基于Hessian矩阵线状滤波的眼底图像血管分割

针对眼底图像血管分割问题,本文研究了一种基于Hessian矩阵多尺度线状滤波的血管分割方法。首先,采用基于Hessian矩阵的多尺度线状滤波增强血管区域,然后对增强后图像采用最大类间方差阈值法进行阈值分割,最后得到血管的二值化分割结果。本文采用了DRIVE数据库眼底图像进行实验验证,实验表明本文方法能够自动地得到较完整和准确的眼底图像血管分割结果。     

基于主曲率和主方向的多尺度视网膜血管骨架提取方法

为了减少视网膜血管骨架提取过程中低对比度血管的漏检和误检数量,提出了一种基于主曲率和主方向的多尺度视网膜血管骨架提取方法。首先,分别提取视网膜图像中每个像素点在多尺度高斯滤波后的主曲率和主方向;其次,在每个尺度下分别提取最大主曲率方向上的局部最大值点,并通过曲率阈值筛选出高对比度血管中心像素点作为种子点;然后,利用最小主方向对低对比度血管进行骨架追踪和标记;最后,对多个尺度下提取的血管骨架进行融合。方法分别在DRIVE训练数据集、DRIVE测试数据集和STARE数据集上进行了测试,漏检数量分别为89、97、106,误检数量分别为99、101、122。实验结果表明,该方法能够提取出低对比度的细小血管骨架,但对于对比度在3个灰度级以内的细小血管存在少量漏检,对于与血管粘连的高对比度细条状纹理和病灶干扰存在少量误检。     

自适应脉冲耦合神经网络与匹配滤波器相结合的视网膜血管分割

针对眼底图像中血管与背景间对比度低以及血管自身结构复杂等因素对视网膜血管分割所带来的问题,本文提出了一种具有自适应连接值的脉冲耦合神经网络(PCNN)与高斯匹配滤波器相结合的视网膜血管分割方法。首先,利用对比度受限制的自适应直方图均衡化(CLAHE)技术与二维高斯匹配滤波器对血管区域的对比度进行有效增强。然后,利用经验阈值选择出一定的血管区域作为初始种子区域。接着,将带有快速连接机制的PCNN与种子区域增长思想相结合,通过自适应动态设置PCNN中的连接强度系数和停止条件,实现眼底图像中血管区域的自动生长。整个算法在DRIVE视网膜图像库中进行了测试,实验结果表明,相比于不使用动态连接强度系数与停止条件的方法,所提出算法的灵敏度从49.79%提高至70.39%,准确度从95%提高到95.39%。证明了该算法具有较好的分割精确度和应用价值。     

彩色视网膜血管图像的自动分割算法

为了保证眼底测量结果的准确性、客观性、可重复性以及实用性，提出了彩色眼底图像自动分割与定量分析的算法。具体步骤如下：首先对彩色视网膜血管图像进行网格划分，其次对包含重要血管信息的网格区域实现Otsu阈值分割，在此基础上对其它相邻网格进行区域生长算法分割，最后由计算机统一处理得到视网膜血管的网络径线。实验结果表明：该算法提取的血管网络径线连续性较好，血管中心线定位准确，抗干扰能力较强，处理速度较快，具有较高的临床应用价值。     

乳腺肿瘤超声图像的特征分析

基于乳腺肿瘤良恶性在超声图像的不同特征,利用计算机自动识别,作为医生的辅助诊断.方法的步骤为本文先在常用超声仪上获得乳腺肿瘤超声图像,接着从图像中自动提取肿瘤边缘,然后自动提取不依赖于超声仪系统的特征参数,用特征选择器选择出最优特征矢量,最后经分类器判别乳腺肿瘤的良恶性.实验基于200例病例随机划分为训练集和测试集各半进行测试,获得结果Accuracy为0.960,Sensitivity为0.982,Specificity为0.935,PPV和NPV分别为0.946和0.977,结果表明本文方法泛化能力强,可以作为识别乳腺肿瘤良恶性的一种辅助手段.     

基于Hessian矩阵的视网膜血管中心线提取

为实现视网膜血管在临床诊断中的重要作用,提出了一种基于Hessian矩阵的视网膜血管提取方法,该方法通过图像预处理增强血管信息,利用血管的微分几何特性,采用离散高斯核对眼底图像进行卷积,结合Hessian矩阵计算血管方向,通过连接算法得到视网膜血管的分布情况.实验结果表明,该方法提取血管中心线的精度可达亚像素级,对不同眼底照相机拍摄的眼底图像可根据血管宽度进行多尺度快速分割.     

融合下补偿结构的眼底血管图像分割网络研究

眼底血管图像在临床中通常被用于眼部疾病的诊断及监测，其中血管的形态结构能够反映疾病的重要特征，因此，眼底血管图像的分割处理对眼部疾病的诊断和预防具有十分重要的医学意义。针对目前人工智能主流算法中卷积和池化操作会导致很多特征丢失，提取特征时会忽视图像中的空间信息，图像中的细小血管很难分割出来等问题，基于U-net模型进行了相关研究，结合空间注意力模块对空间特征进行细化，同时提出了一种下补偿结构LCSAnet。该结构能够减少网络提取特征信息过程中的特征损失，从而提高分割精度。研究实验在DRIVE数据集上完成，LC-SAnet的分割准确率达到96.97%,F1值达到74.36%。结果证明，LC-SAnet表现出更好的分割性能，对细小血管的结构识别更加准确。     

彩色眼底图像视盘自动定位与分割

针对彩色眼底图像视盘定位时图像边缘高亮环对定位准确率的影响,提出了一种有效的图像预处理方法。针对已有的视盘分割算法中存在的问题,提出了一种结合形态学、椭圆拟合及梯度矢量流(GVF)Snake模型的分割算法。提出的预处理方法首先利用最小二乘法拟合出眼底图像的边界,然后裁剪掉边界的一部分高亮像素点,最后进行视盘定位。视盘分割算法则首先进行血管擦除,然后用椭圆拟合提取初始轮廓,最后使用GVF Snake精确调整视盘边界。用提出的方法对Messidor眼底图像数据库1 200幅图像上进行了实验,结果显示:视盘定位准确率由原来没经过预处理的95.4%提升到了98.7%;视盘分割错误率与当前已知最好的算法相比由12.5%降低到了9.39%。结果表明:提出的眼底图像视盘自动定位与分割方法准确率高、实用性强,可以用于眼科疾病的计算机辅助诊断。     

融合特征相互关系的视网膜微动脉瘤提取

为了抑制视网膜不同结构特征之间的影响,提高视网膜微动脉瘤的检测精度,提出了一种基于特征相互关系的视网膜微动脉瘤提取算法.首先,对视网膜灰度图像进行均值滤波,检测圆形边界和视盘,并构建视盘掩模.然后,对视网膜绿色分量图像自适应直方图均衡化,利用Canny方法提取边缘,移除图像圆形边界并填充封闭的小面积对象.最后,考虑不同特征之间的相互关系,消除较大面积对象后进行”逻辑与”运算移除视网膜渗出物、血管和视盘,得到视网膜微动脉瘤图像.实验结果表明:该算法能够有效提取视网膜眼底图像中的微动脉瘤,其敏感度、特异性、阳性预测值和检测精度分别达到了94.81％、96.04％、91.64％和95.66％,基本能够满足临床应用对稳定性和精度的要求.     

动静脉血管自动分类方法及其管径测量

视网膜动静脉管径以及动静脉比值可以反映高血压患者脑卒中发病的风险,因此对视网膜血管直径的量化分析有助于病情的风险评估和防治工作。提出了一种视网膜动静脉自动分类和血管直径的自动测量方法。首先,对视网膜血管网络进行分割,并获取中心线;其次选取了不同颜色空间中的不同通道分量,提出了基于中心线像素和血管像素的特征向量、血管宽度和中心光反射的特征向量,采用K均值聚类实现感兴趣测量区域内动静脉的自动分类;最后统计血管横截面的灰度曲线分布,利用高斯曲线进行拟合,根据半高度全宽获取动静脉宽度。分别对REVIEW和DRIVE数据库进行实验,验证了本方法的有效性。     

Microscopic retinal blood vessels detection and segmentation using support vector machine and K-nearest neighbors

The retina is the deepest layer of texture covering the rear of the eye, recorded by fundus images. Vessel detection and segmentation are useful in disease diagnosis. The retina's blood vessels could help diagnose maladies such as glaucoma, diabetic retinopathy, and blood pressure. A mix of supervised and unsupervised strategies exists for the detection and segmentation of blood vessels images. The tree structure of retinal blood vessels, their random area, and different thickness have caused vessel detection difficulties at machine learning calculations. Since the green band of retinal images conveys more information about the vessels, they are utilized for microscopic vessels detection. The current research proposes an administered calculation for segmentation of retinal vessels, where two upgrading stages depending on filtering and comparative histogram were applied after pre-processing and image quality improvement. At that point, statistical features of vessel tracking, maximum curvature and curvelet coefficient are extracted for each pixel. The extracted features are classified by support vector machine and the k-nearest neighbors. The morphological operators then enhance the classified image at the final stage to segment with higher accuracy. The dice coefficient is utilized for the evaluation of the proposed method. The proposed approach is concluded to be better than different strategies with a normal of 92%.     

Automated techniques for blood vessels segmentation through fundus retinal images: A review

Retina is the interior part of human's eye, has a vital role in vision. The digital image captured by fundus camera is very useful to analyze the abnormalities in retina especially in retinal blood vessels. To get information of blood vessels through fundus retinal image, a precise and accurate vessels segmentation image is required. This segmented blood vessel image is most beneficial to detect retinal diseases. Many automated techniques are widely used for retinal vessels segmentation which is a primary element of computerized diagnostic systems for retinal diseases. The automatic vessels segmentation may lead to more challenging task in the presence of lesions and abnormalities. This paper briefly describes the various publicly available retinal image databases and various machine learning techniques. State of the art exhibited that researchers have proposed several vessel segmentation methods based on supervised and supervised techniques and evaluated their results mostly on publicly datasets such as digital retinal images for vessel extraction and structured analysis of the retina. A comprehensive review of existing supervised and unsupervised vessel segmentation techniques or algorithms is presented which describes the philosophy of each algorithm. This review will be useful for readers in their future research.     

免散瞳眼底照相机精密调焦技术研究

提出采用双光楔裂像调焦技术实现在被观测眼底图像很暗情况下的精确调焦,将一条矩形狭缝成像到眼底,在双光楔的作用下,通过矩形狭缝上下两半部的光线传播方向不同,在精确聚焦的情况下,上下两半条矩形亮斑将位于一条直线上,如果聚焦不准确,上下两半条矩形亮斑将分离,分离的方向和大小由离焦的情况决定。实验证实通过判断上下两条矩形亮斑是否位于一条直线上来调焦具有操作简单、精确度高等优点。     

Observation of the retina using the tandem scanning confocal microscope

A tandem scanning confocal microscope (TSCM) is currently being used to obtain high-resolution images of the human cornea in vivo. Advantages of confocal microscopy for in vivo imaging include optical sectioning and increased contrast through removal of scattered light. We have adapted the TSCM to view the retina in vivo by constructing an applanating lens and fitting the microscope with an imaging-intensifying camera of increased sensitivity. The microscope uses a spinning disc with 40,000 holes, each of 30 microns diameter, and a 100 W mercury arc lamp light source with a 455 nm long pass filter. The applanating lens is composed of three elements, two of which are movable for focusing. Images of a rabbit retina were obtained in vivo revealing the nerve fiber layer and blood vessels around the optic disc. The power density at the retina was calculated to be 3 mW/cm², which is well below the power levels of a direct or indirect ophthalmoscope. Magnification of the retinal image was approximately 60x and a 1 mm wide area of retina was in view. This prototype TSCM system demonstrates that images of a retina in vivo are obtainable with confocal microscopy and that the sharpness is comparable to standard fundus camera photography. Further modifications to improve the light level and alterations in the design of the objective should improve the quality of the images obtained and achieve the enhanced resolution of which, in theory, the confocal microscope is capable.     

Feature extraction and soft computing methods for aerospace structure defect classification

This study concerns the effectiveness of several techniques and methods of signals processing and data interpretation for the diagnosis of aerospace structure defects. This is done by applying different known feature extraction methods, in addition to a new CBIR-based one; and some soft computing techniques including a recent HPC parallel implementation of the U-BRAIN learning algorithm on Non Destructive Testing data. The performance of the resulting detection systems are measured in terms of Accuracy, Sensitivity, Specificity, and Precision. Their effectiveness is evaluated by the Matthews correlation, the Area Under Curve (AUC), and the F-Measure. Several experiments are performed on a standard dataset of eddy current signal samples for aircraft structures. Our experimental results evidence that the key to a successful defect classifier is the feature extraction method – namely the novel CBIR-based one outperforms all the competitors – and they illustrate the greater effectiveness of the U-BRAIN algorithm and the MLP neural network among the soft computing methods in this kind of application.     

基于迁移学习与特征融合的眼底图像分类

针对大量眼底图片难以收集和标注、有经验的眼科医生地区分配不均匀等,导致眼底疾病患者检查准确度低、花费时间较长等问题,本文基于迁移学习提出一种图像分类方法:首先修改EfficientNet-B0和EfficientNet-B7模型并进行参数微调,将微调后的模型作为特征提取器用于提取眼底图像的特征,再对提取的特征进行特征融...