore, we propose a retinal vessel segmentation method based on multi-scale feature extraction and decoupled representation. Specifically, we design a multi-scale feature extraction module at the skip connections, utilizing dilated convolutions to capture multi-scale features and further emphasizing crucial information through channel attention modules. Additionally, to separate useful spatial information from redundant information and enhance segmentation performance, we introduce an image reconstruction branch to assist in the segmentation task. The specific approach involves using a disentangled representation method to decouple the image into content and style, utilizing the content part for segmentation tasks. We conducted experiments on the DRIVE, STARE, and CHASE_DB1 datasets, and the results showed that our method outperformed others, achieving the highest accuracy across all three datasets (DRIVE:0.9690, CHASE_DB1:0.9757, and STARE:0.9765).