Fine Vessels Research Articles

VDMNet: A Deep Learning Framework with Vessel Dynamic Convolution and Multi-Scale Fusion for Retinal Vessel Segmentation

Retinal vessel segmentation is crucial for diagnosing and monitoring ophthalmic and systemic diseases. Optical Coherence Tomography Angiography (OCTA) enables detailed imaging of the retinal microvasculature, but existing methods for OCTA segmentation face significant limitations, such as susceptibility to noise, difficulty in handling class imbalance, and challenges in accurately segmenting complex vascular morphologies. In this study, we propose VDMNet, a novel segmentation network designed to overcome these challenges by integrating several advanced components. Firstly, we introduce the Fast Multi-Head Self-Attention (FastMHSA) module to effectively capture both global and local features, enhancing the network’s robustness against complex backgrounds and pathological interference. Secondly, the Vessel Dynamic Convolution (VDConv) module is designed to dynamically adapt to curved and crossing vessels, thereby improving the segmentation of complex morphologies. Furthermore, we employ the Multi-Scale Fusion (MSF) mechanism to aggregate features across multiple scales, enhancing the detection of fine vessels while maintaining vascular continuity. Finally, we propose Weighted Asymmetric Focal Tversky Loss (WAFT Loss) to address class imbalance issues, focusing on the accurate segmentation of small and difficult-to-detect vessels. The proposed framework was evaluated on the publicly available ROSE-1 and OCTA-3M datasets. Experimental results demonstrated that our model effectively preserved the edge information of tiny vessels and achieved state-of-the-art performance in retinal vessel segmentation across several evaluation metrics. These improvements highlight VDMNet’s superior ability to capture both fine vascular details and overall vessel connectivity, making it a robust solution for retinal vessel segmentation.

Deep learning for 3D vascular segmentation in hierarchical phase contrast tomography: a case study on kidney

Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine-learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using HiP-CT as part of the Human Organ Atlas Project. HiP-CT pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering a resolution of around 20 μm/voxel and enabling highly detailed localised zooms up to 1–2 μm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice similarity coefficient (DSC) scores of 0.9523, 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline DSC ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydrostatic pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Our study establishes the benchmark across various evaluation metrics, for vascular segmentation of HiP-CT imaging data, an imaging technology that has the potential to substantively shift our understanding of human vascular networks.

Piezoelectric Actuator-Driven Pulsed Water Jet for Neurosurgery: Laboratory Evaluation with the Swine Model and Implications of Mechanical Properties.

Pulsed water jet is an emerging surgical instrumentation intended to achieve both maximal lesion resection and functional maintenance through preservation of fine vessels and minimal damage to the surrounding tissue. The piezoelectric actuator-driven pulsed water jet (ADPJ) is a new technology that can deliver a precisely controlled uniform and efficient pulsed water jet with minimum water flow. The present study evaluated the ADPJ system in preclinical animal studies in the swine brain, and investigated breaking strength, one of the parameters for mechanical properties, to elucidate the mechanism of tissue selectivity for tissue dissection by the water jet. This system consisted of a pump chamber driven by a piezoelectric actuator, a stainless steel tube, and a nozzle (internal diameter: 0.15 mm). Water was supplied at 6 ml/min. The relationship between input voltage (3-25 V at 400 Hz) and peak pressure was measured using a pressure sensor through a sensing hole. The temporal profile of dissection depth during moving application was evaluated using gelatin brain phantom and swine brain. The dissected specimens were evaluated histologically. The mechanical property (breaking strength) of the swine brain was measured by a compact table-top universal tester. Peak pressure increased linearly with increase in input voltage, which reflected the dissection depth in both the gelatin brain phantom and swine brain. Small arteries were preserved, and minimum damage to surrounding tissues occurred. The breaking strength of the arachnoid membrane (0.12 ± 0.014 MPa) was significantly higher compared with the gray matter (0.030 ± 0.010 MPa) and white matter (0.056 ± 0.009 MPa; p < 0.05). The breaking strength of the gray matter corresponded to that of 3 wt% gelatin, and that of white matter corresponded to a value between 3.5 and 4 wt% gelatin, and the dissection depth seemed to be estimated at 3 to 4 wt% gelatin. The present study suggests that the ADPJ system has the potential to achieve accurate tissue dissection with preservation of blood vessels in neurosurgery. The difference in breaking strength may explain the tissue selectivity between the brain parenchyma and tissue protected by the arachnoid membrane.

FINE VESSEL SEGMENTATION WITH REFINEMENT GATE IN DEEP LEARNING ARCHITECTURES

Automated vessel segmentation is essential in diagnosing eye-related disorders and monitoring progressive retinal diseases. State-of-the-art methods have achieved excellent results in this field, but very few have considered the post-processing of feature maps. As a result, there is often a lack of small and fine vessels or discontinuities in segmented vessels. To address this issue, this study introduces a novel post-processing technique called the refinement gate, which works with a deep learning model during training. The refinement gate enhances contextual information to extract important features from feature maps better. The proposed technique is applied with U-net architecture and placed after every convolution block in the encoder path. Visual and statistical comparisons demonstrate the robustness of the proposed method using three publicly available datasets, namely: the DRIVE DB, the STARE DB, and CHASE_DB1 datasets, showing significant improvements to segment weak and tiny vessels. The reported results confirm the potential of the model to be used as a segmentation tool in the medical field. This study is the first to propose such a gating mechanism without additional trainable parameters or standalone networks as in other literature.

Structure preservation constraints for unsupervised domain adaptation intracranial vessel segmentation.

Unsupervised domain adaptation (UDA) has received interest as a means to alleviate the burden of data annotation. Nevertheless, existing UDA segmentation methods exhibit performance degradation in fine intracranial vessel segmentation tasks due to the problem of structure mismatch in the image synthesis procedure. To improve the image synthesis quality and the segmentation performance, a novel UDA segmentation method with structure preservation approaches, named StruP-Net, is proposed. The StruP-Net employs adversarial learning for image synthesis and utilizes two domain-specific segmentation networks to enhance the semantic consistency between real images and synthesized images. Additionally, two distinct structure preservation approaches, feature-level structure preservation (F-SP) and image-level structure preservation (I-SP), are proposed to alleviate the problem of structure mismatch in the image synthesis procedure. The F-SP, composed of two domain-specific graph convolutional networks (GCN), focuses on providing feature-level constraints to enhance the structural similarity between real images and synthesized images. Meanwhile, the I-SP imposes constraints on structure similarity based on perceptual loss. The cross-modality experimental results from magnetic resonance angiography (MRA) images to computed tomography angiography (CTA) images indicate that StruP-Net achieves better segmentation performance compared with other state-of-the-art methods. Furthermore, high inference efficiency demonstrates the clinical application potential of StruP-Net. The code is available at https://github.com/Mayoiuta/StruP-Net .

A fundus vessel segmentation method based on double skip connections combined with deep supervision.

Fundus vessel segmentation is vital for diagnosing ophthalmic diseases like central serous chorioretinopathy (CSC), diabetic retinopathy, and glaucoma. Accurate segmentation provides crucial vessel morphology details, aiding the early detection and intervention of ophthalmic diseases. However, current algorithms struggle with fine vessel segmentation and maintaining sensitivity in complex regions. Challenges also stem from imaging variability and poor generalization across multimodal datasets, highlighting the need for more advanced algorithms in clinical practice. This paper aims to explore a new vessel segmentation method to alleviate the above problems. We propose a fundus vessel segmentation model based on a combination of double skip connections, deep supervision, and TransUNet, namely DS2TUNet. Initially, the original fundus images are improved through grayscale conversion, normalization, histogram equalization, gamma correction, and other preprocessing techniques. Subsequently, by utilizing the U-Net architecture, the preprocessed fundus images are segmented to obtain the final vessel information. Specifically, the encoder firstly incorporates the ResNetV1 downsampling, dilated convolution downsampling, and Transformer to capture both local and global features, which upgrades its vessel feature extraction ability. Then, the decoder introduces the double skip connections to facilitate upsampling and refine segmentation outcomes. Finally, the deep supervision module introduces multiple upsampling vessel features from the decoder into the loss function, so that the model can learn vessel feature representations more effectively and alleviate gradient vanishing during the training phase. Extensive experiments on publicly available multimodal fundus datasets such as DRIVE, CHASE_DB1, and ROSE-1 demonstrate that the DS2TUNet model attains F1-scores of 0.8195, 0.8362, and 0.8425, with Accuracy of 0.9664, 0.9741, and 0.9557, Sensitivity of 0.8071, 0.8101, and 0.8586, and Specificity of 0.9823, 0.9869, and 0.9713, respectively. Additionally, the model also exhibits excellent test performance on the clinical fundus dataset CSC, with F1-score of 0.7757, Accuracy of 0.9688, Sensitivity of 0.8141, and Specificity of 0.9801 based on the weight trained on the CHASE_DB1 dataset. These results comprehensively validate that the proposed method obtains good performance in fundus vessel segmentation, thereby aiding clinicians in the further diagnosis and treatment of fundus diseases in terms of effectiveness and feasibility.

Dermoscopy as an additional method for diagnosis of mycosis fungoides

Mycosis fungoides is a primary epidermotropic T-cell lymphoma of the skin, characterized by the proliferation of small and medium-sized T-lymphocytes with cerebriform nuclei. Mycosis fungoides accounts for 60.6% of the total number of all cases of primary T-cell lymphomas of the skin. Diagnosis of mycosis fungoides remains a big challenge in dermatology: the average time for diagnosis from the onset of the disease is 5 years. The difficulty of differential diagnosis with inflammatory dermatoses, such as psoriasis, is due to the similarity of their clinical characteristics, especially in the early stages of the mycosis fungoides. The search for new methods aimed at early diagnosis of skin T-cell lymphoma is one of the most important tasks in dermatooncology. A number of morden studies aimed at assessing the capabilities of dermatoscopy as an additional method for diagnosing mycosis fungoides. Specific dermoscopic pattern of mycosis fungoides were identified: fine short linear vessels, orange-yellowish patchy areas and vascular structure resembling spermatozoa. Description of this dermoscopic pattern can influence the accuracy of diagnosis and timeliness of diagnosis, the prescription of effective methods of therapy in the early stages of the disease, improving the quality and increasing the life expectancy of patients. The article provides an overview of the most up-to-date information on the dermoscopic pattern of mycosis fungoides.

Traumatic hyphema in a neonate: An unusual presentation

Subconjunctival hemorrhages following forceps delivery are common. However, their presence with hyphema is rare. This case report describes a full-term neonate who was initially examined for trauma and subconjunctival hemorrhage in both eyes with diffuse hyphema in right eye following forceps delivery. The anterior segment showed nondilating pupil with fine blood vessels on the iris in one eye along with tunica vasculosa lentis. B-scan showed a hyperechoic line in the vitreous suggestive of unilateral persistent fetal vasculature.

Endoscopic ultrasonography for microvascular imaging without contrast enhancement in the differential diagnosis of pancreatic lesions.

Detective flow imaging endoscopic ultrasonography (DFI-EUS) is a recent imaging modality developed for detecting fine vessels without the need for ultrasound contrast agents. The aim of the present study was to evaluate the utility of DFI-EUS for solid pancreatic lesions and to compare the diagnostic ability for pancreatic cancer (PC) between DFI-EUS, directional power Doppler (eFLOW) EUS, and contrast-enhanced harmonic (CH)-EUS. Patients with a pancreatic lesion who underwent DFI-EUS, eFLOW-EUS, and CH-EUS between March 2019 and November 2023 were retrospectively enrolled. Final diagnoses were confirmed by pathologic examination of EUS-guided tissue acquisition and/or resected specimens. Lesions were categorized into the three patterns of poor, mild, and rich vascularity on DFI-EUS and eFLOW-EUS, and hypo-, iso-, and hypervascular on CH-EUS. PC was defined as a poor pattern on DFI-EUS and eFLOW-EUS, and a hypovascular pattern on CH-EUS. The final diagnoses of 90 examined tumors were PC (n = 57), inflammatory mass (n = 6), autoimmune pancreatitis (n = 13), neuroendocrine tumor (n = 9), and others (n = 5). The sensitivity, specificity, and accuracy for diagnosis of PC were 93%, 82%, and 88%, respectively, on DFI-EUS, 97%, 42%, and 77% on eFLOW-EUS, and 95%, 89%, and 92% on CH-EUS. The accuracy of DFI-EUS was significantly superior to eFLOW-EUS (P = 0.005), but no significant difference was found between DFI-EUS and CH-EUS. DFI-EUS is more sensitive for depicting vasculature than eFLOW-EUS, and has higher diagnostic sensitivity for PC. Evaluation of vascularity on DFI-EUS is useful for the differential diagnosis of pancreatic lesions without the need for intravenous contrast agent.

DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation.

Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.

Impact of the Plant Growth-promoting Rhizobacterium Streptomyces saraceticus Strain 31 on Berry Quality of ‘Benifuji’ Grape: Improvements through the Reconfiguration of Fine Root Morphology and Vessel Anatomy

In an effort to mitigate the environmental impact of chemical fertilizers, plant growth-promoting rhizobacteria (PGPR) have emerged as a more sustainable alternative. Streptomyces saraceticus 31 (‘SS31’), a new strain of biocontrol bacteria, was inoculated into rhizosphere soils of ‘Benifuji’ grape to evaluate its impact on grape roots and berries. The results indicated significant improvements in soil fertility, with higher levels of organic matter, phosphorus, potassium, and nitrate nitrogen compared with those of the controls. Moreover, ‘SS31’ application elicited a notable reduction in soil pH levels, along with a substantial augmentation in the enzymatic activities of both phosphatase and invertase. The grapes treated with ‘SS31’ exhibited a notable increase in the number, length, surface area, and volume of fine roots in both 0- to 10-cm and 10- to 20-cm soil profiles. The application of ‘SS31’ resulted in the observation of greater diameter, lower density, and larger lumen area, along with increased specific hydraulic conductivity in the vessels of roots with 1- to 2-mm diameters. Despite a slight reduction in berry weight compared with that of the controls, ‘Benifuji’ grape berries displayed higher total soluble solids and lower total titratable acidity after ‘SS31’ application. Furthermore, ‘SS31’ treatment elevated the levels of volatile compounds in berries, especially fatty acid-derived compounds. A network analysis revealed a robust positive correlation between the observed improvements in grape berry quality and the morphology as well as the hydraulic conductivity of the grape fine roots. In conclusion, these findings suggest that ‘SS31’ has the potential to enhance grape root function by expanding the root absorption area and facilitating water transportation. This, in turn, may improve the flavor and aroma of ‘Benifuji’ grape berries.

Fourier feature network for 3D vessel reconstruction from biplane angiograms

3D reconstruction of biplane cerebral angiograms remains a challenging, unsolved research problem due to the loss of depth information and the unknown pixelwise correlation between input images. The occlusions arising from only two views complicate the reconstruction of fine vessel details and the simultaneous addressing of inherent missing information. In this paper, we take an incremental step toward solving this problem by reconstructing the corresponding 2D slice of the cerebral angiogram using biplane 1D image data. We developed a coordinate-based neural network that encodes the 1D image data along with a deterministic Fourier feature mapping from a given input point, resulting in a slice reconstruction that is more spatially accurate. Using only one 1D row of biplane image data, our Fourier feature network reconstructed the corresponding volume slices with a peak signal-to-noise ratio (PSNR) of 26.32 ± 0.36, a structural similarity index measure (SSIM) of 61.38 ± 1.79, a mean squared error (MSE) of 0.0023 ± 0.0002, and a mean absolute error (MAE) of 0.0364 ± 0.0029. Our research has implications for future work aimed at improving backprojection-based reconstruction by first examining individual slices from 1D information as a prerequisite.

Deep Learning for 3D Vascular Segmentation in Phase Contrast Tomography.

Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using Hierarchical Phase-Contrast Tomography (HiP-CT) as part of the Human Organ Atlas Project. HiP-CT, pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering resolution around 20μm/voxel, and enabling highly detailed localized zooms up to 1μm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice scores of 0.9523 and 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline Dice values ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydro-static pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Through our review and outputs, we aim to set a benchmark for subsequent model evaluations using various modalities, especially with the HiP-CT imaging database.

Embossed x-ray computed tomography utilizing pixel-shifted dual-energy subtraction.

To observe fine blood vessels as uneven tomographic images at a high contrast, we performed tentative experiments on embossed x-ray computed tomography (CT). We constructed a cone-beam CT scanner and carried out dual-energy CT with tube voltages of 60 and 100kV. X-ray photons penetrating through an object were detected using an indirect-conversion flat panel detector, and radiograms were produced and sent to a personal computer to reconstruct tomograms. Embossed CT was performed using pixel-shifted dual-energy subtraction, and blood vessels filled with Gd medium were observed as uneven images at high contrast and spatial resolutions. Using 1.4-time magnification imaging in combination with a 0.1-mm-focus x-ray tube, the diameter of the object visible on the embossed CT was below 100 μm.

Unsupervised domain adaptation multi-level adversarial learning-based crossing-domain retinal vessel segmentation

BackgroundThe retinal vasculature, a crucial component of the human body, mirrors various illnesses such as cardiovascular disease, glaucoma, and retinopathy. Accurate segmentation of retinal vessels in funduscopic images is essential for diagnosing and understanding these conditions. However, existing segmentation models often struggle with images from different sources, making accurate segmentation in crossing-source fundus images challenging. MethodsTo address the crossing-source segmentation issues, this paper proposes a novel Multi-level Adversarial Learning and Pseudo-label Denoising-based Self-training Framework (MLAL&PDSF). Expanding on our previously proposed Multiscale Context Gating with Breakpoint and Spatial Dual Attention Network (MCG&BSA-Net), MLAL&PDSF introduces a multi-level adversarial network that operates at both the feature and image layers to align distributions between the target and source domains. Additionally, it employs a distance comparison technique to refine pseudo-labels generated during the self-training process. By comparing the distance between the pseudo-labels and the network predictions, the framework identifies and corrects inaccuracies, thus enhancing the accuracy of the fine vessel segmentation. ResultsWe have conducted extensive validation and comparative experiments on the CHASEDB1, STARE, and HRF datasets to evaluate the efficacy of the MLAL&PDSF. The evaluation metrics included the area under the operating characteristic curve (AUC), sensitivity (SE), specificity (SP), accuracy (ACC), and balanced F-score (F1). The performance results from unsupervised domain adaptive segmentation are remarkable: for DRIVE to CHASEDB1, results are AUC: 0.9806, SE: 0.7400, SP: 0.9737, ACC: 0.9874, and F1: 0.8851; for DRIVE to STARE, results are AUC: 0.9827, SE: 0.7944, SP: 0.9651, ACC: 0.9826, and F1: 0.8326. ConclusionThese results demonstrate the effectiveness and robustness of MLAL&PDSF in achieving accurate segmentation results from crossing-domain retinal vessel datasets. The framework lays a solid foundation for further advancements in cross-domain segmentation and enhances the diagnosis and understanding of related diseases.

DCNet: A lightweight retinal vessel segmentation network

Retinal vessel segmentation is a crucial focus within the realm of medical image analysis, playing a pivotal role in early disease diagnosis, notably retinopathy. Deep learning has exhibited remarkable segmentation capabilities for retinal blood vessels, leveraging the advantages of contextual feature learning. However, there are still some shortcomings in fine retinal vessel segmentation due to the loss of semantic information due to too many pooling operations or limited receptive fields due to fewer pooling operations. In response to the nuanced balance required for expanding the receptive field while preserving information integrity during multiple downsampling operations, this paper introduces DCNet (Dilated Convolution Net), a novel lightweight three-layer dilated-convolution-based network tailored for retinal blood vessel segmentation. This three-layer architecture autonomously extracts crucial segmentation features from various levels of the feature map. Each layer comprises a dilated convolution Positive Sequence Block (PSB) and a dilated convolution Reverse Sequence Block (RSB). The dilated convolution operation is strategically exploited for its capacity to extend the receptive field, facilitating effective feature information extraction. Simultaneously, to alleviate semantic information loss within the deep network's feature map, this paper proposes the Nonlinear Feature Extraction Module (NFEM) to supplement shallow network feature information. Furthermore, to comprehensively leverage information from various scale features, a Feature Fusion Module (FFM) is introduced for multiscale vascular feature extraction, ultimately enhancing segmentation accuracy. DCNet undergoes rigorous evaluation on four publicly accessible retinal vascular datasets – DRIVE, STARE, CHASE_DB1, and HRF. Experimental results unequivocally demonstrate that DCNet achieves superior segmentation performance with fewer model parameters compared to existing state-of-the-art methods. The code for DCNet can be accessed on the following website: https://github.com/ChunhuiYu1/DCNet.

A Microvascular Segmentation Network Based on Pyramidal Attention Mechanism.

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.

Multi-scale Knowledge Transfer Vision Transformer for 3D vessel shape segmentation

In order to facilitate the robust and precise 3D vessel shape extraction and quantification from in-vivo Magnetic Resonance Imaging (MRI), this paper presents a novel multi-scale Knowledge Transfer Vision Transformer (i.e., KT-ViT) for 3D vessel shape segmentation. First, it uniquely integrates convolutional embeddings with transformer in a U-net architecture, which simultaneously responds to local receptive fields with convolution layers and global contexts with transformer encoders in a multi-scale fashion. Therefore, it intrinsically enriches local vessel feature and simultaneously promotes global connectivity and continuity for a more accurate and reliable vessel shape segmentation. Furthermore, to enable using relatively low-resolution (LR) images to segment fine scale vessel shapes, a novel knowledge transfer network is designed to explore the inter-dependencies of data and automatically transfer the knowledge gained from high-resolution (HR) data to the low-resolution handling network at multiple levels, including the multi-scale feature levels and the decision level, through an integration of multi-level loss functions. The modeling capability of fine-scale vessel shape data distribution, possessed by the HR image transformer network, can be transferred to the LR image transformer to enhance its knowledge for fine vessel shape segmentation. Extensive experimental results on public image datasets have demonstrated that our method outperforms all other state-of-the-art deep learning methods.

Enhancement of the Consistency and Connectivity of the Ant-tracking Algorithm via 3D U-Net with Dual-Threshold Iteration

Abstract The ant-tracking algorithm is commonly used to extract faults in geological structures. However, obtaining 3D ant-tracking data requires the calculation of various volume attributes. To obtain satisfactory data, it is necessary to iterate through the parameters of these attributes to achieve reasonable continuity. Moreover, due to the numerous parameters involved, the algorithm can produce different outputs with each execution. In this study, we aimed to enhance the performance of the ant-tracking algorithm by combining it with a basic U-Net structure. The input and corresponding labels to the model are "cubic shaped" 3D data segmented from the original 3D seismic volume to facilitate cross-validation with distinct regions. We used the label data as the single ant-tracking result to minimize the operator’s bias by executing the ant-tracking with several different parameters and executors and then taking the average. An evaluative comparison of three different loss functions (MAE, RMSE, and MSE) was conducted to identify the optimal function for training the model. Across five out of the six metrics, MSE function demonstrated predominant performance, leading to its adoption. Apart from this, a significant number of misinterpreted faults led us to propose the post-processing algorithm named "Dual-Threshold Iteration." It was initially used to extract fine blood vessels branching out from large vessels in medical image segmentation and adapted in our work to ensure a high level of continuity while ignoring worthless noise. Comparison with the F1 score and the number of 3D-connected components confirmed that the proposed method could generate reduced bias and smoothly connected fault structures.

FRD-Net: a full-resolution dilated convolution network for retinal vessel segmentation

Accurate and automated retinal vessel segmentation is essential for performing diagnosis and surgical planning of retinal diseases. However, conventional U-shaped networks often suffer from segmentation errors when dealing with fine and low-contrast blood vessels due to the loss of continuous resolution in the encoding stage and the inability to recover the lost information in the decoding stage. To address this issue, this paper introduces an effective full-resolution retinal vessel segmentation network, namely FRD-Net, which consists of two core components: the backbone network and the multi-scale feature fusion module (MFFM). The backbone network achieves horizontal and vertical expansion through the interaction mechanism of multi-resolution dilated convolutions while preserving the complete image resolution. In the backbone network, the effective application of dilated convolutions with varying dilation rates, coupled with the utilization of dilated residual modules for integrating multi-scale feature maps from adjacent stages, facilitates continuous learning of multi-scale features to enhance high-level contextual information. Moreover, MFFM further enhances segmentation by fusing deeper multi-scale features with the original image, facilitating edge detail recovery for accurate vessel segmentation. In tests on multiple classical datasets,compared to state-of-the-art segmentation algorithms, FRD-Net achieves superior performance and generalization with fewer model parameters.