Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at nonvascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matched-filter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a six-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements, both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an efficient and effective vessel centerline extraction algorithm.     

Extraction of line properties based on direction fields

The authors present a new set of algorithms for segmenting lines, mainly blood vessels in X-ray images, and extracting properties such as their intensities, diameters, and center lines. The authors developed a tracking algorithm that checks rules taking the properties of vessels into account. The tools even detect veins, arteries, or catheters of two pixels in diameter and with poor contrast. Compared with other algorithms, such as the Canny line detector or anisotropic diffusion, the authors extract a smoother and connected vessel tree without artifacts in the image background. As the tools depend on common intermediate results, they are very fast when used together. The authors' results will support the 3-D reconstruction of the vessel tree from stereoscopic projections. Moreover, the authors make use of their line intensity measure for enhancing and improving the visibility of vessels in 3-D X-ray images. The processed images are intended to support radiologists in diagnosis, radiation therapy planning, and surgical planning. Radiologists verified the improved quality of the processed images and the enhanced visibility of relevant details, particularly fine blood vessels.     

Cerebral artery-vein separation using 0.1-Hz oscillation in dual-wavelength optical imaging

We present a novel artery-vein separation method using 0.1-Hz oscillation at two wavelengths with optical imaging of intrinsic signals (OIS). The 0.1-Hz oscillation at a green light wavelength of 546 nm exhibits greater amplitude in arteries than in veins and is primarily caused by vasomotion, whereas the 0.1-Hz oscillation at a red light wavelength of 630 nm exhibits greater amplitude in veins than in arteries and is primarily caused by changes of deoxyhemoglobin concentration. This spectral feature enables cortical arteries and veins to be segmented independently. The arteries can be segmented on the 0.1-Hz amplitude image at 546 nm using matched filters of a modified dual Gaussian model combining with a single Gaussian model. The veins are a combination of vessels segmented on both amplitude images at the two wavelengths using multiscale matched filters of single Gaussian model. Our method can separate most of the thin arteries and veins from each other, especially the thin arteries with low contrast in raw gray images. In vivo OIS experiments demonstrate the separation ability of the 0.1-Hz based segmentation method in cerebral cortex of eight rats. Two validation studies were undertaken to evaluate the performance of the method by quantifying the arterial and venous length based on a reference standard. The results indicate that our 0.1-Hz method is very effective in separating both large and thin arteries and veins regardless of vessel crossover or overlapping to great extent in comparison with previous methods.     

基于Hesse矩阵和多尺度分析的视网膜动静脉血管管径测量方法

许多全身性疾病会引起视网膜血管管径及动静脉血管比例(Arteriolar-to-Venular diameter Ratios, AVR)的变化,因此对视网膜血管管径进行准确的量化分析对病情诊断具有重要的意义。该文提出一种视网膜动静脉血管管径及AVR的自动测量方法。首先,在分割血管网络的基础上,依据Hesse矩阵检测线状结构的优势,结合多尺度分析准确定位血管方向并计算血管管径;然后利用广义回归神经网络(General Regression Neural Network, GRNN)分类器对动静脉血管骨架线上的点进行准确分类;最后计算感兴趣区域(Region Of Interest, ROI)内的AVR。对REVIEW和DRIVE数据库进行实验,验证了该文方法的有效性。     

Automatic identification of retinal arteries and veins from dual-wavelength images using structural and functional features

This paper presents an automated method to identify arteries and veins in dual-wavelength retinal fundus images recorded at 570 and 600 nm. Dual-wavelength imaging provides both structural and functional features that can be exploited for identification. The processing begins with automated tracing of the vessels from the 570-nm image. The 600-nm image is registered to this image, and structural and functional features are computed for each vessel segment. We use the relative strength of the vessel central reflex as the structural feature. The central reflex phenomenon, caused by light reflection from vessel surfaces that are parallel to the incident light, is especially pronounced at longer wavelengths for arteries compared to veins. We use a dual-Gaussian to model the cross-sectional intensity profile of vessels. The model parameters are estimated using a robust -estimator, and the relative strength of the central reflex is computed from these parameters. The functional feature exploits the fact that arterial blood is more oxygenated relative to that in veins. This motivates use of the ratio of the vessel optical densities (ODs) from images at oxygen-sensitive and oxygen-insensitive wavelengths () as a functional indicator. Finally, the structural and functional features are combined in a classifier to identify the type of the vessel. We experimented with four different classifiers and the best result was given by a support vector machine (SVM) classifier. With the SVM classifier, the proposed algorithm achieved true positive rates of 97% for the arteries and 90% for the veins, when applied to a set of 251 vessel segments obtained from 25 dual wavelength images. The ability to identify the vessel type is useful in applications such as automated retinal vessel oximetry and automated analysis of vascular changes without manual intervention.     

Detection of optic disc in retinal images by means of a geometrical model of vessel structure

We present here a new method to identify the position of the optic disc (OD) in retinal fundus images. The method is based on the preliminary detection of the main retinal vessels. All retinal vessels originate from the OD and their path follows a similar directional pattern (parabolic course) in all images. To describe the general direction of retinal vessels at any given position in the image, a geometrical parametric model was proposed, where two of the model parameters are the coordinates of the OD center. Using as experimental data samples of vessel centerline points and corresponding vessel directions, provided by any vessel identification procedure, model parameters were identified by means of a simulated annealing optimization technique. These estimated values provide the coordinates of the center of OD. A Matlab prototype implementing this method was developed. An evaluation of the proposed procedure was performed using the set of 81 images from the STARE project, containing images from both normal and pathological subjects. The OD position was correctly identified in 79 out of 81 images (98%), even in rather difficult pathological situations.     

Automatic grading of retinal vessel caliber

New clinical studies suggest that narrowing of the retinal blood vessels may be an early indicator of cardiovascular diseases. One measure to quantify the severity of retinal arteriolar narrowing is the arteriolar-to-venular diameter ratio (AVR). The manual computation of AVR is a tedious process involving repeated measurements of the diameters of all arterioles and venules in the retinal images by human graders. Consistency and reproducibility are concerns. To facilitate large-scale clinical use in the general population, it is essential to have a precise, efficient and automatic system to compute this AVR. This paper describes a new approach to obtain AVR. The starting points of vessels are detected using a matched Gaussian filter. The detected vessels are traced with the help of a combined Kalman filter and Gaussian filter. A modified Gaussian model that takes into account the central light reflection of arterioles is proposed to describe the vessel profile. The width of a vessel is obtained by data fitting. Experimental results indicate a 97.1% success rate in the identification of vessel starting points, and a 99.2% success rate in the tracking of retinal vessels. The accuracy of the AVR computation is well within the acceptable range of deviation among the human graders, with a mean relative AVR error of 4.4%. The system has interested clinical research groups worldwide and will be tested in clinical studies.     

Robust shape regression for supervised vessel segmentation and its application to coronary segmentation in CTA

This paper presents a vessel segmentation method which learns the geometry and appearance of vessels in medical images from annotated data and uses this knowledge to segment vessels in unseen images. Vessels are segmented in a coarse-to-fine fashion. First, the vessel boundaries are estimated with multivariate linear regression using image intensities sampled in a region of interest around an initialization curve. Subsequently, the position of the vessel boundary is refined with a robust nonlinear regression technique using intensity profiles sampled across the boundary of the rough segmentation and using information about plausible cross-sectional vessel shapes. The method was evaluated by quantitatively comparing segmentation results to manual annotations of 229 coronary arteries. On average the difference between the automatically obtained segmentations and manual contours was smaller than the inter-observer variability, which is an indicator that the method outperforms manual annotation. The method was also evaluated by using it for centerline refinement on 24 publicly available datasets of the Rotterdam Coronary Artery Evaluation Framework. Centerlines are extracted with an existing method and refined with the proposed method. This combination is currently ranked second out of 10 evaluated interactive centerline extraction methods. An additional qualitative expert evaluation in which 250 automatic segmentations were compared to manual segmentations showed that the automatically obtained contours were rated on average better than manual contours.     

Three-dimensional motion tracking of coronary arteries in biplane cineangiograms

A three-dimensional (3-D) method for tracking the coronary arteries through a temporal sequence of biplane X-ray angiography images is presented. A 3-D centerline model of the coronary vasculature is reconstructed from a biplane image pair at one time frame, and its motion is tracked using a coarse-to-fine hierarchy of motion models. Three-dimensional constraints on the length of the arteries and on the spatial regularity of the motion field are used to overcome limitations of classical two-dimensional vessel tracking methods, such as tracking vessels through projective occlusions. This algorithm was clinically validated in five patients by tracking the motion of the left coronary tree over one cardiac cycle. The root mean square reprojection errors were found to be submillimeter in 93% (54/58) of the image pairs. The performance of the tracking algorithm was quantified in three dimensions using a deforming vascular phantom. RMS 3-D distance errors were computed between centerline models tracked in the X-ray images and gold-standard centerline models of the phantom generated from a gated 3-D magnetic resonance image acquisition. The mean error was 0.69 (+/- 0.06) mm over eight temporal phases and four different biplane orientations.     

Enhancement of blood vessels in retinal imaging using the nonsubsampled contourlet transform

This paper presents an enhancement method for blood vessels in retinal images based on the nonsubsampled contourlet transform (NSCT). The NSCT is a shift-invariant version of the contourlet transform built upon the nonsubsampled pyramid filter banks and the nonsubsampled directional filter banks. The proposed method uses the NSCT to decompose the input retinal image into eight directions from coarser to finer scales, and then analyzes and classifies the image pixels into three categories: vessel, uncertainty, and non-vessel pixels, according to the NSCT coefficients. Then, we modify the NSCT coefficients according to the class of each pixel using a nonlinear mapping function, and reconstruct the enhanced image from the modified NSCT coefficients. The experimental results show that the proposed method can obviously increase the contrast of retinal vessels and thus outperform other enhancement methods.     

病变视网膜图像血管网络的自动分割

现有的视网膜血管分割方法大多只针对正常的视网膜图像进行分割,不能实现对发生病变的视网膜图像的分割.为此,提出了一种新的病变视网膜图像血管网络分割方法.该方法首先采用向量场散度方法获得病变视网膜图像中大部分血管的中心线,然后计算出中心线上各像素点的方向信息并采用改进的定向局部对比度方法检测出中心线两侧的血管像素,最后对获得的血管段末端进行反向外推追踪,分割出最终的血管网络.通过对通用的STARE眼底图像库中所有病变视网膜图像的实验仿真,结果表明本文算法获得了0.9426的ROC曲线面积和0.9502的准确率,算法性能明显优于Hoover算法和Benson等提出的算法.此外,本文算法还克服了Benson算法的局限性,对不同类型的病变视网膜图像都具有较好的鲁棒性.     

Multi-feature Based Ensemble Classification and Regression Tree (ECART) for Target Tracking in Infrared Imagery

This paper considers target tracking as a binary classification problem to label pixels as either belonging to the target or the background. We present a novel robust algorithm, the multi-feature based ensemble classification and regression tree (ECART), for target tracking in infrared imagery (IR). In the first frame, a region of interest (ROI) containing target and background is initialized manually. Based on the multiple features of pixels, the ECART is trained online to distinguish between the target and the background. In the subsequent frames, the position and size of the ROI are predicted by the position and size of the target in the previous frame, respectively. Then, the ECART is used to label pixels within the predicted ROI, giving the label map. The new position and size of the target are finally found in the label map. Experimental results indicate that the proposed algorithm is effective and robust.     

A novel method for the automatic grading of retinal vessel tortuosity

Tortuosity is among the first alterations in the retinal vessel network to appear in many retinopathies, such as those due to hypertension. An automatic evaluation of retinal vessel tortuosity would help the early detection of such retinopathies. Quite a few techniques for tortuosity measurement and classification have been proposed, but they do not always match the clinical concept of tortuosity. This justifies the need for a new definition, able to express in mathematical terms the tortuosity as perceived by ophthalmologists. We propose here a new algorithm for the evaluation of tortuosity in vessels recognized in digital fundus images. It is based on partitioning each vessel in segments of constant-sign curvature and then combining together each evaluation of such segments and their number. The algorithm has been compared with other available tortuosity measures on a set of 30 arteries and one of 30 veins from 60 different images. These vessels had been preliminarily ordered by a retina specialist by increasing perceived tortuosity. The proposed algorithm proved to be the best one in matching the clinically perceived vessel tortuosity.     

Contrast-to-gradient method for the evaluation of image resolution in scanning electron microscopy

In a previous study, we proposed the contrast-to-gradient (CG) method for evaluating image resolution. Here, the CG resolution is defined as a weighted harmonic mean of the local resolution, which is proportional to the quotient of the threshold contrast divided by the local gradient. The local gradient is calculated from the quadratic function that best fits the local pixel intensities over the region of interest (ROI) of 3 x 3 or 5 x 5 pixels in size. To refine the CG method, some modifications are carried out in the present study. Directional resolutions are employed to evaluate images, including astigmatism or strongly directional patterns as well as isotropic patterns. Here, CG resolution is redefined so as to keep the same value even for the image reversed in black-and-white contrast, because of no difference in the image information during contrast reversing. Besides, CG resolution is characterized to be independent of the brightness/contrast change unless these changes do not bring about both cut-off and saturation in the pixel intensities. Dependencies of the denoising effect and the resolution accuracy on ROI size are demonstrated as a function of image-noise.     

基于LVE和ARG算法的冠状动脉分割

为克服传统区域生长方法中容易发生的欠分割和过分割现象,引入局部图像分析技术,设定一系列感兴趣区域(ROI),对冠状动脉的多层螺旋CT(MSCT)图像进行分割。首先应用基于Hessian矩阵的局部血管增强(LVE)滤波,提升图像的对比度;随后采用自适应性区域生长(ARG)算法,并对阈值适时调整。分割后的局部图像经过全局融合得到整体冠脉树。算法综合了图像的局部形状信息和灰度信息,确保了分割结果的准确性和完整性。实验结果表明,算法对左前降支(LAD)、左回旋支(LCX)、对角支(Diag)及右冠状动脉(RCA)均有较好的分割效果。     

Efficient decision based algorithm for the removal of high density salt and pepper noise in images

In this paper, an efficient decision based scheme is proposed for the restoration of grayscale and colour images that are heavily corrupted by salt and pepper noise. The processed pixel is examined for 0 or 255; if found true, then it is considered as noisy pixel else not noisy. If found noisy the four neighbours of the noisy pixels are checked for 0 or 255. If all the four neighbours of the corrupted pixel are noisy, the mean of the four neighbours replaces the corrupted pixel. If any of the four neighbours is a non-noisy pixel, calculate the number of corrupted pixels in the current processing window. If the count is less than three then the noisy pixel is replaced by an unsymmetrical trimmed median. If the current window has more than three noisy pixels, then unsymmetrical trimmed mean replaces the corrupted pixels. If all the pixels of the current processing window are noisy then instead of unsymmetrical trimmed mean, global mean of the image is replaced as output. The uncorrupted pixel is left unchanged. The proposed algorithm is tested on various grayscale and colour images and found that it gives excellent PSNR, high IEF and lowest MSE. Also it consumes average time with excellent edge preservation even at higher noise densities. The quality of the results of proposed algorithm is superior when compared to the various state of the art methods.     

3-D quantitative vascular shape analysis for arterial bifurcations via dynamic tube fitting

Reliable and reproducible estimation of vessel centerlines and reference surfaces is an important step for the assessment of luminal lesions. Conventional methods are commonly developed for quantitative analysis of the "straight" vessel segments and have limitations in defining the precise location of the centerline and the reference lumen surface for both the main vessel and the side branches in the vicinity of bifurcations. To address this, we propose the estimation of the centerline and the reference surface through the registration of an elliptical cross-sectional tube to the desired constituent vessel in each major bifurcation of the arterial tree. The proposed method works directly on the mesh domain, thus alleviating the need for image upsampling, usually required in conventional volume domain approaches. We demonstrate the efficiency and accuracy of the method on both synthetic images and coronary CT angiograms. Experimental results show that the new method is capable of estimating vessel centerlines and reference surfaces with a high degree of agreement to those obtained through manual delineation. The centerline errors are reduced by an average of 62.3% in the regions of the bifurcations, when compared to the results of the initial solution obtained through the use of mesh contraction method.     

Measurement of retinal vessel widths from fundus images based on 2-D modeling

Changes in retinal vessel diameter are an important sign of diseases such as hypertension, arteriosclerosis and diabetes mellitus. Obtaining precise measurements of vascular widths is a critical and demanding process in automated retinal image analysis as the typical vessel is only a few pixels wide. This paper presents an algorithm to measure the vessel diameter to subpixel accuracy. The diameter measurement is based on a two-dimensional difference of Gaussian model, which is optimized to fit a two-dimensional intensity vessel segment. The performance of the method is evaluated against Brinchmann-Hansen's half height, Gregson's rectangular profile and Zhou's Gaussian model. Results from 100 sample profiles show that the presented algorithm is over 30% more precise than the compared techniques and is accurate to a third of a pixel.     

通用数字图像加密与抗剪切攻击恢复算法

为对数字图像进行有效地保护,提出一种以混沌系统及其混沌序列为基础的通用加密与解密算法。首先,根据密钥产生一个混沌序列,经排序后生成相应的下标序列,并据此进行像素坐标置乱加密。然后,根据子密钥与图像类型值由混沌序列生成相应的无符号整数序列,并按顺序与对应的像素值进行异或运算以实现像素值置换加密。针对恶意剪切攻击,同时提出一种基于邻域相邻像素特性的抗剪切攻击恢复算法。实验结果与理论分析表明,该算法加密效果好,密钥空间大,安全性与通用性强,且具有较为理想的抗统计分析攻击与抗剪切攻击能力。     

Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction

This paper presents an automated method for the segmentation of the vascular network in retinal images. The algorithm starts with the extraction of vessel centerlines, which are used as guidelines for the subsequent vessel filling phase. For this purpose, the outputs of four directional differential operators are processed in order to select connected sets of candidate points to be further classified as centerline pixels using vessel derived features. The final segmentation is obtained using an iterative region growing method that integrates the contents of several binary images resulting from vessel width dependent morphological filters. Our approach was tested on two publicly available databases and its results are compared with recently published methods. The results demonstrate that our algorithm outperforms other solutions and approximates the average accuracy of a human observer without a significant degradation of sensitivity and specificity.