基于密集注意力网络的视网膜血管图像分割

视网膜血管的结构信息对眼科疾病的诊断具有重要的指导意义,对视网膜血管图像进行高效正确的分割成为临床的迫切需求。传统的人工分割方法耗时较长且易受个人主观因素的影响,分割质量不高。为此,提出一种基于密集注意力网络的图像自动分割算法。将编码器-解码器全卷积神经网络的基础结构与密集连接网络相结合,以充分提取每一层的特征,在网络的解码器端引入注意力门模块,对不必要的特征进行抑制,提高视网膜血管图像的分割精度。在DRIVE和STARE眼底图像数据集上的实验结果表明,与其他基于深度学习的算法相比,该算法的敏感性、特异性、准确率和AUC值均较高,分割效果较好。     

基于双注意力编码-解码器架构的视网膜血管分割

眼底视网膜血管的分割提取对于糖尿病、视网膜病、青光眼等眼科疾病的诊断具有重要的意义。针对视网膜血管图像中的血管难以提取、数据量较少等问题,文中提出了一种结合注意力模块和编码-解码器结构的视网膜血管分割方法。首先对编码-解码器卷积神经网络的每个卷积层添加空间和通道注意力模块,加强模型对图像特征的空间信息和通道信息(如血管的大小、形态和连通性等特点)的利用,从而改善视网膜血管的分割效果。其中,空间注意力模块关注于血管的拓扑结构特性,而通道注意力模块关注于血管像素点的正确分类。此外,在训练过程中采用Dice损失函数解决了视网膜血管图像正负样本不均衡的问题。在3个公开的眼底图像数据库DRIVE,STARE和CHASE_DB1上进行了实验,实验数据表明,所提算法的准确率、灵敏度、特异性和AUC值均优于已有的视网膜血管分割方法,其AUC值分别为0.988 9,0.981 2和0.983 1。实验证明,所提算法能够有效提取健康视网膜图像和病变视网膜图像中的血管网络,能够较好地分割细小血管。     

U-net与Dense-net相结合的视网膜血管提取

目的 视网膜血管健康状况的自动分析对糖尿病、心脑血管疾病以及多种眼科疾病的快速无创诊断具有重要参考价值。视网膜图像中血管网络结构复杂且图像背景亮度不均使得血管区域的准确自动提取具有较大难度。本文通过使用具有对称全卷积结构的U-net深度神经网络实现视网膜血管的高精度分割。方法 基于U-net网络中的层次化对称结构和Dense-net网络中的稠密连接方式,提出一种改进的适用于视网膜血管精准提取的深度神经网络模型。首先使用白化预处理技术弱化原始彩色眼底图像中的亮度不均,增强图像中血管区域的对比度;接着对数据集进行随机旋转、Gamma变换操作实现数据增广;然后将每一幅图像随机分割成若干较小的图块,用于减小模型参数规模,降低训练难度。结果 使用多种性能指标对训练后的模型进行综合评定,模型在DRIVE数据集上的灵敏度、特异性、准确率和AUC（area under the curve）分别达到0.740 9、0.992 9、0.970 7和0.917 1。所提算法与目前主流方法进行了全面比较,结果显示本文算法各项性能指标均表现良好。结论 本文针对视网膜图像中血管区域高精度自动提取难度大的问题,提出了一种具有稠密连接方式的对称全卷积神经网络改进模型。结果表明该模型在视网膜血管分割中能够达到良好效果,具有较好的研究及应用价值。     

Construction and verification of retinal vessel segmentation algorithm for color fundus image under BP neural network model

To improve the accuracy of retinal vessel segmentation, a retinal vessel segmentation algorithm for color fundus images based on back-propagation (BP) neural network is proposed according to the characteristics of retinal blood vessels. Four kinds of green channel image enhancement results of adaptive histogram equalization, morphological processing, Gaussian matched filtering, and Hessian matrix filtering are used to form feature vectors. The BP neural network is input to segment blood vessels. Experiments on the color fundus image libraries DRIVE and STARE show that this algorithm can obtain complete retinal blood vessel segmentation as well as connected vessel stems and terminals. When segmenting most small blood vessels, the average accuracy on the DRIVE library reaches 0.9477, and the average accuracy on the STARE library reaches 0.9498, which has a good segmentation effect. Through verification, the algorithm is feasible and effective for blood vessel segmentation of color fundus images and can detect more capillaries.

     

Brain-inspired algorithms for retinal image analysis

Retinal image analysis is a challenging problem due to the precise quantification required and the huge numbers of images produced in screening programs. This paper describes a series of innovative brain-inspired algorithms for automated retinal image analysis, recently developed for the RetinaCheck project, a large-scale screening program for diabetic retinopathy and other retinal diseases in Northeast China. The paper discusses the theory of orientation scores, inspired by cortical multi-orientation pinwheel structures, and presents applications for automated quality assessment, optic nerve head detection, crossing-preserving enhancement and segmentation of retinal vasculature, arterio-venous ratio, fractal dimension, and vessel tortuosity and bifurcations. Many of these algorithms outperform state-of-the-art techniques. The methods are currently validated in collaborating hospitals, with a rich accompanying base of metadata, to phenotype and validate the quantitative algorithms for optimal classification power.     

Quantification and characterisation of arteries in retinal images

A computerised system is presented for the automatic quantification of blood vessel topography in retinal images. This system utilises digital image processing techniques to provide more reliable and comprehensive information for the retinal vascular network. It applies strategies and algorithms for measuring vascular trees and includes methods for locating the centre of a bifurcation, detecting vessel branches, estimating vessel diameter, and calculating angular geometry at a bifurcation. The performance of the system is studied by comparison with manual measurements and by comparing measurements between red-free images and fluorescein images. In general an acceptable degree of accuracy and precision was seen for all measurements, although the system had difficulty dealing with very noisy images and small or especially tortuous blood vessels.     

An analysis of alignment and integral based kernels for machine learning from vessel trajectories

In this paper we present an analysis of the application of the two most important types of similarity measures for moving object trajectories in machine learning from vessel movement data. These similarities are applied in the tasks of clustering, classification and outlier detection. The first similarity type are alignment measures, such as dynamic time warping and edit distance. The second type are based on the integral over time between two trajectories. Following earlier work we define these measures in the context of kernel methods, which provide state-of-the-art, robust algorithms for the tasks studied. Furthermore, we include the influence of applying piecewise linear segmentation as pre-processing to the vessel trajectories when computing alignment measures, since this has been shown to give a positive effect in computation time and performance.In our experiments the alignment based measures show the best performance. Regular versions of edit distance give the best performance in clustering and classification, whereas the softmax variant of dynamic time warping works best in outlier detection. Moreover, piecewise linear segmentation has a positive effect on alignments, due to the fact that salient points in a trajectory, especially important in clustering and outlier detection, are highlighted by the segmentation and have a large influence in the alignments. Based on our experiments, integral over time based similarity measures are not well-suited for learning from vessel trajectories.     

Retinal vessel segmentation employing ANN technique by Gabor and moment invariants-based features

Diabetic retinopathy (DR) is the major ophthalmic pathological cause for loss of eye sight due to changes in blood vessel structure. The retinal blood vessel morphology helps to identify the successive stages of a number of sight threatening diseases and thereby paves a way to classify its severity. This paper presents an automated retinal vessel segmentation technique using neural network, which can be used in computer analysis of retinal images, e.g., in automated screening for diabetic retinopathy. Furthermore, the algorithm proposed in this paper can be used for the analysis of vascular structures of the human retina. Changes in retinal vasculature are one of the main symptoms of diseases like hypertension and diabetes mellitus. Since the size of typical retinal vessel is only a few pixels wide, it is critical to obtain precise measurements of vascular width using automated retinal image analysis. This method segments each image pixel as vessel or nonvessel, which in turn, used for automatic recognition of the vasculature in retinal images. Retinal blood vessels are identified by means of a multilayer perceptron neural network, for which the inputs are derived from the Gabor and moment invariants-based features. Back propagation algorithm, which provides an efficient technique to change the weights in a feed forward network is utilized in our method. The performance of our technique is evaluated and tested on publicly available DRIVE database and we have obtained illustrative vessel segmentation results for those images.     

An approach to localize the retinal blood vessels using bit planes and centerline detection

The change in morphology, diameter, branching pattern or tortuosity of retinal blood vessels is an important indicator of various clinical disorders of the eye and the body. This paper reports an automated method for segmentation of blood vessels in retinal images. A unique combination of techniques for vessel centerlines detection and morphological bit plane slicing is presented to extract the blood vessel tree from the retinal images. The centerlines are extracted by using the first order derivative of a Gaussian filter in four orientations and then evaluation of derivative signs and average derivative values is performed. Mathematical morphology has emerged as a proficient technique for quantifying the blood vessels in the retina. The shape and orientation map of blood vessels is obtained by applying a multidirectional morphological top-hat operator with a linear structuring element followed by bit plane slicing of the vessel enhanced grayscale image. The centerlines are combined with these maps to obtain the segmented vessel tree. The methodology is tested on three publicly available databases DRIVE, STARE and MESSIDOR. The results demonstrate that the performance of the proposed algorithm is comparable with state of the art techniques in terms of accuracy, sensitivity and specificity.     

Retinal vessel segmentation using a probabilistic tracking method

Vessel structures such as retinal vasculature are important features for computer-aided diagnosis. In this paper, a probabilistic tracking method is proposed to detect blood vessels in retinal images. During the tracking process, vessel edge points are detected iteratively using local grey level statistics and vessel's continuity properties. At a given step, a statistic sampling scheme is adopted to select a number of vessel edge points candidates in a local studying area. Local vessel's sectional intensity profiles are estimated by a Gaussian shaped curve. A Bayesian method with the Maximum a posteriori (MAP) probability criterion is then used to identify local vessel's structure and find out the edge points from these candidates. Evaluation is performed on both simulated vascular and real retinal images. Different geometric shapes and noise levels are used for computer simulated images, whereas real retinal images from the REVIEW database are tested. Evaluation performance is done using the Segmentation Matching Factor (SMF) as a quality parameter. Our approach performed better when comparing it with Sun's and Chaudhuri's methods. ROC curves are also plotted, showing effective detection of retinal blood vessels (true positive rate) with less false detection (false positive rate) than Sun's method.     

Automated segmentation of macular layers in OCT images and quantitative evaluation of performances

Optical coherence tomography (OCT) allows high-resolution and noninvasive imaging of the structure of the retina in humans. This technique revolutionized the diagnosis of retinal diseases in routine clinical practice. Nevertheless, quantitative analysis of OCT scans is yet limited to retinal thickness measurements. We propose a novel automated method for the segmentation of eight retinal layers in these images. Our approach is based on global segmentation algorithms, such as active contours and Markov random fields. Moreover, a Kalman filter is designed in order to model the approximate parallelism between the photoreceptor segments and detect them. The performance of the algorithm was tested on a set of retinal images acquired in-vivo from healthy subjects. Results have been compared with manual segmentations performed by five different experts, and intra and inter-physician variability has been evaluated as well. These comparisons have been carried out directly via the computation of the root mean squared error between the segmented interfaces, region-oriented analysis, and retrospectively on the thickness measures derived from the segmentations. This study was performed on a large database including more than seven hundred images acquired from more than one hundred healthy subjects.     

Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results.     

ASRNet: Adversarial Segmentation and Registration Networks for Multispectral Fundus Images

Multispectral imaging (MSI) technique is often used to capture images of the fundus by illuminating it with different wavelengths of light. However, these images are taken at different points in time such that eyeball movements can cause misalignment between consecutive images. The multispectral image sequence reveals important information in the form of retinal and choroidal blood vessel maps, which can help ophthalmologists to analyze the morphology of these blood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deep learning framework called “Adversarial Segmentation and Registration Nets” (ASRNet) for the simultaneous estimation of the blood vessel segmentation and the registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills the blood vessel segmentation task, and (ii) A registration module R that estimates the spatial correspondence of an image pair. Based on the segmention-driven registration network, we train the segmentation network using a semi-supervised adversarial learning strategy. Our experimental results show that the proposed ASRNet can achieve state-of-the-art accuracy in segmentation and registration tasks performed with real MSI datasets.     

基于多尺度2D Gabor小波的视网膜血管自动分割

眼底视网膜血管分割对临床视网膜疾病诊断具有重要意义. 由于视网膜血管结构微小, 血管轮廓边界模糊, 加上图像采集时噪声的影响, 视网膜血管分割非常困难. 本文提出一种视网膜血管自动分割新方法. 首先, 应用对比度受限的自适应直方图均衡法增强视网膜图像;然后, 采用不同尺度的2D Gabor小波对视网膜图像进行变换, 并分别应用形态学重构 (Morphological reconstruction, MR)和区域生长法 (Region growing, RG)对变换后的图像进行分割; 最后, 对以上两种方法分割的视网膜血管和背景像素点重新标记识别, 得到视网膜血管最终分割结果. 通过对DRIVE和STARE数据库视网膜图像的分割实验, 证明了该算法的有效性.     

联合注意力和Transformer的视网膜血管分割网络

视网膜血管分割在许多眼科疾病诊断和治疗方面至关重要。对复杂的视网膜结构及低对比度眼底图像来说,准确地分割视网膜图像的血管特征仍具有挑战性。联合注意力和Transformer的视网膜血管分割网络JAT-Net,通过对编码阶段特征的通道信息和位置信息联合关注增强编码局部细节特征,利用Transformer增强对长距离上下文信息和空间依赖关系建模的能力。在DRIVE和CHASE数据集上进行视网膜血管分割实验,其准确率分别为0.970 6和0.977 4,F1分数分别为0.843 3和0.815 4,在视网膜血管分割方面表现不错。     

融合隐向量对齐和Swin Transformer的OCTA血管分割

目的 光学相干断层扫描血管造影（optical coherence tomography angiography,OCTA）是一种非侵入式的新兴技术,越来越多地应用于视网膜血管成像。与传统眼底彩照相比,OCTA技术能够显示黄斑周围的微血管信息,在视网膜血管成像邻域具有显著优势。临床实践中,医生可以通过OCTA图像观察不同层的血管结构,并通过分析血管结构的变化来判断是否存在相关疾病。大量研究表明,血管结构的任何异常变化通常都意味着存在某种眼科疾病。因此,对OCTA图像中的视网膜血管结构进行自动分割提取,对众多眼部相关疾病量化分析和临床决策具有重大意义。然而,OCTA图像存在视网膜血管结构复杂、图像整体对比度低等问题,给自动分割带来极大挑战。为此,提出了一种新颖的融合隐向量对齐和Swin Transformer的视网膜血管结构的分割方法,能够实现血管结构的精准分割。方法 以ResU-Net为主干网络,通过Swin Transformer编码器获取丰富的血管特征信息。此外,设计了一种基于隐向量的特征对齐损失函数,能够在隐空间层次对网络进行优化,提升分割性能。结果 在3个OCTA图像数据集上的...     

Integrating adaptive neuro-fuzzy inference system and local binary pattern operator for robust retinal blood vessels segmentation

Automatic extraction of blood vessels is an important step in computer-aided diagnosis in ophthalmology. The blood vessels have different widths, orientations, and structures. Therefore, the extracting of the proper feature vector is a critical step especially in the classifier-based vessel segmentation methods. In this paper, a new multi-scale rotation-invariant local binary pattern operator is employed to extract efficient feature vector for different types of vessels in the retinal images. To estimate the vesselness value of each pixel, the obtained multi-scale feature vector is applied to an adaptive neuro-fuzzy inference system. Then by applying proper top-hat transform, thresholding, and length filtering, the thick and thin vessels are highlighted separately. The performance of the proposed method is measured on the publicly available DRIVE and STARE databases. The average accuracy 0.942 along with true positive rate (TPR) 0.752 and false positive rate (FPR) 0.041 is very close to the manual segmentation rates obtained by the second observer. The proposed method is also compared with several state-of-the-art methods. The proposed method shows higher average TPR in the same range of FPR and accuracy.

     

The effect of border noise on the performance of projection-based page segmentation methods

Projection methods have been used in the analysis of bitonal document images for different tasks such as page segmentation and skew correction for more than two decades. However, these algorithms are sensitive to the presence of border noise in document images. Border noise can appear along the page border due to scanning or photocopying. Over the years, several page segmentation algorithms have been proposed in the literature. Some of these algorithms have come into widespread use due to their high accuracy and robustness with respect to border noise. This paper addresses two important questions in this context: 1) Can existing border noise removal algorithms clean up document images to a degree required by projection methods to achieve competitive performance? 2) Can projection methods reach the performance of other state-of-the-art page segmentation algorithms (e.g., Docstrum or Voronoi) for documents where border noise has successfully been removed? We perform extensive experiments on the University of Washington (UW-III) data set with six border noise removal methods. Our results show that although projection methods can achieve the accuracy of other state-of-the-art algorithms on the cleaned document images, existing border noise removal techniques cannot clean up documents captured under a variety of scanning conditions to the degree required to achieve that accuracy.     

Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications

In the last two decades, we have seen an amazing development of image processing techniques targeted for medical applications. We propose multi-GPU-based parallel real-time algorithms for segmentation and shape-based object detection, aiming at accelerating two medical image processing methods: automated blood detection in wireless capsule endoscopy (WCE) images and automated bright lesion detection in retinal fundus images. In the former method we identified segmentation and object detection as being responsible for consuming most of the global processing time. While in the latter, as segmentation was not used, shape-based object detection was the compute-intensive task identified. Experimental results show that the accelerated method running on multi-GPU systems for blood detection in WCE images is on average 265 times faster than the original CPU version and is able to process 344 frames per second. By applying the multi-GPU framework for bright lesion detection in fundus images we are able to process 62 frames per second with a speedup average 667 times faster than the equivalent CPU version.     

Finger vein segmentation in infrared images using supervised and unsupervised clustering algorithms

In this paper, two new methods to segment infrared images of finger in order to perform the finger vein pattern extraction task are presented. In the first, the widespread known and used K nearest neighbor (KNN) classifier, which is a very effective supervised method for clustering data sets, is used. In the second, a novel clustering algorithm named nearest neighbor clustering algorithm (NNCA), which is unsupervised and has been recently proposed for retinal vessel segmentation, is used. As feature vectors for the classification process in both cases two features are used: the multidirectional response of a matched filter and the minimum eigenvalue of the Hessian matrix. The response of the multidirectional filter is essential for robust classification because offers a distinction between vein-like and edge-like structures while Hessian based approaches cannot offer this. The two algorithms, as the experimental results show, perform well with the NNCA has the advantage that is unsupervised and thus can be used for full automatic finger vein pattern extraction. It is also worth to note that the proposed vector, composed only of two features, is the simplest feature set which has proposed in the literature until now and results in a performance comparable with others that use a vector with much larger size (31 features). NNCA evaluated also quantitatively on a database which contains artificial images of finger and achieved the segmentation rates: 0.88 sensitivity, 0.80 specificity and 0.82 accuracy.