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0.9889,0.9812和0.9831。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。     

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.     

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.

     

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。     

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.     

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...     

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.     

Examining the variation of vascular structure in digital fundus images using textural pattern

One of the most significant retinal abnormality in which an individual loses the vision is diabetic retinopathy (DR). The appropriate way to treat this disease would be easier if it is detected at an earlier stage. The study on the vasculature extracted from illumination correction on the fundus image brings the presence of diabetic retinopathy. This preprocessing involves three steps. Initially illumination and reflectance estimation is done and then illumination correction is employed and finally the clipped histogram equalization is done to preserve the brightness of the image so that the information on the retinal image may not get saturated. Here, k-means segmentation process has been done and the local binary pattern (LBP) has been calculated. The selected feature vectors are then classified by using an echo state neural network (ESNN). The proposed method has been tested on publically available database DIARETDB1 that contained 89 DR fundus images in total. The result of detecting and classifying the pathology based on vasculature study on these images yielded sensitivity of 86.46%, specificity of 80.47%, and accuracy of 96.92%.     

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PST和多尺度高斯滤波的视网膜血管的分割

视网膜血管分割是眼科计算机辅助诊断和大规模眼科疾病筛查系统的基础。为辅助眼科医生进行眼底疾病的诊断，文中提出了一种基于相位拉伸变换(PST)和多尺度高斯滤波的视网膜血管分割方法。首先，将彩色眼底影像的绿色通道分量图进行增强预处理；然后采用不同尺度的高斯滤波器对预处理增强后的视网膜血管进行降噪处理，再结合PST边缘检测算法初步获得视网膜血管分割图；最后整合初步获得的视网膜血管分割图并进行形态学去噪，获得最终的视网膜血管分割图。通过在视网膜图像库DRIVE上进行实验，其平均准确率为93%，平均灵敏度达77%，平均特异性为95%，该实验结果验证了文中方法的有效性。     

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.     

Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is neovascularisation, the growth of abnormal new vessels. This paper describes an automated method for the detection of new vessels in retinal images. Two vessel segmentation approaches are applied, using the standard line operator and a novel modified line operator. The latter is designed to reduce false responses to non-vessel edges. Both generated binary vessel maps hold vital information which must be processed separately. This is achieved with a dual classification system. Local morphology features are measured from each binary vessel map to produce two separate feature sets. Independent classification is performed for each feature set using a support vector machine (SVM) classifier. The system then combines these individual classification outcomes to produce a final decision. Sensitivity and specificity results using a dataset of 60 images are 0.862 and 0.944 respectively on a per patch basis and 1.00 and 0.90 respectively on a per image basis.     

Retinal vessels segmentation based on level set and region growing

Retinal vessels play an important role in the diagnostic procedure of retinopathy. Accurate segmentation of retinal vessels is crucial for pathological analysis. In this paper, we propose a new retinal vessel segmentation method based on level set and region growing. Firstly, a retinal vessel image is preprocessed by the contrast-limited adaptive histogram equalization and a 2D Gabor wavelet to enhance the vessels. Then, an anisotropic diffusion filter is used to smooth the image and preserve vessel boundaries. Finally, the region growing method and a region-based active contour model with level set implementation are applied to extract retinal vessels, and their results are combined to achieve the final segmentation. Comparisons are conducted on the publicly available DRIVE and STARE databases using three different measurements. Experimental results show that the proposed method reaches an average accuracy of 94.77% on the DRIVE database and 95.09% on the STARE database.     

基于多尺度高阶注意力机制的视网膜血管分割

视网膜血管分割对于辅助医生诊断糖尿病性视网膜病变、黄斑萎缩、青光眼等眼科疾病具有重要意义.注意力机制被广泛用于U-Net及其变体中以提高血管分割模型的性能.为进一步提高视网膜血管的分割精度,挖掘视网膜图像中的高阶及全局上下文信息,本文提出基于多尺度高阶注意力机制的模型(multi-scale high-order attention network, MHA-Net).首先,多尺度高阶注意力(multi-scale high-order attention, MHA)模块从深层特征图中提取多尺度和全局特征计算初始化注意力图,从而改进模型处理医学图像分割时尺度不变的缺陷.接下来,该模块通过图的传递闭包构建注意力图,进而提取高阶的深层特征.通过将多尺度高阶注意力模块应用于编码器-解码器结构中,在彩色眼底图像数据集DRIVE上进行血管分割,实验结果表明,基于多尺度高阶注意力机制的视网膜血管分割方法有效地提高了分割的精度.     

糖尿病性视网膜图像的深度学习分类方法

目的 糖尿病性视网膜病变（DR）是目前比较严重的一种致盲眼病,因此,对糖尿病性视网膜病理图像的自动分类具有重要的临床应用价值。基于人工分类视网膜图像的方法存在判别性特征提取困难、分类性能差、耗时费力且很难得到客观统一的医疗诊断等问题,为此,提出一种基于卷积神经网络和分类器的视网膜病理图像自动分类系统。方法 首先,结合现有的视网膜图像的特点,对图像进行去噪、数据扩增、归一化等预处理操作;其次,在AlexNet网络的基础上,在网络的每一个卷积层和全连接层前引入一个批归一化层,得到一个网络层次更复杂的深度卷积神经网络BNnet。BNnet网络用于视网膜图像的特征提取网络,对其训练时采用迁移学习的策略利用ILSVRC2012数据集对BNnet网络进行预训练,再将训练得到的模型迁移到视网膜图像上再学习,提取用于视网膜分类的深度特征;最后,将提取的特征输入一个由全连接层组成的深度分类器将视网膜图像分为正常的视网膜图像、轻微病变的视网膜图像、中度病变的视网膜图像等5类。结果 实验结果表明,本文方法的分类准确率可达0.93,优于传统的直接训练方法,且具有较好的鲁棒性和泛化性。结论 本文提出的视网膜病理图像分类框架有效地避免了人工特征提取和图像分类的局限性,同时也解决了样本数据不足而导致的过拟合问题。     

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.     

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.     

基于残差与小波U-Net的视网膜图像分割

视网膜血管分割是医学图像分割中常见的一项任务, 视网膜血管图像有着分割目标小而多的特点, 过去的网络在分割中可以较好地提取粗血管, 但是很容易忽略细血管, 而这部分细血管的提取在一定程度上影响网络的性能, 甚至是诊断的结果. 因此, 为了达到在保证准确提取粗血管的前提下, 提取到更多更连续的细血管的目标, 本文使用对称编解码网络作为基础网络, 使用一种新的卷积模块DR-Conv, 旨在防止过拟合的同时提高网络的学习能力. 同时, 针对最大池化层造成的信息损失问题, 考虑使用小波变换进行图像分解并使用逆小波变换对图像进行恢复, 利用混合损失函数结合不同损失函数的特性以弥补单个损失函数优化能力不足的问题. 为了评估网络的性能, 在3个公共视网膜血管数据集上分别对网络进行了测试, 并与最新方法进行了比较, 实验结果表明本文网络拥有更优的性能.     

Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning

Diseases of the eye require manual segmentation and examination of the optic disc by ophthalmologists. Though, image segmentation using deep learning techniques is achieving remarkable results, it leverages on large-scale labeled datasets. But, in the field of medical imaging, it is challenging to acquire large labeled datasets. Hence, this article proposes a novel deep learning model to automatically segment the optic disc in retinal fundus images by using the concepts of semi-supervised learning and transfer learning. Initially, a convolutional autoencoder (CAE) is trained to automatically learn features from a large number of unlabeled fundus images available from the Kaggle’s diabetic retinopathy (DR) dataset. The autoencoder (AE) learns the features from the unlabeled images by reconstructing the input images and becomes a pre-trained network (model). After this, the pre-trained autoencoder network is converted into a segmentation network. Later, using transfer learning, the segmentation network is trained with retinal fundus images along with their corresponding optic disc ground truth images from the DRISHTI GS1 and RIM-ONE datasets. The trained segmentation network is then tested on retinal fundus images from the test set of DRISHTI GS1 and RIM-ONE datasets. The experimental results show that the proposed method performs on par with the state-of-the-art methods achieving a 0.967 and 0.902 dice score coefficient on the test set of the DRISHTI GS1 and RIM-ONE datasets respectively. The proposed method also shows that transfer learning and semi-supervised learning overcomes the barrier imposed by the large labeled dataset. The proposed segmentation model can be used in automatic retinal image processing systems for diagnosing diseases of the eye.

     

An Image-Processing Strategy for the Segmentation and Quantification of Microaneurysms in Fluorescein Angiograms of the Ocular Fundus

Digital image-processing techniques can provide an objective and highly repeatable way of quantifying retinal pathology. This study describes an image-processing strategy which detects and quantifies microaneurysms present in digitized fluorescein angiograms. After preprocessing stages, a bilinear top-hat transformation and matched filtering are employed to provide an initial segmentation of the images. Thresholding this processed image results in a binary image containing candidate microaneurysms. A novel region-growing algorithm fully delineates each marked object and subsequent analysis of the size, shape, and energy characteristics of each candidate results in the final segmentation of microaneurysms. The technique is assessed by comparing the computer's results with microaneurysm counts carried out by five clinicians, using Receiver Operating Characteristic (ROC) curves. The performance of the automated technique matched that of the clinicians' analyses. This strategy is valuable in providing a way of accurately monitoring the progression of diabetic retinopathy.