Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation

Deep learning based retinal vessel segmentation and hypertensive retinopathy quantification using heterogeneous features cross-attention neural network

Retinal vessels play a pivotal role as biomarkers in the detection of retinal diseases, including hypertensive retinopathy. The manual identification of these retinal vessels is both resource-intensive and time-consuming. The fidelity of vessel segmentation in automated methods directly depends on the fundus images' quality. In instances of sub-optimal image quality, applying deep learning-based methodologies emerges as a more effective approach for precise segmentation. We propose a heterogeneous neural network combining the benefit of local semantic information extraction of convolutional neural network and long-range spatial features mining of transformer network structures. Such cross-attention network structure boosts the model's ability to tackle vessel structures in the retinal images. Experiments on four publicly available datasets demonstrate our model's superior performance on vessel segmentation and the big potential of hypertensive retinopathy quantification.

BiU-net: A dual-branch structure based on two-stage fusion strategy for biomedical image segmentation

BACKGROUND AND OBJECTIVE

Computer-based biomedical image segmentation plays a crucial role in planning of assisted diagnostics and therapy. However, due to the variable size and irregular shape of the segmentation target, it is still a challenge to construct an effective medical image segmentation structure. Recently, hybrid architectures based on convolutional neural networks (CNNs) and transformers were proposed. However, most current backbones directly replace one or all convolutional layers with transformer blocks, regardless of the semantic gap between features. Thus, how to sufficiently and effectively eliminate the semantic gap as well as combine the global and local information is a critical challenge.

METHODS

To address the challenge, we propose a novel structure, called BiU-Net, which integrates CNNs and transformers with a two-stage fusion strategy. In the first fusion stage, called Single-Scale Fusion (SSF) stage, the encoding layers of the CNNs and transformers are coupled, with both having the same feature map size. The SSF stage aims to reconstruct local features based on CNNs and long-range information based on transformers in each encoding block. In the second stage, Multi-Scale Fusion (MSF), BiU-Net interacts with multi-scale features from various encoding layers to eliminate the semantic gap between deep and shallow layers. Furthermore, a Context-Aware Block (CAB) is embedded in the bottleneck to reinforce multi-scale features in the decoder.

RESULTS

Experiments on four public datasets were conducted. On the BUSI dataset, our BiU-Net achieved 85.50 % on Dice coefficient (Dice), 76.73 % on intersection over union (IoU), and 97.23 % on accuracy (ACC). Compared to the state-of-the-art method, BiU-Net improves Dice by 1.17 %. For the Monuseg dataset, the proposed method attained the highest scores, reaching 80.27 % and 67.22 % for Dice and IoU. The BiU-Net achieves 95.33 % and 81.22 % Dice on the PH2 and DRIVE datasets.

CONCLUSIONS

The results of our experiments showed that BiU-Net transcends existing state-of-the-art methods on four publicly available biomedical datasets. Due to the powerful multi-scale feature extraction ability, our proposed BiU-Net is a versatile medical image segmentation framework for various types of medical images. The source code is released on (https://github.com/ZYLandy/BiU-Net).

CS-UNet: Cross-scale U-Net with Semantic-position dependencies for retinal vessel segmentation

Accurate retinal vessel segmentation is the prerequisite for early recognition and treatment of retina-related diseases. However, segmenting retinal vessels is still challenging due to the intricate vessel tree in fundus images, which has a significant number of tiny vessels, low contrast, and lesion interference. For this task, the u-shaped architecture (U-Net) has become the de-facto standard and has achieved considerable success. However, U-Net is a pure convolutional network, which usually shows limitations in global modelling. In this paper, we propose a novel Cross-scale U-Net with Semantic-position Dependencies (CS-UNet) for retinal vessel segmentation. In particular, we first designed a Semantic-position Dependencies Aggregator (SPDA) and incorporate it into each layer of the encoder to better focus on global contextual information by integrating the relationship of semantic and position. To endow the model with the capability of cross-scale interaction, the Cross-scale Relation Refine Module (CSRR) is designed to dynamically select the information associated with the vessels, which helps guide the up-sampling operation. Finally, we have evaluated CS-UNet on three public datasets: DRIVE, CHASE_DB1, and STARE. Compared to most existing state-of-the-art methods, CS-UNet demonstrated better performance.

Automatic segmentation of layers in chorio-retinal complex using Graph-based method for ultra-speed 1.7 MHz wide field swept source FDML optical coherence tomography

The posterior segment of the human eye complex contains two discrete microstructure and vasculature network systems, namely, the retina and choroid. We present a single segmentation framework technique for segmenting the entire layers present in the chorio-retinal complex of the human eye using optical coherence tomography (OCT) images. This automatic program is based on the graph theory method. This single program is capable of segmenting seven layers of the retina and choroid scleral interface. The graph theory was utilized to find the probability matrix and subsequent boundaries of different layers. The program was also implemented to segment angiographic maps of different chorio-retinal layers using "segmentation matrices." The method was tested and successfully validated on OCT images from six normal human eyes as well as eyes with non-exudative age-related macular degeneration (AMD). The thickness of microstructure and microvasculature for different layers located in the chorio-retinal segment of the eye was also generated and compared. A decent efficiency in terms of processing time, sensitivity, and accuracy was observed compared to the manual segmentation and other existing methods. The proposed method automatically segments whole OCT images of chorio-retinal complex with augmented probability maps generation in OCT volume dataset. We have also evaluated the segmentation results using quantitative metrics such as Dice coefficient and Hausdorff distance This method realizes a mean descent Dice similarity coefficient (DSC) value of 0.82 (range, 0.816-0.864) for RPE and CSI layer.

Artificial intelligence in chorioretinal pathology through fundoscopy: a comprehensive review

BACKGROUND

Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction.

MAIN BODY

In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations.

SHORT CONCLUSION

As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.

High-precision retinal blood vessel segmentation based on a multi-stage and dual-channel deep learning network

Objective.The high-precision segmentation of retinal vessels in fundus images is important for the early diagnosis of ophthalmic diseases. However, the extraction for microvessels is challenging due to their characteristics of low contrast and high structural complexity. Although some works have been developed to improve the segmentation ability in thin vessels, they have only been successful in recognizing small vessels with relatively high contrast.Approach.Therefore, we develop a deep learning (DL) framework with a multi-stage and dual-channel network model (MSDC_NET) to further improve the thin-vessel segmentation with low contrast. Specifically, an adaptive image enhancement strategy combining multiple preprocessing and the DL method is firstly proposed to elevate the contrast of thin vessels; then, a two-channel model with multi-scale perception is developed to implement whole- and thin-vessel segmentation; and finally, a series of post-processing operations are designed to extract more small vessels in the predicted maps from thin-vessel channels.Main results.Experiments on DRIVE, STARE and CHASE_DB1 demonstrate the superiorities of the proposed MSDC_NET in extracting more thin vessels in fundus images, and quantitative evaluations on several parameters based on the advanced ground truth further verify the advantages of our proposed DL model. Compared with the previous multi-branch method, the specificity and F1score are improved by about 2.18%, 0.68%, 1.73% and 2.91%, 0.24%, 8.38% on the three datasets, respectively.Significance.This work may provide richer information to ophthalmologists for the diagnosis and treatment of vascular-related ophthalmic diseases.

Retinal vessel segmentation based on multi-scale feature and style transfer

Retinal vessel segmentation is very important for diagnosing and treating certain eye diseases. Recently, many deep learning-based retinal vessel segmentation methods have been proposed; however, there are still many shortcomings (e.g., they cannot obtain satisfactory results when dealing with cross-domain data or segmenting small blood vessels). To alleviate these problems and avoid overly complex models, we propose a novel network based on a multi-scale feature and style transfer (MSFST-NET) for retinal vessel segmentation. Specifically, we first construct a lightweight segmentation module named MSF-Net, which introduces the selective kernel (SK) module to increase the multi-scale feature extraction ability of the model to achieve improved small blood vessel segmentation. Then, to alleviate the problem of model performance degradation when segmenting cross-domain datasets, we propose a style transfer module and a pseudo-label learning strategy. The style transfer module is used to reduce the style difference between the source domain image and the target domain image to improve the segmentation performance for the target domain image. The pseudo-label learning strategy is designed to be combined with the style transfer module to further boost the generalization ability of the model. Moreover, we trained and tested our proposed MSFST-NET in experiments on the DRIVE and CHASE_DB1 datasets. The experimental results demonstrate that MSFST-NET can effectively improve the generalization ability of the model on cross-domain datasets and achieve improved retinal vessel segmentation results than other state-of-the-art methods.

An improved supervised and attention mechanism-based U-Net algorithm for retinal vessel segmentation

The segmentation results of retinal blood vessels are crucial for automatically diagnosing ophthalmic diseases such as diabetic retinopathy, hypertension, cardiovascular and cerebrovascular diseases. To improve the accuracy of vessel segmentation and better extract information about small vessels and edges, we introduce the U-Net algorithm with a supervised attention mechanism for retinal vessel segmentation. We achieve this by introducing a decoder fusion module (DFM) in the encoding part, effectively combining different convolutional blocks to extract features comprehensively. Additionally, in the decoding part of U-Net, we propose the context squeeze and excitation (CSE) decoding module to enhance important contextual feature information and the detection of tiny blood vessels. For the final output, we introduce the supervised fusion mechanism (SFM), which combines multiple branches from shallow to deep layers, effectively fusing multi-scale features and capturing information from different levels, fully integrating low-level and high-level features to improve segmentation performance. Our experimental results on the public datasets of DRIVE, STARE, and CHASED_B1 demonstrate the excellent performance of our proposed network.

TDCAU-Net: retinal vessel segmentation using transformer dilated convolutional attention-based U-Net method

Retinal vessel segmentation plays a vital role in the medical field, facilitating the identification of numerous chronic conditions based on retinal vessel images. These conditions include diabetic retinopathy, hypertensive retinopathy, glaucoma, and others. Although the U-Net model has shown promising results in retinal vessel segmentation, it tends to struggle with fine branching and dense vessel segmentation. To further enhance the precision of retinal vessel segmentation, we propose a novel approach called transformer dilated convolution attention U-Net (TDCAU-Net), which builds upon the U-Net architecture with improved Transformer-based dilated convolution attention mechanisms. The proposed model retains the three-layer architecture of the U-Net network. The Transformer component enables the learning of contextual information for each pixel in the image, while the dilated convolution attention prevents information loss. The algorithm efficiently addresses several challenges to optimize blood vessel detection. The process starts with five-step preprocessing of the images, followed by chunking them into segments. Subsequently, the retinal images are fed into the modified U-Net network introduced in this paper for segmentation. The study employs eye fundus images from the DRIVE and CHASEDB1 databases for both training and testing purposes. Evaluation metrics are utilized to compare the algorithm's results with state-of-the-art methods. The experimental analysis on both databases demonstrates that the algorithm achieves high values of sensitivity, specificity, accuracy, and AUC. Specifically, for the first database, the achieved values are 0.8187, 0.9756, 0.9556, and 0.9795, respectively. For the second database, the corresponding values are 0.8243, 0.9836, 0.9738, and 0.9878, respectively. These results demonstrate that the proposed approach outperforms state-of-the-art methods, achieving higher performance on both datasets. The TDCAU-Net model presented in this study exhibits substantial capabilities in accurately segmenting fine branching and dense vessels. The segmentation performance of the network surpasses that of the U-Net algorithm and several mainstream methods.

CCS-UNet: a cross-channel spatial attention model for accurate retinal vessel segmentation

Precise segmentation of retinal vessels plays an important role in computer-assisted diagnosis. Deep learning models have been applied to retinal vessel segmentation, but the efficacy is limited by the significant scale variation of vascular structures and the intricate background of retinal images. This paper supposes a cross-channel spatial attention U-Net (CCS-UNet) for accurate retinal vessel segmentation. In comparison to other models based on U-Net, our model employes a ResNeSt block for the encoder-decoder architecture. The block has a multi-branch structure that enables the model to extract more diverse vascular features. It facilitates weight distribution across channels through the incorporation of soft attention, which effectively aggregates contextual information in vascular images. Furthermore, we suppose an attention mechanism within the skip connection. This mechanism serves to enhance feature integration across various layers, thereby mitigating the degradation of effective information. It helps acquire cross-channel information and enhance the localization of regions of interest, ultimately leading to improved recognition of vascular structures. In addition, the feature fusion module (FFM) module is used to provide semantic information for a more refined vascular segmentation map. We evaluated CCS-UNet based on five benchmark retinal image datasets, DRIVE, CHASEDB1, STARE, IOSTAR and HRF. Our proposed method exhibits superior segmentation efficacy compared to other state-of-the-art techniques with a global accuracy of 0.9617/0.9806/0.9766/0.9786/0.9834 and AUC of 0.9863/0.9894/0.9938/0.9902/0.9855 on DRIVE, CHASEDB1, STARE, IOSTAR and HRF respectively. Ablation studies are also performed to evaluate the the relative contributions of different architectural components. Our proposed model is potential for diagnostic aid of retinal diseases.

3D vessel extraction using a scale-adaptive hybrid parametric tracker

3D vessel extraction has great significance in the diagnosis of vascular diseases. However, accurate extraction of vessels from computed tomography angiography (CTA) data is challenging. For one thing, vessels in different body parts have a wide range of scales and large curvatures; for another, the intensity distributions of vessels in different CTA data vary considerably. Besides, surrounding interfering tissue, like bones or veins with similar intensity, also seriously affects vessel extraction. Considering all the above imaging and structural features of vessels, we propose a new scale-adaptive hybrid parametric tracker (SAHPT) to extract arbitrary vessels of different body parts. First, a geometry-intensity parametric model is constructed to calculate the geometry-intensity response. While geometry parameters are calculated to adapt to the variation in scale, intensity parameters can also be estimated to meet non-uniform intensity distributions. Then, a gradient parametric model is proposed to calculate the gradient response based on a multiscale symmetric normalized gradient filter which can effectively separate the target vessel from surrounding interfering tissue. Last, a hybrid parametric model that combines the geometry-intensity and gradient parametric models is constructed to evaluate how well it fits a local image patch. In the extraction process, a multipath spherical sampling strategy is used to solve the problem of anatomical complexity. We have conducted many quantitative experiments using the synthetic and clinical CTA data, asserting its superior performance compared to traditional or deep learning-based baselines.

Global Transformer and Dual Local Attention Network via Deep-Shallow Hierarchical Feature Fusion for Retinal Vessel Segmentation

Clinically, retinal vessel segmentation is a significant step in the diagnosis of fundus diseases. However, recent methods generally neglect the difference of semantic information between deep and shallow features, which fail to capture the global and local characterizations in fundus images simultaneously, resulting in the limited segmentation performance for fine vessels. In this article, a global transformer (GT) and dual local attention (DLA) network via deep-shallow hierarchical feature fusion (GT-DLA-dsHFF) are investigated to solve the above limitations. First, the GT is developed to integrate the global information in the retinal image, which effectively captures the long-distance dependence between pixels, alleviating the discontinuity of blood vessels in the segmentation results. Second, DLA, which is constructed using dilated convolutions with varied dilation rates, unsupervised edge detection, and squeeze-excitation block, is proposed to extract local vessel information, consolidating the edge details in the segmentation result. Finally, a novel deep-shallow hierarchical feature fusion (dsHFF) algorithm is studied to fuse the features in different scales in the deep learning framework, respectively, which can mitigate the attenuation of valid information in the process of feature fusion. We verified the GT-DLA-dsHFF on four typical fundus image datasets. The experimental results demonstrate our GT-DLA-dsHFF achieves superior performance against the current methods and detailed discussions verify the efficacy of the proposed three modules. Segmentation results of diseased images show the robustness of our proposed GT-DLA-dsHFF. Implementation codes will be available on https://github.com/YangLibuaa/GT-DLA-dsHFF.

MIL-CT: Multiple Instance Learning via a Cross-Scale Transformer for Enhanced Arterial Light Reflex Detection

One of the early manifestations of systemic atherosclerosis, which leads to blood circulation issues, is the enhanced arterial light reflex (EALR). Fundus images are commonly used for regular screening purposes to intervene and assess the severity of systemic atherosclerosis in a timely manner. However, there is a lack of automated methods that can meet the demands of large-scale population screening. Therefore, this study introduces a novel cross-scale transformer-based multi-instance learning method, named MIL-CT, for the detection of early arterial lesions (e.g., EALR) in fundus images. MIL-CT utilizes the cross-scale vision transformer to extract retinal features in a multi-granularity perceptual domain. It incorporates a multi-head cross-scale attention fusion module to enhance global perceptual capability and feature representation. By integrating information from different scales and minimizing information loss, the method significantly improves the performance of the EALR detection task. Furthermore, a multi-instance learning module is implemented to enable the model to better comprehend local details and features in fundus images, facilitating the classification of patch tokens related to retinal lesions. To effectively learn the features associated with retinal lesions, we utilize weights pre-trained on a large fundus image Kaggle dataset. Our validation and comparison experiments conducted on our collected EALR dataset demonstrate the effectiveness of the MIL-CT method in reducing generalization errors while maintaining efficient attention to retinal vascular details. Moreover, the method surpasses existing models in EALR detection, achieving an accuracy, precision, sensitivity, specificity, and F1 score of 97.62%, 97.63%, 97.05%, 96.48%, and 97.62%, respectively. These results exhibit the significant enhancement in diagnostic accuracy of fundus images brought about by the MIL-CT method. Thus, it holds potential for various applications, particularly in the early screening of cardiovascular diseases such as hypertension and atherosclerosis.

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

Vessel segmentation is crucial in many medical image applications, such as detecting coronary stenoses, retinal vessel diseases and brain aneurysms. However, achieving high pixel-wise accuracy, complete topology structure and robustness to various contrast variations are critical and challenging, and most existing methods focus only on achieving one or two of these aspects. In this paper, we present a novel approach, the affinity feature strengthening network (AFN), which jointly models geometry and refines pixel-wise segmentation features using a contrast-insensitive, multiscale affinity approach. Specifically, we compute a multiscale affinity field for each pixel, capturing its semantic relationships with neighboring pixels in the predicted mask image. This field represents the local geometry of vessel segments of different sizes, allowing us to learn spatial- and scale-aware adaptive weights to strengthen vessel features. We evaluate our AFN on four different types of vascular datasets: X-ray angiography coronary vessel dataset (XCAD), portal vein dataset (PV), digital subtraction angiography cerebrovascular vessel dataset (DSA) and retinal vessel dataset (DRIVE). Extensive experimental results demonstrate that our AFN outperforms the state-of-the-art methods in terms of both higher accuracy and topological metrics, while also being more robust to various contrast changes.

Landmark-Assisted Anatomy-Sensitive Retinal Vessel Segmentation Network

Automatic retinal vessel segmentation is important for assisting clinicians in diagnosing ophthalmic diseases. The existing deep learning methods remain constrained in instance connectivity and thin vessel detection. To this end, we propose a novel anatomy-sensitive retinal vessel segmentation framework to preserve instance connectivity and improve the segmentation accuracy of thin vessels. This framework uses TransUNet as its backbone and utilizes self-supervised extracted landmarks to guide network learning. TransUNet is designed to simultaneously benefit from the advantages of convolutional and multi-head attention mechanisms in extracting local features and modeling global dependencies. In particular, we introduce contrastive learning-based self-supervised extraction anatomical landmarks to guide the model to focus on learning the morphological information of retinal vessels. We evaluated the proposed method on three public datasets: DRIVE, CHASE-DB1, and STARE. Our method demonstrates promising results on the DRIVE and CHASE-DB1 datasets, outperforming state-of-the-art methods by improving the F1 scores by 0.36% and 0.31%, respectively. On the STARE dataset, our method achieves results close to the best-performing methods. Visualizations of the results highlight the potential of our method in maintaining topological continuity and identifying thin blood vessels. Furthermore, we conducted a series of ablation experiments to validate the effectiveness of each module in our model and considered the impact of image resolution on the results.

A lightweight network guided with differential matched filtering for retinal vessel segmentation

The geometric morphology of retinal vessels reflects the state of cardiovascular health, and fundus images are important reference materials for ophthalmologists. Great progress has been made in automated vessel segmentation, but few studies have focused on thin vessel breakage and false-positives in areas with lesions or low contrast. In this work, we propose a new network, differential matched filtering guided attention UNet (DMF-AU), to address these issues, incorporating a differential matched filtering layer, feature anisotropic attention, and a multiscale consistency constrained backbone to perform thin vessel segmentation. The differential matched filtering is used for the early identification of locally linear vessels, and the resulting rough vessel map guides the backbone to learn vascular details. Feature anisotropic attention reinforces the vessel features of spatial linearity at each stage of the model. Multiscale constraints reduce the loss of vessel information while pooling within large receptive fields. In tests on multiple classical datasets, the proposed model performed well compared with other algorithms on several specially designed criteria for vessel segmentation. DMF-AU is a high-performance, lightweight vessel segmentation model. The source code is at https://github.com/tyb311/DMF-AU.

BCU-Net: Bridging ConvNeXt and U-Net for medical image segmentation

Medical image segmentation enables doctors to observe lesion regions better and make accurate diagnostic decisions. Single-branch models such as U-Net have achieved great progress in this field. However, the complementary local and global pathological semantics of heterogeneous neural networks have not yet been fully explored. The class-imbalance problem remains a serious issue. To alleviate these two problems, we propose a novel model called BCU-Net, which leverages the advantages of ConvNeXt in global interaction and U-Net in local processing. We propose a new multilabel recall loss (MRL) module to relieve the class imbalance problem and facilitate deep-level fusion of local and global pathological semantics between the two heterogeneous branches. Extensive experiments were conducted on six medical image datasets including retinal vessel and polyp images. The qualitative and quantitative results demonstrate the superiority and generalizability of BCU-Net. In particular, BCU-Net can handle diverse medical images with diverse resolutions. It has a flexible structure owing to its plug-and-play characteristics, which promotes its practicality.

Computational intelligence in eye disease diagnosis: a comparative study

In recent years, eye disorders are an important health issue among older people. Generally, individuals with eye diseases are unaware of the gradual growth of symptoms. Therefore, routine eye examinations are required for early diagnosis. Usually, eye disorders are identified by an ophthalmologist via a slit-lamp investigation. Slit-lamp interpretations are inadequate due to the differences in the analytical skills of the ophthalmologist, inconsistency in eye disorder analysis, and record maintenance issues. Therefore, digital images of an eye and computational intelligence (CI)-based approaches are preferred as assistive methods for eye disease diagnosis. A comparative study of CI-based decision support models for eye disorder diagnosis is presented in this paper. The CI-based decision support systems used for eye abnormalities diagnosis were grouped as anterior and retinal eye abnormalities diagnostic systems, and numerous algorithms used for diagnosing the eye abnormalities were also briefed. Various eye imaging modalities, pre-processing methods such as reflection removal, contrast enhancement, region of interest segmentation methods, and public eye image databases used for CI-based eye disease diagnosis system development were also discussed in this paper. In this comparative study, the reliability of various CI-based systems used for anterior eye and retinal disorder diagnosis was compared based on the precision, sensitivity, and specificity in eye disease diagnosis. The outcomes of the comparative analysis indicate that the CI-based anterior and retinal disease diagnosis systems attained significant prediction accuracy. Hence, these CI-based diagnosis systems can be used in clinics to reduce the burden on physicians, minimize fatigue-related misdetection, and take precise clinical decisions.

Prompt Deep Light-Weight Vessel Segmentation Network (PLVS-Net)

Achieving accurate retinal vessel segmentation is critical in the progression and diagnosis of vision-threatening diseases such as diabetic retinopathy and age-related macular degeneration. Existing vessel segmentation methods are based on encoder-decoder architectures, which frequently fail to take into account the retinal vessel structure's context in their analysis. As a result, such methods have difficulty bridging the semantic gap between encoder and decoder characteristics. This paper proposes a Prompt Deep Light-weight Vessel Segmentation Network (PLVS-Net) to address these issues by using prompt blocks. Each prompt block use combination of asymmetric kernel convolutions, depth-wise separable convolutions, and ordinary convolutions to extract useful features. This novel strategy improves the performance of the segmentation network while simultaneously decreasing the number of trainable parameters. Our method outperformed competing approaches in the literature on three benchmark datasets, including DRIVE, STARE, and CHASE.

MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image

PURPOSE

Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties.

METHOD

This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information.

RESULTS

We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively.

CONCLUSIONS

Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.

Retinal blood vessel segmentation by using the MS-LSDNet network and geometric skeleton reconnection method

Automatic retinal blood vessel segmentation is a key link in the diagnosis of ophthalmic diseases. Recent deep learning methods have achieved high accuracy in vessel segmentation but still face challenges in maintaining vascular structural connectivity. Therefore, this paper proposes a novel retinal blood vessel segmentation strategy that includes three stages: vessel structure detection, vessel branch extraction and broken vessel segment reconnection. First, we propose a multiscale linear structure detection network (MS-LSDNet), which improves the detection ability of fine blood vessels by learning the types of rich hierarchical features. In addition, to maintain the connectivity of the vascular structure in the process of binarization of the vascular probability map, an adaptive hysteresis threshold method for vascular extraction is proposed. Finally, we propose a vascular tree structure reconstruction algorithm based on a geometric skeleton to connect the broken vessel segments. Experimental results on three publicly available datasets show that compared with current state-of-the-art algorithms, our strategy effectively maintains the connectivity of retinal vascular tree structure.

Feature preserving mesh network for semantic segmentation of retinal vasculature to support ophthalmic disease analysis

Introduction

Ophthalmic diseases are approaching an alarming count across the globe. Typically, ophthalmologists depend on manual methods for the analysis of different ophthalmic diseases such as glaucoma, Sickle cell retinopathy (SCR), diabetic retinopathy, and hypertensive retinopathy. All these manual assessments are not reliable, time-consuming, tedious, and prone to error. Therefore, automatic methods are desirable to replace conventional approaches. The accuracy of this segmentation of these vessels using automated approaches directly depends on the quality of fundus images. Retinal vessels are assumed as a potential biomarker for the diagnosis of many ophthalmic diseases. Mostly newly developed ophthalmic diseases contain minor changes in vasculature which is a critical job for the early detection and analysis of disease.

Method

Several artificial intelligence-based methods suggested intelligent solutions for automated retinal vessel detection. However, existing methods exhibited significant limitations in segmentation performance, complexity, and computational efficiency. Specifically, most of the existing methods failed in detecting small vessels owing to vanishing gradient problems. To overcome the stated problems, an intelligence-based automated shallow network with high performance and low cost is designed named Feature Preserving Mesh Network (FPM-Net) for the accurate segmentation of retinal vessels. FPM-Net employs a feature-preserving block that preserves the spatial features and helps in maintaining a better segmentation performance. Similarly, FPM-Net architecture uses a series of feature concatenation that also boosts the overall segmentation performance. Finally, preserved features, low-level input image information, and up-sampled spatial features are aggregated at the final concatenation stage for improved pixel prediction accuracy. The technique is reliable since it performs better on the DRIVE database, CHASE-DB1 database, and STARE dataset.

Results and discussion

Experimental outcomes confirm that FPM-Net outperforms state-of-the-art techniques with superior computational efficiency. In addition, presented results are achieved without using any preprocessing or postprocessing scheme. Our proposed method FPM-Net gives improvement results which can be observed with DRIVE datasets, it gives Se, Sp, and Acc as 0.8285, 0.98270, 0.92920, for CHASE-DB1 dataset 0.8219, 0.9840, 0.9728 and STARE datasets it produces 0.8618, 0.9819 and 0.9727 respectively. Which is a remarkable difference and enhancement as compared to the conventional methods using only 2.45 million trainable parameters.

Automated grading system of retinal arterio-venous crossing patterns: A deep learning approach replicating ophthalmologist's diagnostic process of arteriolosclerosis

The morphological feature of retinal arterio-venous crossing patterns is a valuable source of cardiovascular risk stratification as it directly captures vascular health. Although Scheie's classification, which was proposed in 1953, has been used to grade the severity of arteriolosclerosis as diagnostic criteria, it is not widely used in clinical settings as mastering this grading is challenging as it requires vast experience. In this paper, we propose a deep learning approach to replicate a diagnostic process of ophthalmologists while providing a checkpoint to secure explainability to understand the grading process. The proposed pipeline is three-fold to replicate a diagnostic process of ophthalmologists. First, we adopt segmentation and classification models to automatically obtain vessels in a retinal image with the corresponding artery/vein labels and find candidate arterio-venous crossing points. Second, we use a classification model to validate the true crossing point. At last, the grade of severity for the vessel crossings is classified. To better address the problem of label ambiguity and imbalanced label distribution, we propose a new model, named multi-diagnosis team network (MDTNet), in which the sub-models with different structures or different loss functions provide different decisions. MDTNet unifies these diverse theories to give the final decision with high accuracy. Our automated grading pipeline was able to validate crossing points with precision and recall of 96.3% and 96.3%, respectively. Among correctly detected crossing points, the kappa value for the agreement between the grading by a retina specialist and the estimated score was 0.85, with an accuracy of 0.92. The numerical results demonstrate that our method can achieve a good performance in both arterio-venous crossing validation and severity grading tasks following the diagnostic process of ophthalmologists. By the proposed models, we could build a pipeline reproducing ophthalmologists' diagnostic process without requiring subjective feature extractions. The code is available (https://github.com/conscienceli/MDTNet).

An efficient registration-based approach for retinal blood vessel segmentation using generalized Pareto and fatigue pdf

Segmentation of Retinal Blood Vessel (RBV) extraction in the retina images and Registration of segmented RBV structure is implemented to identify changes in vessel structure by ophthalmologists in diagnosis of various illnesses like Glaucoma, Diabetes, and Hypertension's. The Retinal Blood Vessel provides blood to the inner retinal neurons, RBV are located mainly in internal retina but it may partly in the ganglion cell layer, following network failure haven't been identified with past methods. Classifications of accurate RBV and Registration of segmented blood vessels are challenging tasks in the low intensity background of Retinal Image. So, we projected a novel approach of segmentation of RBV extraction used matched filter of Generalized Pareto Probability Distribution Function (pdf) and Registration approach on feature-based segmented retinal blood vessel of Binary Robust Invariant Scalable Key point (BRISK). The BRISK provides the predefined sampling pattern as compared to Pdf. The BRISK feature is implemented for attention point recognition & matching approach for change in vessel structure. The proposed approaches contain 3 levels: pre-processing, matched filter-based Generalized Pareto pdf as a source along with the novel approach of fatigue pdf as a target, and BRISK framework is used for Registration on segmented retinal images of supply & intention images. This implemented system's performance is estimated in experimental analysis by the Average accuracy, Normalized Cross-Correlation (NCC), and computation time process of the segmented retinal source and target image. The NCC is main element to give more statistical information about retinal image segmentation. The proposed approach of Generalized Pareto value pdf has Average Accuracy of 95.21%, NCC of both image pairs is 93%, and Average accuracy of Registration of segmented source images and the target image is 98.51% respectively. The proposed approach of average computational time taken is around 1.4 s, which has been identified on boundary condition of Pdf function.

UCR-Net: U-shaped context residual network for medical image segmentation

Medical image segmentation prerequisite for numerous clinical needs is a critical step in biomedical image analysis. The U-Net framework is one of the most popular deep networks in this field. However, U-Net's successive pooling and downsampling operations result in some loss of spatial information. In this paper, we propose a U-shaped context residual network, called UCR-Net, to capture more context and high-level information for medical image segmentation. The proposed UCR-Net is an encoder-decoder framework comprising a feature encoder module and a feature decoder module. The feature decoder module contains four newly proposed context attention exploration(CAE) modules, a newly proposed global and spatial attention (GSA) module, and four decoder blocks. We use the proposed CAE module to capture more multi-scale context features from the encoder. The proposed GSA module further explores global context features and semantically enhanced deep-level features. The proposed UCR-Net can recover more high-level semantic features and fuse context attention information from CAE and global and spatial attention information from GSA module. Experiments on the retinal vessel, femoropopliteal artery stent, and polyp datasets demonstrate that the proposed UCR-Net performs favorably against the original U-Net and other advanced methods.

CPMF-Net: Multi-Feature Network Based on Collaborative Patches for Retinal Vessel Segmentation

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.

Do you need sharpened details? Asking MMDC-Net: Multi-layer multi-scale dilated convolution network for retinal vessel segmentation

Convolutional neural networks (CNN), especially numerous U-shaped models, have achieved great progress in retinal vessel segmentation. However, a great quantity of global information in fundus images has not been fully explored. And the class imbalance problem of background and blood vessels is still serious. To alleviate these issues, we design a novel multi-layer multi-scale dilated convolution network (MMDC-Net) based on U-Net. We propose an MMDC module to capture sufficient global information under diverse receptive fields through a cascaded mode. Then, we place a new multi-layer fusion (MLF) module behind the decoder, which can not only fuse complementary features but filter noisy information. This enables MMDC-Net to capture the blood vessel details after continuous up-sampling. Finally, we employ a recall loss to resolve the class imbalance problem. Extensive experiments have been done on diverse fundus color image datasets, including STARE, CHASEDB1, DRIVE, and HRF. HRF has a large resolution of 3504 × 2336 whereas others have a small resolution of slightly more than 512 × 512. Qualitative and quantitative results verify the superiority of MMDC-Net. Notably, satisfactory accuracy and sensitivity are acquired by our model. Hence, some key blood vessel details are sharpened. In addition, a large number of further validations and discussions prove the effectiveness and generalization of the proposed MMDC-Net.

Local-Sensitive Connectivity Filter (LS-CF): A Post-Processing Unsupervised Improvement of the Frangi, Hessian and Vesselness Filters for Multimodal Vessel Segmentation

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.

MHA-Net: A Multibranch Hybrid Attention Network for Medical Image Segmentation

The robust segmentation of organs from the medical image is the key technique in medical image analysis for disease diagnosis. U-Net is a robust structure for medical image segmentation. However, U-Net adopts consecutive downsampling encoders to capture multiscale features, resulting in the loss of contextual information and insufficient recovery of high-level semantic features. In this paper, we present a new multibranch hybrid attention network (MHA-Net) to capture more contextual information and high-level semantic features. The main idea of our proposed MHA-Net is to use the multibranch hybrid attention feature decoder to recover more high-level semantic features. The lightweight pyramid split attention (PSA) module is used to connect the encoder and decoder subnetwork to obtain a richer multiscale feature map. We compare the proposed MHA-Net to state-of-art approaches on the DRIVE dataset, the fluoroscopic roentgenographic stereophotogrammetric analysis X-ray dataset, and the polyp dataset. The experimental results on different modal images reveal that our proposed MHA-Net provides better segmentation results than other segmentation approaches.

HT-Net: A Hybrid Transformer Network for Fundus Vessel Segmentation

Doctors usually diagnose a disease by evaluating the pattern of abnormal blood vessels in the fundus. At present, the segmentation of fundus blood vessels based on deep learning has achieved great success, but it still faces the problems of low accuracy and capillary rupture. A good vessel segmentation method can guide the early diagnosis of eye diseases, so we propose a novel hybrid Transformer network (HT-Net) for fundus imaging analysis. HT-Net can improve the vessel segmentation quality by capturing detailed local information and implementing long-range information interactions, and it mainly consists of the following blocks. The feature fusion block (FFB) is embedded in the shallow levels, and FFB enriches the feature space. In addition, the feature refinement block (FRB) is added to the shallow position of the network, which solves the problem of vessel scale change by fusing multi-scale feature information to improve the accuracy of segmentation. Finally, HT-Net's bottom-level position can capture remote dependencies by combining the Transformer and CNN. We prove the performance of HT-Net on the DRIVE, CHASE_DB1, and STARE datasets. The experiment shows that FFB and FRB can effectively improve the quality of microvessel segmentation by extracting multi-scale information. Embedding efficient self-attention mechanisms in the network can effectively improve the vessel segmentation accuracy. The HT-Net exceeds most existing methods, indicating that it can perform the task of vessel segmentation competently.

Retinal Vessel Segmentation With Skeletal Prior and Contrastive Loss

The morphology of retinal vessels is closely associated with many kinds of ophthalmic diseases. Although huge progress in retinal vessel segmentation has been achieved with the advancement of deep learning, some challenging issues remain. For example, vessels can be disturbed or covered by other components presented in the retina (such as optic disc or lesions). Moreover, some thin vessels are also easily missed by current methods. In addition, existing fundus image datasets are generally tiny, due to the difficulty of vessel labeling. In this work, a new network called SkelCon is proposed to deal with these problems by introducing skeletal prior and contrastive loss. A skeleton fitting module is developed to preserve the morphology of the vessels and improve the completeness and continuity of thin vessels. A contrastive loss is employed to enhance the discrimination between vessels and background. In addition, a new data augmentation method is proposed to enrich the training samples and improve the robustness of the proposed model. Extensive validations were performed on several popular datasets (DRIVE, STARE, CHASE, and HRF), recently developed datasets (UoA-DR, IOSTAR, and RC-SLO), and some challenging clinical images (from RFMiD and JSIEC39 datasets). In addition, some specially designed metrics for vessel segmentation, including connectivity, overlapping area, consistency of vessel length, revised sensitivity, specificity, and accuracy were used for quantitative evaluation. The experimental results show that, the proposed model achieves state-of-the-art performance and significantly outperforms compared methods when extracting thin vessels in the regions of lesions or optic disc. Source code is available at https://www.github.com/tyb311/SkelCon.

Retinal Vessel Segmentation, a Review of Classic and Deep Methods

Retinal illnesses such as diabetic retinopathy (DR) are the main causes of vision loss. In the early recognition of eye diseases, the segmentation of blood vessels in retina images plays an important role. Different symptoms of ocular diseases can be identified by the geometric features of ocular arteries. However, due to the complex construction of the blood vessels and their different thicknesses, segmenting the retina image is a challenging task. There are a number of algorithms that helped the detection of retinal diseases. This paper presents an overview of papers from 2016 to 2022 that discuss machine learning and deep learning methods for automatic vessel segmentation. The methods are divided into two groups: Deep learning-based, and classic methods. Algorithms, classifiers, pre-processing and specific techniques of each group is described, comprehensively. The performances of recent works are compared based on their achieved accuracy in different datasets in inclusive tables. A survey of most popular datasets like DRIVE, STARE, HRF and CHASE_DB1 is also given in this paper. Finally, a list of findings from this review is presented in the conclusion section.

The RETA Benchmark for Retinal Vascular Tree Analysis

Topological and geometrical analysis of retinal blood vessels could be a cost-effective way to detect various common diseases. Automated vessel segmentation and vascular tree analysis models require powerful generalization capability in clinical applications. In this work, we constructed a novel benchmark RETA with 81 labelled vessel masks aiming to facilitate retinal vessel analysis. A semi-automated coarse-to-fine workflow was proposed for vessel annotation task. During database construction, we strived to control inter-annotator and intra-annotator variability by means of multi-stage annotation and label disambiguation on self-developed dedicated software. In addition to binary vessel masks, we obtained other types of annotations including artery/vein masks, vascular skeletons, bifurcations, trees and abnormalities. Subjective and objective quality validations of the annotated vessel masks demonstrated significantly improved quality over the existing open datasets. Our annotation software is also made publicly available serving the purpose of pixel-level vessel visualization. Researchers could develop vessel segmentation algorithms and evaluate segmentation performance using RETA. Moreover, it might promote the study of cross-modality tubular structure segmentation and analysis.

TiM-Net: Transformer in M-Net for Retinal Vessel Segmentation

retinal image is a crucial window for the clinical observation of cardiovascular, cerebrovascular, or other correlated diseases. Retinal vessel segmentation is of great benefit to the clinical diagnosis. Recently, the convolutional neural network (CNN) has become a dominant method in the retinal vessel segmentation field, especially the U-shaped CNN models. However, the conventional encoder in CNN is vulnerable to noisy interference, and the long-rang relationship in fundus images has not been fully utilized. In this paper, we propose a novel model called Transformer in M-Net (TiM-Net) based on M-Net, diverse attention mechanisms, and weighted side output layers to efficaciously perform retinal vessel segmentation. First, to alleviate the effects of noise, a dual-attention mechanism based on channel and spatial is designed. Then the self-attention mechanism in Transformer is introduced into skip connection to re-encode features and model the long-range relationship explicitly. Finally, a weighted SideOut layer is proposed for better utilization of the features from each side layer. Extensive experiments are conducted on three public data sets to show the effectiveness and robustness of our TiM-Net compared with the state-of-the-art baselines. Both quantitative and qualitative results prove its clinical practicality. Moreover, variants of TiM-Net also achieve competitive performance, demonstrating its scalability and generalization ability. The code of our model is available at https://github.com/ZX-ECJTU/TiM-Net.

Development of an approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms

Purpose: In stable coronary artery disease (CAD), reduction in mortality and/or myocardial infarction with revascularization over medical therapy has not been reliably achieved. Coronary arteries are usually extracted to perform stenosis detection. As such, developing accurate segmentation of vascular structures and quantification of coronary arterial stenosis in invasive coronary angiograms (ICA) is necessary. Approach: A multi-input and multiscale (MIMS) U-Net with a two-stage recurrent training strategy was proposed for the automatic vessel segmentation. The proposed model generated a refined prediction map with the following two training stages: (i) stage I coarsely segmented the major coronary arteries from preprocessed single-channel ICAs and generated the probability map of arteries; and (ii) during the stage II, a three-channel image consisting of the original preprocessed image, a generated probability map, and an edge-enhanced image generated from the preprocessed image was fed to the proposed MIMS U-Net to produce the final segmentation result. After segmentation, an arterial stenosis detection algorithm was developed to extract vascular centerlines and calculate arterial diameters to evaluate stenotic level. Results: Experimental results demonstrated that the proposed method achieved an average Dice similarity coefficient of 0.8329, an average sensitivity of 0.8281, and an average specificity of 0.9979 in our dataset with 294 ICAs obtained from 73 patients. Moreover, our stenosis detection algorithm achieved a true positive rate of 0.6668 and a positive predictive value of 0.7043. Conclusions: Our proposed approach has great promise for clinical use and could help physicians improve diagnosis and therapeutic decisions for CAD.

Multifilters-Based Unsupervised Method for Retinal Blood Vessel Segmentation

Fundus imaging is one of the crucial methods that help ophthalmologists for diagnosing the various eye diseases in modern medicine. An accurate vessel segmentation method can be a convenient tool to foresee and analyze fatal diseases, including hypertension or diabetes, which damage the retinal vessel’s appearance. This work suggests an unsupervised approach for vessels segmentation out of retinal images. The proposed method includes multiple steps. Firstly, from the colored retinal image, green channel is extracted and preprocessed utilizing Contrast Limited Histogram Equalization as well as Fuzzy Histogram Based Equalization for contrast enhancement. To expel geometrical articles (macula, optic disk) and noise, top-hat morphological operations are used. On the resulted enhanced image, matched filter and Gabor wavelet filter are applied, and the outputs from both is added to extract vessels pixels. The resulting image with the now noticeable blood vessel is binarized using human visual system (HVS). A final image of segmented blood vessel is obtained by applying post-processing. The suggested method is assessed on two public datasets (DRIVE and STARE) and showed comparable results with regard to sensitivity, specificity and accuracy. The results we achieved with respect to sensitivity, specificity together with accuracy on DRIVE database are 0.7271, 0.9798 and 0.9573, and on STARE database these are 0.7164, 0.9760, and 0.9560, respectively, in less than 3.17 s on average per image.

Data-Driven Deep Supervision for Medical Image Segmentation

Medical image segmentation plays a vital role in disease diagnosis and analysis. However, data-dependent difficulties such as low image contrast, noisy background, and complicated objects of interest render the segmentation problem challenging. These difficulties diminish dense prediction and make it tough for known approaches to explore data-specific attributes for robust feature extraction. In this paper, we study medical image segmentation by focusing on robust data-specific feature extraction to achieve improved dense prediction. We propose a new deep convolutional neural network (CNN), which exploits specific attributes of input datasets to utilize deep supervision for enhanced feature extraction. In particular, we strategically locate and deploy auxiliary supervision, by matching the object perceptive field (OPF) (which we define and compute) with the layer-wise effective receptive fields (LERF) of the network. This helps the model pay close attention to some distinct input data dependent features, which the network might otherwise 'ignore' during training. Further, to achieve better target localization and refined dense prediction, we propose the densely decoded networks (DDN), by selectively introducing additional network connections (the 'crutch' connections). Using five public datasets (two retinal vessel, melanoma, optic disc/cup, and spleen segmentation) and two in-house datasets (lymph node and fungus segmentation), we verify the effectiveness of our proposed approach in 2D and 3D segmentation.

U-shaped Retinal Vessel Segmentation Based on Adaptive Aggregation of Feature Information

Detection and analysis of retinal blood vessels contribute to the clinical diagnosis of many ophthalmic diseases. In this paper, aiming on achieving more accurate segmentation of retinal vessels and enhance the ability of the algorithm to identify microvessels, we propose a U-shaped network based on adaptive aggregation of feature information. The introduced feature selection module, which could strengthen feature transmission and selectively emphasize feature information. To effectively capture the characteristics of vessels at different scales, generate richer and denser context information, and DenseASPP is embedded at the bottom of the network. Meanwhile, we propose an adaptive aggregation module to aggregate the semantic information in each layer of the encoder part and transmit it to subsequent layers, which is beneficial to the spatial reconstruction of retinal vessels. A joint loss function is also introduced to facilitate network training. The proposed network is evaluated on three public datasets. The sensitivity, accuracy, and area under curve(AUC) are 83.48%/83.16/85.86, 95.67%/96.67%/96.52%, and 98.11%/98.69%/98.60% on DRIVE, STARE and CHASE_DB1, respectively. In order to achieve more accurate retinal blood vessel segmentation and improve the ability of the algorithm to identify microvessels. We propose a U-shaped network based on adaptive aggregation of feature information. The introduction of the adaptive aggregation module aggregates the semantic information of each level of the encoder part, which improves the robustness of the model to segment blood vessels.

A Lightweight Network for Accurate Coronary Artery Segmentation Using X-Ray Angiograms

An accurate and automated segmentation of coronary arteries in X-ray angiograms is essential for cardiologists to diagnose coronary artery disease in clinics. The existing deep learning-based coronary arteries segmentation models focus on using complex networks to improve the accuracy of segmentation while ignoring the computational cost. However, performing such segmentation networks requires a high-performance device with a powerful GPU and a high bandwidth memory. To address this issue, in this study, a lightweight deep learning network is developed for a better balance between computational cost and segmentation accuracy. We have made two efforts in designing the network. On the one hand, we adopt bottleneck residual blocks to replace the internal components in the encoder and decoder of the traditional U-Net to make the network more lightweight. On the other hand, we embed the two attention modules to model long-range dependencies in spatial and channel dimensions for the accuracy of segmentation. In addition, we employ Top-hat transforms and contrast-limited adaptive histogram equalization (CLAHE) as the pre-processing strategy to enhance the coronary arteries to further improve the accuracy. Experimental evaluations conducted on the coronary angiograms dataset show that the proposed lightweight network performs well for accurate coronary artery segmentation, achieving the sensitivity, specificity, accuracy, and area under the curve (AUC) of 0.8770, 0.9789, 0.9729, and 0.9910, respectively. It is noteworthy that the proposed network contains only 0.75 M of parameters, which achieves the best performance by the comparative experiments with popular segmentation networks (such as U-Net with 31.04 M of parameters). Experimental results demonstrate that our network can achieve better performance with an extremely low number of parameters. Furthermore, the generalization experiments indicate that our network can accurately segment coronary angiograms from other coronary angiograms' databases, which demonstrates the strong generalization and robustness of our network.