Retinal vessel extraction using dynamic multi-scale matched filtering and dynamic threshold processing based on histogram fitting

Automatic extraction of retinal vessels is of great significance in the field of medical diagnosis. Unfortunately, extracting vessels in retinal images with uneven background is a challenging task. In addition, accurate extraction of vessels with different widths is difficult. Aiming at these problems, in this paper, a new dynamic multi-scale filtering method together with a dynamic threshold processing scheme was proposed. The image is first divided into sub-images to facilitate the analysis of gray features. Then for each sub-image, the scales of the matched filter and the segmentation threshold are dynamically determined in accordance with the Gaussian fitting results of the gray distribution. Compared with the current blood vessel extraction algorithms based on multi-scale matched filter using uniform scales for the whole retinal image, the proposed method detects many fine vessels drowned by noise and avoids an overestimation of the thin vessels while improving the accuracy of segmentation in general.     

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。     

DF-Net: Deep fusion network for multi-source vessel segmentation

Accurate retinal vessel segmentation is very challenging. Recently, the deep learning based method has greatly improved performance. However, the non-vascular structures usually harm the performance and some low contrast small vessels are hard to be detected after several down-sampling operations. To solve these problems, we design a deep fusion network (DF-Net) including multiscale fusion, feature fusion and classifier fusion for multi-source vessel image segmentation. The multiscale fusion module allows the network to detect blood vessels with different scales. The feature fusion module fuses deep features with vessel responses extracted from a Frangi filter to obtain a compact yet domain invariant feature representation. The classifier fusion module provides the network more supervision. DF-Net also predicts the parameter of the Frangi filter to avoid manually picking the best parameters. The learned Frangi filter enhances the feature map of the multiscale network and restores the edge information loss caused by down-sampling operations. The proposed end-to-end network is easy to train and the inference time for one image is 41ms on a GPU. The model outperforms state-of-the-art methods and achieves the accuracy of 96.14%, 97.04%, 98.02% from three publicly available fundus image datasets DRIVE, STARE, CHASEDB1, respectively. The code is available at https://github.com/y406539259/DF-Net.     

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.     

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.

     

Maximum likelihood estimation of vessel parameters from scale space analysis

We describe a method of detecting features in retinal images using a model-based approach. The image is processed using a bank of filters in a scale space. A parametric model of the target feature is then proposed and the filter responses to the model calculated. A noise model is proposed, and incorporated into a maximum likelihood estimator to estimate model parameters. The estimator uses the generative parametric model to explore smoothly the scale space. This method is applied to the detection of retinal blood vessels, using a Gaussian-profiled valley as a model. A simple thresholding method is proposed as an example of using the rich estimated parameter maps to detect vessels and the results are compared against two existing vessel detectors. Our system is compared against ground truth and the output of existing systems. It is found to be comparable and, in addition, produces direct estimates of vessel calibres and contrasts. It does not use any form of region growing or vessel tracking, but thresholds a function of the estimated vessel parameters to determine vessel regions.     

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.     

Segmentation of retinal blood vessels using the radial projection and semi-supervised approach

Automatic segmentation of retinal blood vessels has become a necessary diagnostic procedure in ophthalmology. The blood vessels consist of two types of vessels, i.e., thin vessels and wide vessels. Therefore, a segmentation method may require two different processes to treat different vessels. However, traditional segmentation algorithms hardly draw a distinction between thin and wide vessels, but deal with them together. The major problems of these methods are as follows: (1) If more emphasis is placed on the extraction of thin vessels, the wide vessels tend to be over detected; and more artificial vessels are generated, too. (2) If more attention is paid on the wide vessels, the thin and low contrast vessels are likely to be missing. To overcome these problems, a novel scheme of extracting the retinal vessels based on the radial projection and semi-supervised method is presented in this paper. The radial projection method is used to locate the vessel centerlines which include the low-contrast and narrow vessels. Further, we modify the steerable complex wavelet to provide better capability of enhancing vessels under different scales, and construct the vector feature to represent the vessel pixel by line strength. Then, semi-supervised self-training is used for extraction of the major structures of vessels. The final segmentation is obtained by the union of the two types of vessels. Our approach is tested on two publicly available databases. Experiment results show that the method can achieve improved detection of thin vessels and decrease false detection of vessels in pathological regions compared to rival solutions.     

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.     

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。     

一种视网膜血管自适应提取方法

为了快速有效地提取视网膜血管，根据视网膜图像的灰度分布特征，提出了一种新的基于自适应阈值化的血管提取方法。该方法是首先把图像划分成很多同样尺寸的小子图像，然后在每个子图像中分别计算局部阈值，并用该阈值分割该子图像。因为视网膜图像中血管和背景在局部范围内都比较均匀，所以在每个子图像中都存在一个局部阈值能够将其中的血管分割出来。采用的局部阈值计算方法不仅允许子图像可以取得很小，而且能够保证得到平方误差最小意义下的最优阈值。在阈值计算过程中，还用到一种基于过零点边缘检测技术的边缘追踪算法。最后还提出一种基于区域生长的特征综合方法，即通过综合两次阈值化分割得到的血管结构来清除碎片。多幅视网膜图像的实验证明，该方法的计算速度很快，并且可以提取包括细血管在内的绝大部分血管。     

基于不同尺度增强融合的视网膜血管分割算法

针对现有视网膜血管图像提取细小血管准确率较低的问题,提出了一种基于多尺度线性检测器与局部和全局增强相结合的视网膜血管分割方法.对多尺度线检测器进行研究,将其分为小尺度和大尺度两部分;利用小尺度对局部增强后的图像与大尺度对全局增强后的图像分别进行检测,得到不同尺度下的响应函数;将不同尺度下的响应函数进行融合,得到最终的视网膜血管结构.在STARE和DRIVE两个数据库上进行实验,结果表明:该算法得到的平均血管准确率分别达到96.62％和96.45％,平均真阳性率分别达到75.52％和83.07％,分割准确率高,能够得到较好的血管分割结果.     

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.     

Local feature extraction for iris recognition with automatic scale selection

This paper presents an iris recognition system using automatic scale selection algorithm for iris feature extraction. The proposed system first filters the given iris image adopting a bank of Laplacian of Gaussian (LoG) filters with many different scales and computes the normalized response of every filter. The parameter γ used to normalize the filter responses, is derived by analyzing the scale-space maxima of the blob feature detector responses. Then the maxima normalized response over scales for each point are selected together as the optimal filter outputs of the given iris image and the binary codes for iris feature representation are achieved by encoding these optimal outputs through a zero threshold. Comparison experiment results clearly demonstrate an efficient performance of the proposed algorithm.     

基于核模糊C均值的眼底视网膜血管分割算法

针对眼底视网膜图像对比度差、背景不一致的问题,提出了一种基于核模糊C均值的眼底视网膜血管分割算法。首先采用二维高斯匹配滤波预处理以增强血管,然后采用核模糊C均值算法对增强眼底图像进行分割,并根据血管与各类隶属度的关系自动合并聚类图像得到最终的血管图像。实验结果表明,该算法分割结果令人满意。     

High-resolution SAR images segmentation using NSCT denoising and QIGA based parameters selection of PCNN model

The high-resolution synthetic aperture radar (SAR) images usually contain inhomogeneous coherent speckle noises. For the high-resolution SAR image segmentation with such noises, the conventional methods based on pulse coupled neural networks (PCNN) have to face heavy parameters with a low efficiency. In order to solve the problems, this paper proposes a novel SAR image segmentation algorithm based on non-subsampling Contourlet transform (NSCT) denoising and quantum immune genetic algorithm (QIGA) improved PCNN models. The proposed method first denoising the SAR images for a pre-processing based on NSCT. Then, by using the QIGA to select parameters for the PCNN models, such models self-adaptively select the suitable parameters for segmentation of SAR images with different scenes. This method decreases the number of parameters in the PCNN models and improves the efficiency of PCNN models. At last, by using the optimal threshold to binary the segmented SAR images, the small objects and large scales from the original SAR images will be segmented. To validate the feasibility and effectiveness of the proposed algorithm, four different comparable experiments are applied to validate the proposed algorithm. Experimental results have shown that NSCT pre-processing has a better performance for coherent speckle noises suppression, and QIGA-PCNN model based on denoised SAR images has an obvious segmentation performance improvement on region consistency and region contrast than state-of-the-arts methods. Besides, the segmentation efficiency is also improved than conventional PCNN model, and the level of time complexity meets the state-of-the-arts methods. Our proposed NSCT+QIGA-PCNN model can be used for small object segmentation and large scale segmentation in high-resolution SAR images. The segmented results will be further used for object classification and recognition, regions of interest extraction, and moving object detection and tracking.

     

An improved vessel extraction scheme from retinal fundus images

Vessel extraction from retinal fundus images is essential for the diagnosis of different opthalmologic diseases like glaucoma, diabetic retinopathy and hypertension. It is a challenging task due to presence of several noises embedded with thin vessels. In this article, we have proposed an improved vessel extraction scheme from retinal fundus images. First, mathematical morphological operation is performed on each planes of the RGB image to remove the vessels for obtaining noise in the image. Next, the original RGB and vessel removed RGB image are transformed into negative gray scale image. These negative gray scale images are subtracted and finally binarized (BW₁) by leveling the image. It still contains some granular noise which is removed based on the area of connected component. Further, previously detected vessels are replaced in the gray-scale image with mean value of the gray-scale image and then the gray-scale image is enhanced to obtain the thin vessels. Next, the enhanced image is binarized and thin vessels are obtained (BW₂). Finally, the thin vessel image (BW₂) is merged with the previously obtained binary image (BW₁) and finally we obtain the vessel extracted image. To analyze the performance of our proposed method we have experimented on publicly available DRIVE dataset. We have observed that our algorithm have provides satisfactory performance with the sensitivity, specificity and accuracy of 0.7260, 0.9802 and 0.9563 respectively which is better than the most of the recent works.

     

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.     

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.