Contextual information enhanced convolutional neural networks for retinal vessel segmentation in color fundus images

Accurate retinal vessel segmentation is a challenging problem in color fundus image analysis. An automatic retinal vessel segmentation system can effectively facilitate clinical diagnosis and ophthalmological research. In general, this problem suffers from various degrees of vessel thickness, perception of details, and contextual feature fusion in technique. For addressing these challenges, a deep learning based method has been proposed and several customized modules have been integrated into the well-known U-net with encoder–decoder architecture, which is widely employed in medical image segmentation. In the network structure, cascaded dilated convolutional modules have been integrated into the intermediate layers, for obtaining larger receptive field and generating denser encoded feature maps. Also, the advantages of the pyramid module with spatial continuity have been taken for multi-thickness perception, detail refinement, and contextual feature fusion. Additionally, the effectiveness of different normalization approaches has been discussed on different datasets with specific properties. Finally, sufficient comparative experiments have been enforced on three retinal vessel segmentation datasets, DRIVE, CHASE_DB1, and the STARE dataset with unhealthy samples. As a result, the proposed method outperforms the work of predecessors and achieves state-of-the-art performance.     

Optimal scheduling of tracing computations for real-time vascularlandmark extraction from retinal fundus images

This group published fast algorithms for automatic tracing (vectorization) of the vasculature in live retinal angiograms, and for the extraction of visual landmarks formed by vascular bifurcations and crossings. These landmarks are used for feature-based image matching for controlling a computer-assisted laser retinal surgery instrument under development. This paper describes methods to schedule the vascular tracing computations to maximize the rate of growth of quality of the partial tracing results within a frame cycle. There are two main advantages. First, progressive image matching from partially extracted landmark sets can be faster, and provide an earlier indication of matching failure. Second, the likelihood of successful image matching is greatly improved since the extracted landmarks are of the highest quality for the given computational budget. The scheduling method is based on quantitative measures for the computational work and the quality of landmarks. A coarse grid-based analysis of the image is used to generate seed points for the tracing computations, along with estimates of local edge strengths, orientations, and vessel thickness. These estimates are used to define criteria for real-time preemptive scheduling of the tracing computations     

Textureless macula swelling detection with multiple retinal fundus images

Retinal fundus images acquired with nonmydriatic digital fundus cameras are versatile tools for the diagnosis of various retinal diseases. Because of the ease of use of newer camera models and their relatively low cost, these cameras can be employed by operators with limited training for telemedicine or point-of-care (PoC) applications. We propose a novel technique that uses uncalibrated multiple-view fundus images to analyze the swelling of the macula. This innovation enables the detection and quantitative measurement of swollen areas by remote ophthalmologists. This capability is not available with a single image and prone to error with stereo fundus cameras. We also present automatic algorithms to measure features from the reconstructed image, which are useful in PoC automated diagnosis of early macular edema, e.g., before the appearance of exudation. The technique presented is divided into three parts: first, a preprocessing technique simultaneously enhances the dark microstructures of the macula and equalizes the image; second, all available views are registered using nonmorphological sparse features; finally, a dense pyramidal optical flow is calculated for all the images and statistically combined to build a naive height map of the macula. Results are presented on three sets of synthetic images and two sets of real-world images. These preliminary tests show the ability to infer a minimum swelling of 300 μm and to correlate the reconstruction with the swollen location.     

Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms

Algorithms are presented for rapid, automatic, robust, adaptive, and accurate tracing of retinal vasculature and analysis of intersections and crossovers. This method improves upon prior work in several ways: automatic adaptation from frame to frame without manual initialization/adjustment, with few tunable parameters; robust operation on image sequences exhibiting natural variability, poor and varying imaging conditions, including over/under-exposure, low contrast, and artifacts such as glare; does not require the vasculature to be connected, so it can handle partial views; and operation is efficient enough for use on unspecialized hardware, and amenable to deadline-driven computing, being able to produce a rapidly and monotonically improving sequence of usable partial results. Increased computation can be traded for superior tracing performance. Its efficiency comes from direct processing on gray-level data without any preprocessing, and from processing only a minimally necessary fraction of pixels in an exploratory manner, avoiding low-level image-wide operations such as thresholding, edge detection, and morphological processing. These properties make the algorithm suited to real-time, on-line (live) processing and is being applied to computer-assisted laser retinal surgery.     

荧光视网膜图像的照度均衡及自适应血管增强算法

提出一种基于图像反射度照度模型的荧光视网膜图像照度校正与均衡算法.首先,使用多尺度处理及形态学测地膨胀运算将原始图像分离为背景图像和前景图像,然后,在背景图像的基础上使用多方向直线均值法对图像的照度成分进行估计,并由反射度照度模型得到背景的均衡图像;最后,单独对前景血管自适应增强的图像进行灰度校正,并将均衡后的背景图像...     

基于二维对称交叉熵的红外图像阈值分割

针对现有的阈值选取方法应用于目标与背景面积相差悬殊的红外图像时常导致严重的误分割现象,本文提出了一种基于对称交叉熵及背景与目标面积差的红外目标图像阈值选取方法。对称交叉熵能确保分割后类的内聚性好,而背景与目标面积差可抑制均等分割的趋势,将两者综合构成了更为合理的阈值选取准则函数。首先导出了一维阈值选取公式;然后给出了二维直方图斜分阈值及二维直方图斜分的简化阈值选取方法,抗噪性能明显改善;最后与二维斜分的最大熵阈值、Otsu阈值及非对称交叉熵阈值选取方法进行了比较,实验结果表明,本文方法在分割效果上具有明显的优势。     

Finite-element method modeling of superconductors: from 2-D to 3-D

A three-dimensional (3-D) numerical modeling technique for solving problems involving superconducting materials is presented. The model is implemented in finite-element method software and is based on a recently developed 3-D formulation for general electromagnetic problems with solid conductors. It has been adapted for modeling of superconductors with nonlinear resistivity in 3-D, characterized by a power-law E-J relation. It has first been compared with an existing and verified two-dimensional (2-D) model: Compared are the current density distribution inside the conductors and the self-field ac losses for different applied transport currents. Second, the model has been tested for computing the current distribution with typical 3-D geometries, such as corner-shaped and twisted superconductors. Finally, it has been used with two superconducting filaments in the presence of external magnetic field for verifying the existence of coupling currents. This effect deals with the finite length of the conductors and cannot be taken into account by 2-D models.     

A quantitative analysis of 3-D coronary modeling from two or more projection images

A method is introduced to examine the geometrical accuracy of the three-dimensional (3-D) representation of coronary arteries from multiple (two and more) calibrated two-dimensional (2-D) angiographic projections. When involving more then two projections, (multiprojection modeling) a novel procedure is presented that consists of fully automated centerline and width determination in all available projections based on the information provided by the semi-automated centerline detection in two initial calibrated projections. The accuracy of the 3-D coronary modeling approach is determined by a quantitative examination of the 3-D centerline point position and the 3-D cross sectional area of the reconstructed objects. The measurements are based on the analysis of calibrated phantom and calibrated coronary 2-D projection data. From this analysis a confidence region (alpha degrees approximately equal to [35 degrees - 145 degrees]) for the angular distance of two initial projection images is determined for which the modeling procedure is sufficiently accurate for the applied system. Within this angular border range the centerline position error is less then 0.8 mm, in terms of the Euclidean distance to a predefined ground truth. When involving more projections using our new procedure, experiments show that when the initial pair of projection images has an angular distance in the range alpha degrees approximately equal to [35 degrees - 145 degrees], the centerlines in all other projections (gamma = 0 degrees - 180 degrees) were indicated very precisely without any additional centering procedure. When involving additional projection images in the modeling procedure a more realistic shape of the structure can be provided. In case of the concave segment, however, the involvement of multiple projections does not necessarily provide a more realistic shape of the reconstructed structure.     

Projective analysis of 2-D images

The use of the heatlike equation has been extended to the projective case in order to find a projective analysis of curves and images; unfortunately, this formulation leads to a fifth-order partial differential equation (PDE) that is not easy to implement. Thanks to the use of a three-dimensional (3-D) homogeneous representation of a picture, we present an alternative. Roughly speaking, it is a kind of decomposition of the heatlike formulation with well-posed second-order PDEs. The number of parameters goes from one to three (the scale parameter and two direction parameters). Moreover, this study allows us to propose a simplified multiscale analysis, which is given by an unique PDE (one parameter), for the subgroup of the projective transformations associated, up to a nonzero scalar factor, to an orthogonal 3x3 matrix.     

Image modeling based on a 2-D stochastic subspace system identification algorithm

Fitting a causal dynamic model to an image is a fundamental problem in image processing, pattern recognition, and computer vision. In image restoration, for instance, the goal is to recover an estimate of the true image, preferably in the form of a parametric model, given an image that has been degraded by a combination of blur and additive white Gaussian noise. In texture analysis, on the other hand, a model of a particular texture image can serve as a tool for simulating texture patterns. Finally, in image enhancement one computes a model of the true image and the residuals between the image and the modeled image can be interpreted as the result of applying a de-noising filter. There are numerous other applications within the field of image processing that require a causal dynamic model. Such is the case in scene analysis, machined parts inspection, and biometric analysis, to name only a few. There are many types of causal dynamic models that have been proposed in the literature, among which the autoregressive moving average and state-space models (i.e., Kalman filter) are the most commonly used. In this paper we introduce a 2-D stochastic state-space system identification algorithm for fitting a quarter plane causal dynamic Roesser model to an image. The algorithm constructs a causal, recursive, and separable-in-denominator 2-D Kalman filter model. The algorithm is tested with three real images and the quality of the estimated images are assessed.     

Reflectance pulse oximetry measurements from the retinal fundus

Conventional transmission pulse oximetry is a noninvasive technique for the continuous monitoring of arterial oxygen saturation (SaO₂) from peripheral vascular beds such as the finger tip or earlobe. It is proposed to exploit the unique transparency of the ocular media to make reflectance pulse oximetry measurements on the retinal fundus. This technique potentially offers significant advantages over conventional pulse oximetry, primarily in the ability to monitor cerebral, as opposed to peripheral, oxygen saturation. An in vitro system has been developed to simulate the retinal circulation and ocular optics. This system consists of a flexible cuvette located in a model eye and an extracorporeal blood circuit to simulate arterial blood flow. The system was used to investigate the relationship between SaO₂ and the R/IR ratio in reflectance pulse oximetry. To enable in vivo measurements to be made, a standard haptic contact lens was modified to hold the pulse oximeter probe in front of the pupil. In a preliminary study, the lens was fitted to an awake volunteer and cardiac-synchronous signals were detected by the retinal pulse oximeter     

Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images

A model-based algorithm, termed exclusion region and position refinement (ERPR), is presented for improving the accuracy and repeatability of estimating the locations where vascular structures branch and cross over, in the context of human retinal images. The goal is two fold. First, accurate morphometry of branching and crossover points (landmarks) in neuronal/vascular structure is important to several areas of biology and medicine. Second, these points are valuable as landmarks for image registration, so improved accuracy and repeatability in estimating their locations and signatures leads to more reliable image registration for applications such as change detection and mosaicing. The ERPR algorithm is shown to reduce the median location error from 2.04 pixels down to 1.1 pixels, while improving the median spread (a measure of repeatability) from 2.09 pixels down to 1.05 pixels. Errors in estimating vessel orientations were similarly reduced from 7.2 degrees down to 3.8 degrees.     

Noise characteristics of 3-D and 2-D PET images

The authors analyzed the noise characteristics of two-dimensional (2-D) and three-dimensional (3-D) images obtained from the GE Advance positron emission tomography (PET) scanner. Three phantoms were used: a uniform 20-cm phantom, a 3-D Hoffman brain phantom, and a chest phantom with heart and lung inserts. Using gated acquisition, the authors acquired 20 statistically equivalent scans of each phantom in 2-D and 3-D modes at several activity levels. From these data, they calculated pixel normalized standard deviations (NSD's), scaled to phantom mean, across the replicate scans, which allowed them to characterize the radial and axial distributions of pixel noise. The authors also performed sequential measurements of the phantoms in 2-D and 3-D modes to measure noise (from interpixel standard deviations) as a function of activity. To compensate for the difference in axial slice width between 2-D and 3-D images (due to the septa and reconstruction effects), they developed a smoothing kernel to apply to the 2-D data. After matching the resolution, the ratio of image-derived NSD values (NSD_2D/NSD_3D)² averaged throughout the uniform phantom was in good agreement with the noise equivalent count (NEC) ratio (NEC_3D/NEC_2D). By comparing different phantoms, the authors showed that the attenuation and emission distributions influence the spatial noise distribution. The estimates of pixel noise for 2-D and 3-D images produced here can be applied in the weighting of PET kinetic data and may be useful in the design of optimal dose and scanning requirements for PET studies. The accuracy of these phantom-based noise formulas should be validated for any given imaging situation, particularly in 3-D, if there is significant activity outside the scanner field of view     

Assessment of the 3-d reconstruction and high-resolution geometrical modeling of the human skeletal trunk from 2-D radiographic images

This paper presents an in vivo validation of a method for the three-dimensional (3-D) high-resolution modeling of the human spine, rib cage, and pelvis for the study of spinal deformities. The method uses an adaptation of a standard close-range photogrammetry method called direct linear transformation to reconstruct the 3-D coordinates of anatomical landmarks from three radiographic images of the subject's trunk. It then deforms in 3-D 1-mm-resolution anatomical primitives (reference bones) obtained by serial computed tomography-scan reconstruction of a dry specimen. The free-form deformation is calculated using dual kriging equations. In vivo validation of this method on 40 scoliotic vertebrae gives an overall accuracy of 3.3 +/- 3.8 mm, making it an adequate tool for clinical studies and mechanical analysis purposes.     

Interpolation of 3-D binary images based on morphological skeletonization

In this paper, the morphological skeleton interpolation (MSI) algorithm is presented. It is an efficient, shape-based interpolation method used for interpolating slices in a three-dimensional (3-D) binary object. It is based on morphological skeletonization, which is used for two-dimensional (2-D) slice representation. The proposed morphological skeleton matching process provides translation, rotation, and scaling information at the same time. The interpolated slices preserve the shape of the original object slices, when the slices have similar shapes. It can also modify the shape of an object when the successive slices do not have similar shapes. Applications on artificial and real data are also presented.     

Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter

In this paper, the fitness of estimating vessel profiles with Gaussian function is evaluated and an amplitude-modified second-order Gaussian filter is proposed for the detection and measurement of vessels. Mathematical analysis is given and supported by a simulation and experiments to demonstrate that the vessel width can be measured in linear relationship with the "spreading factor" of the matched filter when the magnitude coefficient of the filter is suitably assigned. The absolute value of vessel diameter can be determined simply by using a precalibrated line, which is typically required since images are always system dependent. The experiment shows that the inclusion of the width measurement in the detection process can improve the performance of matched filter and result in a significant increase in success rate of detection.     

基于可控图像分割的快速视网膜血管提取算法

针对多数视网膜血管提取算法实时性不强和分割 精度不高的问题,提出了一种基于可控图像分割的 快速视网膜血管提取算法。首先,对视网膜G分量图像的灰 度进行反转和自适应直方图均衡化,应用结 构元素为“菱形”和“圆盘形”的形态学“开”运算平滑图像背景和增强血管对比度,消除 视盘后阈值分割并二值 化得到不含视盘的分割图像。其次,根据在灰度图像中检测到的视盘构建掩膜,再次对 视网膜绿色分 量图像自适应直方图均衡化后进行阈值分割,并和掩膜进行逻辑“与”运算得到含有掩膜的 分割图像。最后, 将不含视盘的分割图像与含有掩膜的分割图像进行逻辑“与”运算,并融合边界信息获得最 终的视网膜血管 结构。实验结果表明,本文算法能有效提取视网膜眼底图像的血管网络,有较强的实时性和 较高的分割精度。     

SOI flash memory scaling limit and design consideration based on 2-D analytical modeling

In this paper, the short-channel effect in ultrathin body (UTB) SOI Flash memory cell induced by the floating-gate is investigated by a newly developed two-dimensional analytical model. A concept of effective natural length (/spl lambda//sub eff/) is introduced as a measure of the impact of the floating-gate on the scaling limit. Even though scaling the channel thickness can significantly reduce SCE in UTB MOSFET, it becomes less effective in floating-gate device due to the floating polysilicon induced gate coupling. To minimize the floating-gate induced SCEs, the drain to floating-gate coupling has to be minimized.     

基于U-Net网络改进算法的视网膜血管分割研究北大核心CSCD

针对视网膜图像血管细小,细节特征丢失、梯度下降、爆炸而导致分割效果差的问题,本文提出了一种引入残差块、循环卷积模块和空间通道挤压激励模块的U-Net视网膜血管图像分割模型。首先通过使用一系列随机增强来扩展训练集并对数据集进行预处理,然后在U-Net模型中引入残差块,避免随着网络深度增加,分割准确率达到饱和然后迅速退化以及优化计算成本;并将U-Net网络的底部替换为循环卷积模块,提取图像低层次的特征,并不断的进行特征积累,增强上下文之间的语义信息,获得更有效的分割模型;最后在卷积层之间嵌入空间通道挤压激励模块,通过找到特征较好的通道,强调这一通道,压缩不相关的通道使得网络模型能够加强关键语义特征信息的学习,通过训练过程学习到有效的特征信息,同时增强抗干扰能力。通过在DRIVE数据集上的验证结果可得,本文所提模型的准确率为98.42%,灵敏度达到了82.36%,特异值达到了98.86%。通过和其他网络分割方法比较,本文所提分割方法具有更优的分割效果。