MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation

Purpose Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

Assessment of blood vessels in retinal images is an important factor for many medical disorders. The changes in the retinal vessels due to the pathologies can be easily identified by segmenting the retinal vessels. Segmentation of retinal vessels is done to identify the early diagnosis of the disease like glaucoma, diabetic retinopathy, macular degeneration, hypertensive retinopathy and arteriosclerosis. In this paper, we propose two automatic blood vessel segmentation methods. The first proposed algorithm starts with the extraction of blood vessel centerline pixels. The final segmentation is obtained using an iterative region growing method that merges the contents of several binary images resulting from vessel width dependent modified morphological filters on normalized retinal images. In the second proposed algorithm the blood vessel is segmented using normalized modified morphological operations and neuro fuzzy classifier. Normalized morphological operations are used to enhance the vessels and neuro fuzzy classifier is used to segment retinal blood vessels. These methods are applied on the publicly available DRIVE database and the experimental results obtained by using green channel images have been presented and their results are compared with recently published methods. The results demonstrate that our algorithms are very effective methods to detect retinal blood vessels. DOI: http://dx.doi.org/10.11591/ijece.v4i3.5829

Vascular diseases cause tortuosity in the retinal blood vessel's structure which can be identified using fundus images.The computerized retinal vessel tortuosity diagnosis is suffered from high time consuming and less accuracy due to the less effective retinal vessel segmentation algorithms.The success of retinal vessel tortuosity diagnosis depends on the performance quality of the vessel segmentation algorithm.Hence, this research proposes a new retinal vessel segmentation method, namely 'Retinal Vessel Segmentation using CLAHE and VJSTFD (RVSCV)'.The proposed segmentation method separates the vessel region from the background, tissue region, and Optic Disc (OD).It is constituted by two algorithms, viz.(i) vessel enhancement based on Contrast Limited Adaptive Histogram Equalization (CLAHE) and (ii) Vessel Joining algorithm based on vessel Skeletonization and Tetra vessel Flow Directions (VJSTFD).The CLAHE method, which is an existing method, enhances the vessel structure.The main contribution of this paper is the VJSTFD algorithm, which is a novel method to segment the vessel region from the enhanced fundus image.The VJSTFD algorithm makes a binary segmentation and joints the broken vessels in a novel approach through vessel skeletonization and tetra vessel flow directions-based vessel extension.The specialty of this approach is that minute vessels are also captured for segmentation even at the low contrast level because of the proposed preeminence vessel joining approach that is powered by tetra direction-based vessel searching.The CHASE_DB, RITE_DB, and STARE_DB databases have been involved in the testing process.These databases have retinal fundus images which clearly exposes the retinal vessel areas.Experimental results reveal that the proposed RVSCV method accomplishes the overall average F-score of 0.9580, along with the average segmentation accuracy of 96.73% in retinal vessel segmentation.The proposed method can be activated as a tool for ophthalmologists to extract the vessel course essentially.

The segmentation of fundus vascular images is a key step in retinal image processing and analysis. It plays an important role in the early prevention and diagnosis of eye diseases and blood system diseases. In view of the low accuracy of retinal blood vessel segmentation caused by the complex features of fundus images, the presence of soft, hard penetrant and bleeding noises, the low contrast between retinal blood vessels and background, uneven changes in width and curvature, small shape and blurred edges, this paper proposes a new network model RCU-Net for retinal vessel segmentation. Specifically, this paper proposes CBAM-Conv convolution block and RA-Conv convolution block based on visual attention mechanism (CBAM) and residual connection idea, which can make the network better use of the information at the spatial and channel levels. Experiments were carried out in public datasets DRIVE and CHASE_DB1. The accuracy, sensitivity, F1-Score and AUC of RCU-Net network on DRIVE datasets reached 96.75%, 82.02%, 81.45% and 98.33% respectively. Compared with the classical U-Net network, the proposed model can effectively improve the performance of retinal vessel segmentation.

Fractional and B-COSFIRE filter based approach for efficient segmentation of retinal blood vessels

Medical image segmentation of tissue abnormalities, key organs, or blood vascular system is of great significance for any computerized diagnostic system. However, automatic segmentation in medical image analysis is a challenging task since it requires sophisticated knowledge of the target organ anatomy. This paper develops an end-to-end deep learning segmentation method called Contextual Multi-Scale Multi-Level Network (CMM-Net). The main idea is to fuse the global contextual features of multiple spatial scales at every contracting convolutional network level in the U-Net. Also, we re-exploit the dilated convolution module that enables an expansion of the receptive field with different rates depending on the size of feature maps throughout the networks. In addition, an augmented testing scheme referred to as Inversion Recovery (IR) which uses logical “OR” and “AND” operators is developed. The proposed segmentation network is evaluated on three medical imaging datasets, namely ISIC 2017 for skin lesions segmentation from dermoscopy images, DRIVE for retinal blood vessels segmentation from fundus images, and BraTS 2018 for brain gliomas segmentation from MR scans. The experimental results showed superior state-of-the-art performance with overall dice similarity coefficients of 85.78%, 80.27%, and 88.96% on the segmentation of skin lesions, retinal blood vessels, and brain tumors, respectively. The proposed CMM-Net is inherently general and could be efficiently applied as a robust tool for various medical image segmentations.

Diabetic retinopathy (DR) is the major ophthalmic disorder because of variation in veins structure which may cause blindness. The retinal vein morphology distinguishes the progressive phases of various sight debilitating maladies and consequently clears an approach to characterize its seriousness. The proposed method for retinal blood vessels detection consists of two major processes: denoising and vasculature segmentation. First, we used denoising preprocessing steps which comprises of Contrast Limited Adaptive Histogram Equalization (CLAHE) for contrast enhancement along with morphological filters to remove low frequency noise, followed by masking to excerpt Region Of Interest (ROI) and difference image of low pass filter to suppress high frequency noise. Adaptive thresholding has been used for vessels segmentation, followed by postprocessing to eliminate unconnected pixels and to obtain Vessel Location Map (VLM). Dilate operation has been used to enhance vessels diameter. In the second step, Combination Of Shifted Filter Responses (B-COSFIRE) for vasculature enhancement along with adaptive thresholding has been applied to segment vessel and background pixels. B represents the bar/vessel like structure. Finally, using pixel by pixel AND operation between VLM and the output of adaptive thresholding, to obtain desired binary image. The proposed framework has been validated on DRIVE and STARE images datasets and compared with other recent approaches for retinal blood vessels segmentation. The proposed scheme provides good results in the term of Accuracy (Acc), Sensitivity (Se) and Specificity (Sp) as compared to other competing methods.

Accurate segmentation of retinal blood vessels plays a vital role in medical image analysis for the diagnosis and management of eye diseases, as most health conditions affect the retinal vascular network.Despite progress made in recent decades, issues such as complex textures, vessel discontinuities, and unidentified areas remain unresolved, particularly in segmenting fine veins and handling low-contrast images.This method integrates three advanced techniques for retinal vessel segmentation.Initially, it applies Adaptive Gradient Domain Guided Image Filtering (AGD-GIF) for preprocessing.Subsequently, it utilizes an efficient feature extraction method called the proposed Cascading Residual Graph Convolutional Network (CRGCN).Finally, segmentation is performed using an enhanced Mask Region-Based Convolutional Neural Network with a Parrot Optimizer (Improved Mask R-CNN-PO), ensuring precision and reliability in detecting retinal vessels from medical images.When tested on the CHASE_DB1 datasets, the proposed model achieves specificity of 99.53%, accuracy of 99.65%, and an AUC of 99%.Additionally, it attains an accuracy of 99.63% and F1 scores of 99.59%.

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.

Automatic segmentation of the retinal vasculature is a first step in computer-assisted diagnosis and treatment planning. The extraction of retinal vessels in pediatric retinal images is challenging because of comparatively wide arterioles with a light streak running longitudinally along the vessel's center, the central vessel reflex. A new method for automatic segmentation was developed and tested. A supervised method for retinal vessel segmentation in the images of multi-ethnic school children was developed based on ensemble classifier of bootstrapped decision trees. A collection of dual Gaussian, second derivative of Gaussian and Gabor filters, along with the generalized multiscale line strength measure and morphological transformation is used to generate the feature vector. The feature vector encodes information to handle the normal vessels as well as the vessels with the central reflex. The methodology is evaluated on CHASE_DB1, a relatively new public retinal image database of multi-ethnic school children, which is a subset of retinal images from the Child Heart and Health Study in England (CHASE) dataset. The segmented retinal images from the CHASE_DB1 database produced best case accuracy, sensitivity and specificity of 0.96, 0.74 and 0.98, respectively, and worst case measures of 0.94, 0.67 and 0.98, respectively. A new retinal blood vessel segmentation algorithm was developed and tested with a shared database. The observed accuracy, speed, robustness and simplicity suggest that the algorithm may be a suitable tool for automated retinal image analysis in large population-based studies.

Objective: The aim of this research is to present a novel computer-aided decision support tool in analyzing, quantifying, and evaluating the retinal blood vessel structure from fluorescein angiogram (FA) videos. Methods: The proposed method consists of three phases: i) image registration for large motion removal from FA videos, followed by ii) retinal vessel segmentation, and lastly, iii) segmentation-guided video magnification. In the image registration phase, individual frames of the FA video are spatiotemporally aligned using a novel wavelet-based registration approach to compensate for the global camera and patient motion. In the second phase, a capsule-based neural network architecture is employed to perform the segmentation of retinal vessels for the first time in the literature. In the final phase, a segmentation-guided Eulerian video magnification is proposed for magnifying subtle changes in the retinal video produced by blood flow through the retinal vessels. The magnification is applied only to the segmented vessels, as determined by the capsule network. This minimizes the high levels of noise present in FA videos and maximizes useful information, enabling ophthalmologists to more easily identify potential regions of pathology. Results: The collected FA video dataset consists of 1402 frames from 10 normal subjects (prospective study). Experimental results for retinal vessel segmentation show that the capsule-based algorithm outperforms a state-of-the-art CNN (U-Net), obtaining a higher dice coefficient (85.94%) and sensitivity (92.36%) while using just 5% of the network parameters. Qualitative analysis of the FA videos was performed after the final phase by expert ophthalmologists, supporting the claim that artificial intelligence assisted decision support tool can be helpful for providing a better analysis of blood flow dynamics. Conclusions: The authors introduce a novel computational tool, combining a wavelet-based video registration method with a deep learning capsule-based retinal vessel segmentation algorithm and a Eulerian video magnification technique to quantitatively and qualitatively analyze FA videos. To authors' best knowledge, this is the first-ever development of such a computational tool to assist ophthalmologists with analyzing blood flow in FA videos.

Accurate retinal vessel segmentation from Optical Coherence Tomography Angiography (OCTA) images is vital in ophthalmic medicine, particularly for the early diagnosis and monitoring of diseases, such as diabetic retinopathy and hypertensive retinopathy. The retinal vascular system exhibits complex characteristics, including branching, crossing, and continuity, which are crucial for precise segmentation and subsequent medical analysis. However, traditional pixel-wise vessel segmentation methods focus on learning how to effectively divide each pixel into different categories, relying mainly on local features, such as intensity and texture, and often neglecting the intrinsic structural properties of vessels. This can cause suboptimal segmentation accuracy and robustness, particularly when handling low-contrast, noisy, or pathologicalimages. This study aims to integrate structural priors into a segmentation framework. Prior embeddings are used to guide the segmentation process, which encode the typical morphology and topological structure of blood vessels. Incorporating these embeddings can improve the accuracy of retinal vessel segmentation, particularly in challenging areas such as small vessels and regions with ambiguous boundaries. This approach could help to preserve the integrity and continuity of the vascular structure, resulting in more reliable and precisesegmentation. This study adopts a generative image segmentation framework. A structured representation in a latent embedding space is presented to explore retinal vessel priors. On this basis, a prior-driven retinal vessel segmentation network is introduced. First, the retinal vessel priors from ground truth data are learned, which are encoded as embedding tokens through a residual quantization reconstruction network. The learned priors are stored in a codebook. In our network, a raw OCTA image is transformed into semantic features using an encoder. Each semantic feature is subsequently represented by a set of embedding tokens from the codebook. Finally, the retinal vessels are reconstructed, preserving the integrity and continuity of the vascular structures using the learned structuralpriors. The performance of our proposed network was assessed across three OCTA datasets: publically available ROSE-1 and ROSE-2, and the private dataset OCTA-Z. Both quantitative and qualitative evaluations revealed that our network outperformed current state-of-the-art methods. In particular, our approach achieved the average Dice scores of 77.63, 71.01, and 81.11% for ROSE-1, ROSE-2, and OCTA-Z,respectively. The experimental results demonstrated that the proposed network effectively learned and utilized implicit vessel priors for OCTA vessel segmentation. Extensive evaluations indicated that our network surpassed the current state-of-the-art methods. Specifically, our reconstruction approach of applying latent prior tokens offered a promising solution for the pattern representation of retinal vessels. In the future, we will extend this method to support more comprehensive retinal structure segmentation and eye-related disease classification tasks. Additionally, we plan to integrate diverse and detailed prior knowledge, such as anatomical and pathological information, to enhance the performance and versatility of ourapproach.

Retinal vessel segmentation has high value for the research on the diagnosis of diabetic retinopathy, hypertension, and cardiovascular and cerebrovascular diseases. Most methods based on deep convolutional neural networks (DCNN) do not have large receptive fields or rich spatial information and cannot capture global context information of the larger areas. Therefore, it is difficult to identify the lesion area, and the segmentation efficiency is poor. This paper presents a butterfly fully convolutional neural network (BFCN). First, in view of the low contrast between blood vessels and the background in retinal blood vessel images, this paper uses automatic color enhancement (ACE) technology to increase the contrast between blood vessels and the background. Second, using the multiscale information extraction (MSIE) module in the backbone network can capture the global contextual information in a larger area to reduce the loss of feature information. At the same time, using the transfer layer (T_Layer) can not only alleviate gradient vanishing problem and repair the information loss in the downsampling process but also obtain rich spatial information. Finally, for the first time in the paper, the segmentation image is postprocessed, and the Laplacian sharpening method is used to improve the accuracy of vessel segmentation. The method mentioned in this paper has been verified by the DRIVE, STARE, and CHASE datasets, with the accuracy of 0.9627, 0.9735, and 0.9688, respectively.

The retinal vascular condition is a reliable biomarker of several ophthalmologic and cardiovascular diseases, so automatic vessel segmentation may be crucial to diagnose and monitor them. However, existing methods have various problems in the segmentation of the retinal vessels, such as insufficient segmentation of retinal vessels, weak anti-noise interference ability. Aiming to the shortcomings of existed methods, this paper proposes an improved model based on the Generative Adversarial Networks with U-Net, which contains densely-connected convolutional network and a novel attention gate (AG) model in the generator, referred as U-GAN, to automatically segment the retinal blood vessels. The method can strengthen feature propagation, substantially reduce the number of parameters, and automatically learn to focus on target structures without additional supervision. By verifying the method on the DRIVE datasets, the segmentation accuracy rate is 96.15%, higher than that of U-Net and R2U-Net.

Objective. Retinal vessel segmentation from optical coherence tomography angiography (OCTA) volumes is significant in analyzing blood supply structures and the diagnosing ophthalmic diseases. However, accurate retinal vessel segmentation in 3D OCTA remains challenging due to the interference of choroidal blood flow signals and the variations in retinal vessel structure. Approach. This paper proposes a layer attention network (LA-Net) for 3D-to-2D retinal vessel segmentation. The network comprises a 3D projection path and a 2D segmentation path. The key component in the 3D path is the proposed multi-scale layer attention module, which effectively learns the layer features of OCT and OCTA to attend to the retinal vessel layer while suppressing the choroidal vessel layer. This module also efficiently captures 3D multi-scale information for improved semantic understanding during projection. In the 2D path, a reverse boundary attention module is introduced to explore and preserve boundary and shape features of retinal vessels by focusing on non-salient regions in deep features. Main results. Experimental results in two subsets of the OCTA-500 dataset showed that our method achieves advanced segmentation performance with Dice similarity coefficients of 93.04% and 89.74%, respectively. Significance. The proposed network provides reliable 3D-to-2D segmentation of retinal vessels, with potential for application in various segmentation tasks that involve projecting the input image. Implementation code: https://github.com/y8421036/LA-Net.