CN109829942B - An automatic quantification method of retinal vessel diameter in fundus images - Google Patents

An automatic quantification method of retinal vessel diameter in fundus images Download PDF

Info

Publication number
CN109829942B
CN109829942B CN201910128419.8A CN201910128419A CN109829942B CN 109829942 B CN109829942 B CN 109829942B CN 201910128419 A CN201910128419 A CN 201910128419A CN 109829942 B CN109829942 B CN 109829942B
Authority
CN
China
Prior art keywords
image
retinal
optic disc
blood vessels
pixel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910128419.8A
Other languages
Chinese (zh)
Other versions
CN109829942A (en
Inventor
罗忠亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shaoguan University
Original Assignee
Shaoguan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shaoguan University filed Critical Shaoguan University
Priority to CN201910128419.8A priority Critical patent/CN109829942B/en
Publication of CN109829942A publication Critical patent/CN109829942A/en
Application granted granted Critical
Publication of CN109829942B publication Critical patent/CN109829942B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Eye Examination Apparatus (AREA)

Abstract

本发明属于医学图像处理技术领域,公开了一种眼底图像视网膜血管管径自动量化方法;利用粗细定位相结合的两步定位法自动检测视盘;对眼底图像进行预处理,包含眼底图像的去噪和增强处理;采用多尺度分析的方法把视网膜血管从眼底图像背景中分离出来,利用数学形态学开重构剔除分割中的伪血管;利用边界法测量血管管径,并将结果显示出来。本发明在眼底图像特征的基础上,先检测出视盘,然后增强图像对比度,分割出视网膜血管,最后测量视网膜血管管径的大小,将结果显示在系统界面上,给临床医生的早期预测和辅助诊断提供参考,节省人工,提高效率。

Figure 201910128419

The invention belongs to the technical field of medical image processing, and discloses a method for automatically quantifying retinal vessel diameters in fundus images; using a two-step positioning method that combines thick and thin positioning to automatically detect optic discs; preprocessing the fundus images, including denoising the fundus images and enhanced processing; use multi-scale analysis method to separate retinal blood vessels from fundus image background, use mathematical morphology to open and reconstruct to eliminate false blood vessels in segmentation; use boundary method to measure blood vessel diameter, and display the results. Based on the characteristics of the fundus image, the present invention first detects the optic disc, then enhances the image contrast, segments the retinal blood vessels, and finally measures the size of the retinal blood vessel diameters, displays the results on the system interface, and provides early prediction and assistance to clinicians. Diagnosis provides reference, saves labor and improves efficiency.

Figure 201910128419

Description

一种眼底图像视网膜血管管径自动量化方法An automatic quantification method of retinal vessel diameter in fundus images

技术领域technical field

本发明属于医学图像处理技术领域,尤其涉及一种眼底图像视网膜血管管径自动量化方法。The invention belongs to the technical field of medical image processing, and in particular relates to a method for automatically quantifying retinal vessel diameters in fundus images.

背景技术Background technique

目前,业内常用的现有技术是这样的:视网膜血管的眼底图像是一种经济而又有效的眼科疾病临床辅助手段,其发展得到人们的普遍关注。在视网膜动静脉交叉处、动脉分支处、静脉行走路径及形态方面改变是视网膜动脉发生硬化病变的重要症状。医生在观察眼底图像时,主要采用摄片法、投影法、检眼镜测像法、定标观测法等测量视网膜血管管径。这些方法大多根据靠人工观察、手工测量和经验进行判断,不能从技术上准确地检测与提取视网膜血管、量化血管管径大小,这将不利于心脑血管疾病的早期预测与辅助诊断,导致患者对自己病情没有清晰的认识。因此人工分析眼底图像存在主观性强、诊断效率低、可重复性差、耗时较长、劳动强度大、准确性和一致性难以得到很好的保证等诸多不足。本发明利用数字图像处理技术测量视网膜血管管径,克服了人为主观误差较大、重复性差的不足,具有测量数据客观、可重复测量、节约人力成本的优势。At present, the commonly used existing technology in the industry is as follows: the fundus image of retinal blood vessels is an economical and effective clinical auxiliary method for ophthalmic diseases, and its development has attracted widespread attention. Changes in retinal arteriovenous intersections, arterial branches, venous paths, and morphology are important symptoms of retinal arteriosclerosis. When doctors observe fundus images, they mainly use radiography, projection, ophthalmoscopy, and calibration observation to measure the diameter of retinal vessels. Most of these methods are judged by manual observation, manual measurement and experience, and cannot technically accurately detect and extract retinal blood vessels and quantify the diameter of blood vessels, which will not be conducive to early prediction and auxiliary diagnosis of cardiovascular and cerebrovascular diseases, resulting in the I don't have a clear understanding of my condition. Therefore, manual analysis of fundus images has many shortcomings such as strong subjectivity, low diagnostic efficiency, poor repeatability, long time consumption, high labor intensity, and difficulty in ensuring accuracy and consistency. The invention uses digital image processing technology to measure the diameter of retinal blood vessels, overcomes the shortcomings of large subjective errors and poor repeatability, and has the advantages of objective measurement data, repeatable measurement, and labor cost savings.

发明内容Contents of the invention

针对现有技术存在的问题,本发明提供了一种眼底图像视网膜血管管径自动量化方法。Aiming at the problems existing in the prior art, the present invention provides a method for automatically quantifying the diameter of retinal blood vessels in fundus images.

本发明是这样实现的,一种眼底图像视网膜血管管径自动量化方法,所述眼底图像视网膜血管管径自动量化方法包括以下步骤:The present invention is achieved in this way, a method for automatically quantifying the diameter of retinal vessels in fundus images, the method for automatically quantifying the diameters of retinal vessels in fundus images includes the following steps:

步骤一,利用粗细定位相结合的两步定位法检测视盘。In step one, the optic disc is detected using a two-step positioning method combining coarse and fine positioning.

视盘定位是眼底图像视网膜血管跟踪、黄斑和病变提取等工作的基础,视盘的各种参数对早期预测和临床辅助诊断具有十分重要的意义。视盘的边缘形状介于椭圆与圆形之间,粗定位把它看成是圆形,精定位检测出真实的形状。Optic disc positioning is the basis of retinal blood vessel tracking, macular and lesion extraction in fundus images, and various parameters of optic disc are of great significance for early prediction and clinical auxiliary diagnosis. The shape of the edge of the optic disc is between an ellipse and a circle. The rough positioning regards it as a circle, and the fine positioning detects the real shape.

(1)视盘粗定位(1) Coarse positioning of optic disc

根据眼底图像的灰度分布情况进行二值化,采用数学形态学知识,去除部分干扰,获得视盘区间,粗定位视盘质心,将视盘粗定位为圆形。假设视盘质心为O,分别沿O点的水平和垂直方向找到视盘边缘上下点A、B和左右点C、D,共四点,利用最小二乘法拟合圆寻求质心,然后获取视盘子图像,According to the gray level distribution of the fundus image, binarization is carried out, and some interference is removed by using mathematical morphology knowledge to obtain the optic disc interval, roughly locate the centroid of the optic disc, and roughly position the optic disc as a circle. Assuming that the centroid of the optic disc is O, find the upper and lower points A, B and the left and right points C and D of the optic disc edge along the horizontal and vertical directions of point O, respectively, a total of four points, use the least square method to fit the circle to find the centroid, and then obtain the sub-image of the optic disc.

质心O的坐标(xo,yo)计算如下,The coordinates (x o , y o ) of the centroid O are calculated as follows,

Figure BDA0001974374900000021
Figure BDA0001974374900000021

其中xi和yi分别为视盘边缘点的横坐标和纵坐标,N为视盘边缘点的总数。Among them, x i and y i are the abscissa and ordinate of the optic disc edge points respectively, and N is the total number of the optic disc edge points.

在误差平方和最小的原则下,圆参数的最小二乘估计为:Under the principle of the smallest sum of squared errors, the least squares estimate of the circle parameter is:

X=(UTU)-1UTV=U-1V   (2)X=(U T U) -1 U T V=U -1 V (2)

其中in

Figure BDA0001974374900000022
Figure BDA0001974374900000022

(x1,y1),(x2,y2),(x3,y3)是A、B、C、D中的任意3点的坐标,将4种情况下的圆心坐标均值分别作为视盘质心坐标。(x 1 , y 1 ), (x 2 , y 2 ), (x 3 , y 3 ) are the coordinates of any three points in A, B, C, and D, and the mean values of the circle center coordinates in the four cases are respectively taken as Optic disc centroid coordinates.

(2)视盘精定位(2) Optic disc fine positioning

利用视盘亮度信息和局部血管信息来粗定位视盘,能够大致确定视盘所在的位置,以此截取子图像。采用基于非重新初始化的变分水平集的动态轮廓跟踪方法可以方便地得到最佳的视盘边界曲线,具有很好的容错性和健壮性,实现视盘的精确定位。Using the optic disc brightness information and local blood vessel information to roughly locate the optic disc, the position of the optic disc can be roughly determined, and the sub-image can be intercepted. Using the dynamic contour tracking method based on non-reinitialized variational level sets can easily obtain the best optic disc boundary curve, which has good fault tolerance and robustness, and realizes precise positioning of the optic disc.

图像能量函数可表示为The image energy function can be expressed as

Figure BDA0001974374900000031
Figure BDA0001974374900000031

式中Ω表图像域,

Figure BDA0001974374900000032
为符号距离函数。
Figure BDA0001974374900000033
其中d是点(x,y)到曲线的最短距离,
Figure BDA0001974374900000034
表惩罚项,它确保水平集函数为符号距离函数,μ为惩罚项权重,常系数λ和v,λ>0,δ(■)是Dirac函数,停止函数
Figure BDA0001974374900000035
H(■)是Heaviside函数。In the formula, Ω represents the image domain,
Figure BDA0001974374900000032
is a signed distance function.
Figure BDA0001974374900000033
where d is the shortest distance from the point (x,y) to the curve,
Figure BDA0001974374900000034
Table penalty item, which ensures that the level set function is a signed distance function, μ is the weight of the penalty item, constant coefficients λ and v, λ>0, δ(■) is the Dirac function, and the stop function
Figure BDA0001974374900000035
H(■) is a Heaviside function.

步骤二,对眼底图像进行预处理,进行去噪和增强处理,采用多尺度方法把视网膜血管从眼底图像背景中分离出来,剔除分割中存在的伪血管。Step 2: Preprocessing the fundus image, performing denoising and enhancement processing, using a multi-scale method to separate the retinal blood vessels from the background of the fundus image, and eliminating the pseudo blood vessels that exist in the segmentation.

个别图像出现畸变现象,采用线性内插值法和归一化图像处理方法实现畸变校正。对于眼底图像成像过程中,非理想采集条件以及成像传感器等特征差异影响,所采集到图像往往存在噪声、光照不均匀、图像对比度较低等问题。因此,在视网膜血管分割前对眼底图像进行预处理。预处理主要包括图像去噪和对比度增强、数学形态学处理等。Distortion occurs in individual images, and the distortion correction is realized by using linear interpolation method and normalized image processing method. In the imaging process of fundus images, due to the influence of non-ideal acquisition conditions and differences in imaging sensors and other characteristics, the collected images often have problems such as noise, uneven illumination, and low image contrast. Therefore, fundus images are preprocessed before retinal vessel segmentation. Preprocessing mainly includes image denoising and contrast enhancement, mathematical morphology processing, etc.

(1)基于Contourlet变换的眼底图像去噪和对比度增强。在Contourlet域采用软阈值去噪的方法抑制噪声;采用非线性增强算子对变换的各带通方向子带系数做增强处理,经反变换得到对比度增强图像。(1) Fundus image denoising and contrast enhancement based on Contourlet transform. In the Contourlet domain, the soft threshold denoising method is used to suppress the noise; the non-linear enhancement operator is used to enhance the transformed sub-band coefficients in each bandpass direction, and the contrast-enhanced image is obtained through inverse transformation.

非线性增强算子如下:The nonlinear enhancement operator is as follows:

E(xi,j)=xi,j.sign(xi,j).tanh(b.u).(1+c.exp(-u.u)    (4)E(xi ,j )=xi ,j .sign(xi ,j ).tanh(bu).(1+c.exp(-uu) (4)

其中,

Figure BDA0001974374900000036
in,
Figure BDA0001974374900000036

(2)基于多尺度分析线性跟踪的视网膜血管分割(2) Retinal vessel segmentation based on multi-scale analysis linear tracking

利用多尺度分析方法对视网膜血管分割的过程就是在不同尺度下提取不同区域和宽度大小血管的过程。首先从图像中选取一部分种子像素后开始跟踪,跟踪过程中对满足条件的像素点赋予较高置信度,跟踪结束后对所有像素点置信度矩阵进行量化,从而获得最初血管。The process of segmenting retinal blood vessels by using multi-scale analysis method is the process of extracting blood vessels of different regions and widths at different scales. First select a part of the seed pixels from the image and start tracking. During the tracking process, a higher confidence is given to the pixels that meet the conditions. After the tracking is completed, the confidence matrix of all pixels is quantified to obtain the initial blood vessel.

①线性跟踪初始种子的选取① Selection of initial seed for linear tracking

跟踪初始种子的血管路径被定义为:Tracing the vessel path of the initial seed is defined as:

Vs={(x,y:Tlow<I(x,y)<Thigh)    (5)V s ={(x,y:T low <I(x,y)<T high ) (5)

Vs为选取的种子序列,I(x,y)表示图像在(x,y)处像素的灰度级,Tlow和Thigh表示图像最小和最高灰度值,通过图像中血管区域的大小来估计,像素低于Tlow的点属于视网膜图像血管较暗区域,像素高于Thigh的点,其属于视网膜图像血管较亮区域,这些像素点的置信度较高。V s is the selected seed sequence, I(x, y) represents the gray level of the image pixel at (x, y), T low and T high represent the minimum and highest gray value of the image, through the size of the blood vessel area in the image It is estimated that the points with pixels lower than T low belong to the darker area of retinal image blood vessels, and the points with pixels higher than T high belong to the brighter area of retinal image blood vessels, and the confidence of these pixel points is higher.

线性跟踪过程中,将属于血管像素的置信度保存在序列Cw中,若置信度矩阵中某个像素的置信度较高,则其属于血管的概率也相对较高。初始时,将置信度矩阵中所有尺度下的元素都设置为0。During the linear tracking process, the confidence degree of the pixel belonging to the blood vessel is stored in the sequence Cw . If the confidence degree of a certain pixel in the confidence matrix is high, the probability that it belongs to the blood vessel is relatively high. Initially, the elements of all scales in the confidence matrix are set to 0.

Cw(x,y):=0   (6)C w (x, y): = 0 (6)

②线性跟踪的初始化②Initialization of linear tracking

视网膜血管线性跟踪的初始化过程可以用式(7)表示:The initialization process of linear tracking of retinal blood vessels can be expressed by formula (7):

k:=1,Vc(k):=Vs(t),Cc:={}  (7)k:=1, V c (k):=V s (t), C c :={} (7)

其中,Vc为当前循环变量t下跟踪得到的像素序列,Cc为新跟踪像素序列。Among them, V c is the pixel sequence obtained by tracking under the current loop variable t, and C c is the new tracking pixel sequence.

③新跟踪像素的估计③ Estimation of new tracking pixels

当前跟踪的像素点为最后一个进入Vc的对象,Cc是一个由候选像素点构成的序列,候选像素点就是当前跟踪像素周围最近的8个像素点,不包括属于Vc的点,如式(8)所示:The currently tracked pixel is the last object entering Vc , and Cc is a sequence composed of candidate pixels, and the candidate pixels are the nearest 8 pixels around the current tracking pixel, excluding points belonging to Vc , such as Formula (8) shows:

Cc=N8(Vc(k))-Vc    (8)C c = N 8 (V c (k)) - V c (8)

将当前的跟踪像素加入到Vc中,如式(9)所示:Add the current tracking pixel to Vc , as shown in formula (9):

k:=k+1,Vc(k):=(x,y)   (9)k:=k+1, V c (k):=(x,y) (9)

则置信度矩阵Cw可以更新为:Then the confidence matrix C w can be updated as:

Cw(x,y):=Cw(x,y)+1,(x,y):=(xc,yc)  (10)C w (x,y):=C w (x,y)+1,(x,y):=(x c ,y c ) (10)

式(9)中所有的参数值均小于T时,开始寻找下一个种子像素点(t:=t+1)。When all parameter values in formula (9) are less than T, start to search for the next seed pixel point (t:=t+1).

④多尺度线性跟踪④Multi-scale linear tracking

按照一定的尺度对所有种子点进行重复跟踪,尺度数由视网膜图像中待检测血管的宽度决定,若视网膜图像中的血管有较大的可变性,则其对应尺度数也较多。经过多次仿真实验,尺度W=3,5,7,9,11时效果较好。Repeatedly track all seed points according to a certain scale. The number of scales is determined by the width of the blood vessels to be detected in the retinal image. If the blood vessels in the retinal image have greater variability, the number of corresponding scales will also be larger. After several simulation experiments, the effect is better when the scale W=3,5,7,9,11.

⑤视网膜血管的初始提取⑤ Initial extraction of retinal blood vessels

采用映射量化法对血管进行初始估计。最初的血管是由置信度矩阵中大于TC的像素点构建,通常TC值等于尺度W的值。Initial estimates of blood vessels were performed using map quantification. The initial blood vessels are constructed from pixels larger than T C in the confidence matrix, and usually the T C value is equal to the value of the scale W.

步骤三,采用边界法测量血管管径,并将结果显示在系统界面上。Step 3: measure the diameter of the blood vessel using the boundary method, and display the result on the system interface.

(1)血管测量图像区域选择(1) Selection of blood vessel measurement image area

从分割出来的视网膜血管图像中,选择感兴趣的区域截取血管子图像做边缘检测,然后对子图像的血管进行宽度测量,可以减少处理的时间。From the segmented retinal blood vessel image, select the region of interest to intercept the blood vessel sub-image for edge detection, and then measure the width of the blood vessel in the sub-image, which can reduce the processing time.

(2)血管管径宽度的计算(2) Calculation of vessel diameter width

子图像中的血管方向尽量与水平方向平行,如果不是水平的,可以采用旋转角度的方法,使其尽量平行水平方向。采用最小距离法实现视网膜血管管径宽度的自动测量。The direction of the blood vessels in the sub-image should be parallel to the horizontal direction as much as possible. If it is not horizontal, the method of rotating the angle can be used to make it parallel to the horizontal direction as much as possible. The minimum distance method is used to realize the automatic measurement of the diameter and width of retinal vessels.

对垂直方向上下边缘点的坐标,利用两点间的距离公式计算,算出距离值作为血管宽度值,可表示为:For the coordinates of the upper and lower edge points in the vertical direction, use the distance formula between two points to calculate, and calculate the distance value as the blood vessel width value, which can be expressed as:

Figure BDA0001974374900000051
Figure BDA0001974374900000051

其中,wi是i列的宽度值,(xi,yi)和(xk,yk)分别是血管上下边缘的坐标。距离法具有适应范围广、稳定性好、精度高的优点。Wherein, w i is the width value of column i, and (x i , y i ) and (x k , y k ) are the coordinates of the upper and lower edges of the blood vessel respectively. The distance method has the advantages of wide adaptability, good stability and high precision.

(3)标尺定位及像素间距计算(3) Ruler positioning and pixel spacing calculation

为把以像素标定的血管管径转变为血管管径的实际大小,需测量像素间距,因此,必须在图像中对标尺定位。In order to convert the vascular diameter marked by pixels into the actual size of the vascular caliber, the pixel pitch needs to be measured, therefore, the scale must be positioned in the image.

通过最小刻度值与相邻刻度线之间的像素个数计算出像素的物理长度。在与截取子图像同样大小的图像中设定标尺,如尺度为10mm×10mm,对标尺图像进行边缘检测处理之后,得到的是二值图像,设标尺的像素值为1,背景的像素值为0。对二值化标尺图像从上到下遍历二值图像,计算其像素数目。The physical length of the pixel is calculated by the number of pixels between the minimum tick value and the adjacent tick mark. Set the scale in the image of the same size as the intercepted sub-image, for example, the scale is 10mm×10mm, after performing edge detection processing on the scale image, a binary image is obtained, the pixel value of the scale is set to 1, and the pixel value of the background is 0. For the binary scale image, traverse the binary image from top to bottom, and calculate the number of pixels.

设固定标尺尺寸为10mm,刻度间的像素数为Num,则像素的物理长度p可以由

Figure BDA0001974374900000061
决定,p的单位为mm/pixel。Let the size of the fixed ruler be 10mm, and the number of pixels between the scales be Num, then the physical length p of the pixels can be given by
Figure BDA0001974374900000061
Determined, the unit of p is mm/pixel.

(4)把血管管径的像素大小转换为物理大小(4) Convert the pixel size of the vessel diameter to the physical size

每个标记点测得的像素与p相乘就可知视网膜血管管径宽度的物理大小。By multiplying the pixels measured by each marker point with p, the physical size of the diameter of the retinal blood vessels can be known.

本发明的另一目的在于提供一种实现所述眼底图像视网膜血管管径测量方法的自动量化系统,该系统包括:Another object of the present invention is to provide an automatic quantification system for realizing the retinal blood vessel diameter measurement method of the fundus image, the system comprising:

眼底图像视盘检测模块,用于实现眼底图像视盘的检测;The fundus image optic disc detection module is used to realize the detection of the fundus image optic disc;

预处理与血管分割模块,用于实现眼底图像去噪和对比度增强,实现视网膜血管的分割;The preprocessing and blood vessel segmentation module is used to achieve fundus image denoising and contrast enhancement, and to achieve retinal blood vessel segmentation;

血管宽度测量与应用模块,用于实现视网膜血管管径测量、临床医生的早期预测和辅助诊断。The blood vessel width measurement and application module is used to realize retinal blood vessel diameter measurement, early prediction and auxiliary diagnosis for clinicians.

综上所述,本发明的优点及积极效果为:在检测出眼底图像视盘的基础上,对图像进行预处理,改善了眼底图像对比度。采用多尺度分析方法分割出视网膜血管,采用边界法测量管径的大小,将结果显示在系统界面上,给临床医生的早期预测和辅助诊断提供参考,节省人工,提高效率。To sum up, the advantages and positive effects of the present invention are: on the basis of detecting the optic disk of the fundus image, the image is preprocessed to improve the contrast of the fundus image. Multi-scale analysis method is used to segment retinal blood vessels, and the boundary method is used to measure the diameter of the vessels, and the results are displayed on the system interface to provide references for early prediction and auxiliary diagnosis of clinicians, saving labor and improving efficiency.

附图说明Description of drawings

图1是本发明实施例提供的眼底图像视网膜血管管径自动量化方法流程图。Fig. 1 is a flowchart of a method for automatically quantifying retinal vessel diameters in fundus images provided by an embodiment of the present invention.

图2是本发明实施例提供的眼底图像视网膜血管管径自动量化系统结构示意图;2 is a schematic structural diagram of an automatic quantification system for retinal blood vessel diameters in fundus images provided by an embodiment of the present invention;

图中:1、图像预处理模块;2、检测与分割模块;3、量化与应用模块。In the figure: 1. Image preprocessing module; 2. Detection and segmentation module; 3. Quantization and application module.

图3是本发明实施例提供的眼底图像视网膜血管管径自动量化方法实现流程图。Fig. 3 is a flowchart for realizing the method for automatically quantifying retinal vessel diameters in fundus images provided by an embodiment of the present invention.

图4是本发明实施例提供的粗定位过程效果示意图。Fig. 4 is a schematic diagram of the effect of the rough positioning process provided by the embodiment of the present invention.

图中:a、去干扰后的视盘;b、质心定位原理图;c、视盘子图像;d、粗定位结果。In the figure: a, optic disc after interference removal; b, schematic diagram of centroid positioning; c, subimage of optic disc; d, rough positioning result.

图5是本发明实施例提供的精定位效果示意图。Fig. 5 is a schematic diagram of the fine positioning effect provided by the embodiment of the present invention.

图中:a、动态跟踪过程图;b、跟踪结果图;c、跟踪曲线加粗;d、精定位结果。In the figure: a, dynamic tracking process diagram; b, tracking result diagram; c, tracking curve bold; d, fine positioning result.

图6是本发明实施例提供的预处理与视网膜血管分割效果示意图。Fig. 6 is a schematic diagram of the effect of preprocessing and retinal vessel segmentation provided by the embodiment of the present invention.

图中:a、原始图像;b、对比度增强图像;c、血管初始分割;d、去除干扰后的血管。In the figure: a, the original image; b, the contrast-enhanced image; c, the initial segmentation of blood vessels; d, the blood vessels after removing interference.

图7是本发明实施例提供的视网膜血管宽度测量过程测量效果示意图。Fig. 7 is a schematic diagram of the measurement effect of the retinal blood vessel width measurement process provided by the embodiment of the present invention.

图中:a、截取血管;b、边缘检测;c、移除孤立噪声;d、旋转血管;e、建立标尺;f、测量结果。In the figure: a, intercepting blood vessels; b, edge detection; c, removing isolated noise; d, rotating blood vessels; e, establishing a ruler; f, measurement results.

具体实施方式Detailed ways

为了使本发明的目的、技术方案及优点更加清楚明白,以下结合实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

针对现有技术采用人工观察、手工测量血管管径劳动强度大、耗时较长的问题。本发明通过图像处理技术自动测量视网膜血管管径,给医生提供早期预测和辅助诊断提供参考,减轻医生劳动强度,提高诊断效率。Aiming at the problems of manual observation and manual measurement of blood vessel diameter in the prior art, labor intensity is high and time-consuming is long. The invention automatically measures the diameter of the retinal blood vessels through the image processing technology, provides early prediction and reference for auxiliary diagnosis for doctors, reduces the labor intensity of doctors, and improves diagnosis efficiency.

下面结合附图对本发明的应用原理作详细的描述。The application principle of the present invention will be described in detail below in conjunction with the accompanying drawings.

如图1所示,本发明实施例提供的眼底图像视网膜血管管径自动量化方法包括以下步骤:As shown in Figure 1, the method for automatically quantifying the diameter of retinal blood vessels in fundus images provided by the embodiment of the present invention includes the following steps:

S101:利用粗细定位相结合的两步定位法自动检测视盘;S101: Automatically detect the optic disc by using a two-step positioning method combining coarse and fine positioning;

S102:对眼底图像进行预处理,对把视网膜血管从眼底图像背景中分离出来,剔除分割中存在的伪血管;S102: Preprocessing the fundus image, separating retinal blood vessels from the background of the fundus image, and removing pseudo blood vessels in the segmentation;

S103:采用边界法测量血管管径,并将结果显示在系统界面上。S103: Measure the diameter of the blood vessel by the boundary method, and display the result on the system interface.

所述步骤S101中,自动检测视盘中视盘定位是眼底图像视网膜血管跟踪、黄斑和病变提取等工作的基础,视盘的各种参数对临床的诊断具有十分重要的意义。视盘的边缘形状在椭圆与圆形之间,粗定位把它看成是圆形,精定位检测出真实的形状。In the step S101, the automatic detection of the optic disc location in the optic disc is the basis for retinal blood vessel tracking, macular and lesion extraction in fundus images, and various parameters of the optic disc are of great significance to clinical diagnosis. The shape of the edge of the optic disc is between an ellipse and a circle. The rough positioning regards it as a circle, and the fine positioning detects the real shape.

(1)视盘粗定位(1) Coarse positioning of optic disc

根据眼底图像的灰度分布情况对图像二值化,采用数学形态学知识,去除部分干扰,获得视盘区间,粗定位视盘质心,将视盘粗定位为圆形。假设视盘质心为O,分别沿O点的水平和垂直方向找到视盘边缘上下点A、B和左右点C、D,共四点,利用最小二乘法拟合圆寻求质心,然后获取视盘子图像,According to the gray level distribution of the fundus image, the image is binarized, and the knowledge of mathematical morphology is used to remove part of the interference, obtain the optic disc interval, roughly locate the centroid of the optic disc, and roughly position the optic disc as a circle. Assuming that the centroid of the optic disc is O, find the upper and lower points A, B and the left and right points C and D of the optic disc edge along the horizontal and vertical directions of point O, respectively, a total of four points, use the least square method to fit the circle to find the centroid, and then obtain the sub-image of the optic disc.

质心O的坐标(xo,yo)计算如下,The coordinates (x o , y o ) of the centroid O are calculated as follows,

Figure BDA0001974374900000081
Figure BDA0001974374900000081

其中xi和yi分别为视盘边缘点的横坐标和纵坐标,N为视盘边缘点的总数。Among them, x i and y i are the abscissa and ordinate of the optic disc edge points respectively, and N is the total number of the optic disc edge points.

在误差平方和最小的原则下,圆参数的最小二乘估计为:Under the principle of the smallest sum of squared errors, the least squares estimate of the circle parameter is:

X=(UTU)-1UTV=U-1V   (2)X=(U T U) -1 U T V=U -1 V (2)

其中in

Figure BDA0001974374900000082
Figure BDA0001974374900000082

(x1,y1),(x2,y2),(x3,y3)是A、B、C、D中的任意3点的坐标,将4种情况下的圆心坐标均值分别作为视盘质心坐标。(x 1 , y 1 ), (x 2 , y 2 ), (x 3 , y 3 ) are the coordinates of any three points in A, B, C, and D, and the mean values of the circle center coordinates in the four cases are respectively taken as Optic disc centroid coordinates.

(2)视盘精定位(2) Optic disc fine positioning

利用视盘亮度信息和局部血管信息来粗定位视盘,能够大致确定视盘所在的位置,以此截取子图像。采用基于非重新初始化的变分水平集的动态轮廓跟踪方法可以方便地得到最佳的视盘边界曲线,具有很好的容错性和健壮性,实现视盘的精确定位。Using the optic disc brightness information and local blood vessel information to roughly locate the optic disc, the position of the optic disc can be roughly determined, and the sub-image can be intercepted. Using the dynamic contour tracking method based on non-reinitialized variational level sets can easily obtain the best optic disc boundary curve, which has good fault tolerance and robustness, and realizes precise positioning of the optic disc.

图像能量函数可表示为The image energy function can be expressed as

Figure BDA0001974374900000091
Figure BDA0001974374900000091

式中Ω表图像域,

Figure BDA0001974374900000094
为符号距离函数。
Figure BDA0001974374900000095
其中d是点(x,y)到曲线的最短距离,
Figure BDA0001974374900000096
表惩罚项,它确保水平集函数为符号距离函数,μ为惩罚项权重,常系数λ和v,λ>0,δ(■)是Dirac函数,停止函数
Figure BDA0001974374900000092
H(■)是Heaviside函数。In the formula, Ω represents the image domain,
Figure BDA0001974374900000094
is a signed distance function.
Figure BDA0001974374900000095
where d is the shortest distance from the point (x,y) to the curve,
Figure BDA0001974374900000096
Table penalty item, which ensures that the level set function is a signed distance function, μ is the weight of the penalty item, constant coefficients λ and v, λ>0, δ(■) is the Dirac function, and the stop function
Figure BDA0001974374900000092
H(■) is a Heaviside function.

所述步骤S102中,个别图像出现畸变现象,采用线性内插值法和归一化图像处理方法实现畸变校正。对于眼底图像成像过程中,非理想采集条件以及成像传感器等特征差异影响,所采集到图像往往存在噪声、光照不均匀、图像对比度较低等问题。因此,在视网膜血管分割前对眼底图像进行预处理。预处理主要包括图像去噪和对比度增强、数学形态学处理等。In the step S102, if some images are distorted, linear interpolation method and normalized image processing method are used to realize distortion correction. In the imaging process of fundus images, due to the influence of non-ideal acquisition conditions and differences in imaging sensors and other characteristics, the collected images often have problems such as noise, uneven illumination, and low image contrast. Therefore, fundus images are preprocessed before retinal vessel segmentation. Preprocessing mainly includes image denoising and contrast enhancement, mathematical morphology processing, etc.

(1)基于Contourlet变换的眼底图像去噪和对比度增强。在Contourlet域采用软阈值去噪的方法抑制噪声;采用非线性增强算子对变换的各带通方向子带系数做增强处理,经反变换得到对比度增强图像。(1) Fundus image denoising and contrast enhancement based on Contourlet transform. In the Contourlet domain, the soft threshold denoising method is used to suppress the noise; the non-linear enhancement operator is used to enhance the transformed sub-band coefficients in each bandpass direction, and the contrast-enhanced image is obtained through inverse transformation.

非线性增强算子如下:The nonlinear enhancement operator is as follows:

E(xi,j)=xi,j.sign(xi,j).tanh(b.u).(1+c.exp(-u.u)    (4)E(xi ,j )=xi ,j .sign(xi ,j ).tanh(bu).(1+c.exp(-uu) (4)

其中,

Figure BDA0001974374900000093
in,
Figure BDA0001974374900000093

(2)基于多尺度分析线性跟踪的视网膜血管分割(2) Retinal vessel segmentation based on multi-scale analysis linear tracking

利用多尺度分析方法对视网膜血管分割的过程就是在不同尺度下提取不同区域和宽度大小血管的过程。首先从图像中选取一部分种子像素后开始跟踪,在跟踪过程中对满足条件的像素点赋予较高置信度,跟踪结束后对所有像素点置信度矩阵进行量化,从而获得最初血管。The process of segmenting retinal blood vessels by using multi-scale analysis method is the process of extracting blood vessels of different regions and widths at different scales. First select a part of the seed pixels from the image and start tracking. During the tracking process, a higher confidence is given to the pixels that meet the conditions. After the tracking is completed, the confidence matrix of all pixels is quantified to obtain the initial blood vessel.

①线性跟踪初始种子的选取① Selection of initial seed for linear tracking

跟踪初始种子的血管路径被定义为:Tracing the vessel path of the initial seed is defined as:

Vs={(x,y:Tlow<I(x,y)<Thigh)   (5)V s ={(x,y:T low <I(x,y)<T high ) (5)

Vs为选取的种子序列,I(x,y)表示图像在(x,y)处像素的灰度级,Tlow和Thigh是图像最小灰度值和最高灰度值,通过图像中血管区域的大小来估计,像素低于Tlow的点属于视网膜图像血管较暗区域,像素高于Thigh的点,其属于视网膜图像血管较亮区域,这些像素点的置信度较高。Vs is the selected seed sequence, I(x, y) represents the gray level of the image pixel at (x, y), T low and T high are the minimum gray value and the highest gray value of the image, through the blood vessel area in the image Estimated by the size of , the points with pixels lower than T low belong to the darker area of retinal image blood vessels, and the points with pixels higher than T high belong to the brighter area of retinal image blood vessels, and the confidence of these pixel points is higher.

线性跟踪过程中,将属于血管像素的置信度保存在序列Cw中,若置信度矩阵中的某个像素的置信度较高,则其属于血管的概率也相对较高。初始时,将置信度矩阵中所有尺度下的元素都设置为0。During the linear tracking process, the confidence degree of the pixel belonging to the blood vessel is stored in the sequence Cw . If the confidence degree of a certain pixel in the confidence degree matrix is high, the probability that it belongs to the blood vessel is relatively high. Initially, the elements of all scales in the confidence matrix are set to 0.

Cw(x,y):=0    (6)C w (x, y): = 0 (6)

②线性跟踪的初始化②Initialization of linear tracking

视网膜血管线性跟踪的初始化过程可用式(7)表示:The initialization process of retinal blood vessel linear tracking can be expressed by formula (7):

k:=1,Vc(k):=Vs(t),Cc:={}   (7)k:=1, V c (k):=V s (t), C c :={} (7)

其中,Vc为当前循环变量t下跟踪得到的像素序列,Cc为新跟踪像素序列。Among them, V c is the pixel sequence obtained by tracking under the current loop variable t, and C c is the new tracking pixel sequence.

③新跟踪像素的估计③ Estimation of new tracking pixels

当前跟踪的像素点为最后一个进入Vc的对象,Cc是一个由候选像素点构成的序列,候选像素点就是当前跟踪像素周围最近的8个像素点,不包括属于Vc的点,如式(8)所示:The currently tracked pixel is the last object entering Vc , and Cc is a sequence composed of candidate pixels, and the candidate pixels are the nearest 8 pixels around the current tracking pixel, excluding points belonging to Vc , such as Formula (8) shows:

Cc=N8(Vc(k))-Vc   (8)C c = N 8 (V c (k)) - V c (8)

将当前的跟踪像素加入到Vc中,如式(9)所示:Add the current tracking pixel to Vc , as shown in formula (9):

k:=k+1,Vc(k):=(x,y)    (9)k:=k+1, V c (k):=(x,y) (9)

则置信度矩阵Cw可以更新为:Then the confidence matrix C w can be updated as:

Cw(x,y):=Cw(x,y)+1,(x,y):=(xc,yc)   (10)C w (x,y):=C w (x,y)+1,(x,y):=(x c ,y c ) (10)

式(9)中所有的参数值均小于T时,开始寻找下一个种子像素点(t:=t+1)。When all parameter values in formula (9) are less than T, start to search for the next seed pixel point (t:=t+1).

④多尺度线性跟踪④Multi-scale linear tracking

按照一定的尺度对所有种子点进行重复跟踪,尺度数由视网膜图像中待检测血管宽度决定,若视网膜图像中血管有较大的可变性,则其对应的尺度数也较多。经过多次仿真实验,尺度W=3,5,7,9,11时效果较好。Repeatedly track all seed points according to a certain scale. The number of scales is determined by the width of the blood vessels to be detected in the retinal image. If the blood vessels in the retinal image have greater variability, the number of corresponding scales will also be more. After several simulation experiments, the effect is better when the scale W=3,5,7,9,11.

⑤视网膜血管的初始提取⑤ Initial extraction of retinal blood vessels

采用映射量化法对血管进行初始估计。最初的血管是由置信度矩阵中大于TC的像素点构建,通常TC的值等于尺度W值。Initial estimates of blood vessels were performed using map quantification. The initial blood vessels are constructed from pixels larger than T C in the confidence matrix, and usually the value of T C is equal to the scale W value.

所述步骤S103中,边界法测量血管管径具体过程,如下:In the step S103, the specific process of measuring the vascular diameter by the boundary method is as follows:

(1)血管测量图像区域选择(1) Selection of blood vessel measurement image area

从分割出来的视网膜血管图像中,选择感兴趣的区域截取血管子图像做边缘检测,然后对子图像的血管进行宽度测量,可以减少处理的时间。From the segmented retinal blood vessel image, select the region of interest to intercept the blood vessel sub-image for edge detection, and then measure the width of the blood vessel in the sub-image, which can reduce the processing time.

(2)血管管径宽度的计算(2) Calculation of vessel diameter width

子图像中血管方向尽量与水平方向平行,如果不是水平的,可以采用旋转角度的方法,使其尽量平行水平方向。采用最小距离法实现视网膜血管管径宽度的自动测量。The direction of blood vessels in the sub-image should be parallel to the horizontal direction as much as possible. If it is not horizontal, the method of rotation angle can be used to make it parallel to the horizontal direction as much as possible. The minimum distance method is used to realize the automatic measurement of the diameter and width of retinal vessels.

对垂直方向上下边缘点的坐标,利用两点间的距离公式计算,算出距离值作为血管宽度值,可表示为:For the coordinates of the upper and lower edge points in the vertical direction, use the distance formula between two points to calculate, and calculate the distance value as the blood vessel width value, which can be expressed as:

Figure BDA0001974374900000111
Figure BDA0001974374900000111

其中,wi是i列的宽度值,(xi,yi)和(xj,yj)分别是血管上下边缘的坐标。距离法具有适应范围广、稳定性好、精度高的优点。Wherein, w i is the width value of column i, (x i , y i ) and (x j , y j ) are the coordinates of the upper and lower edges of the blood vessel respectively. The distance method has the advantages of wide adaptability, good stability and high precision.

(3)标尺定位及像素间距计算(3) Ruler positioning and pixel spacing calculation

为把以像素标定的血管管径转变为血管管径的实际大小,需测量像素间距,因此,必须在图像中对标尺定位。In order to convert the vascular caliber marked by pixels into the actual size of the vascular caliber, the pixel pitch needs to be measured, therefore, the scale must be positioned in the image.

通过最小刻度值与相邻刻度线之间的像素个数计算出像素的物理长度。在与截取子图像同样大小的图像中设定标尺,尺度为10mm×10mm,对标尺图像进行边缘检测处理之后,得到的是二值图像,设标尺的像素值为1,背景的像素值为0。对二值化标尺图像从上到下遍历二值图像,计算其像素数目。The physical length of the pixel is calculated by the number of pixels between the minimum tick value and the adjacent tick mark. Set the scale in the image of the same size as the intercepted sub-image, the scale is 10mm×10mm, after the edge detection process is performed on the scale image, a binary image is obtained, the pixel value of the scale is set to 1, and the pixel value of the background is 0 . For the binary scale image, traverse the binary image from top to bottom, and calculate the number of pixels.

设固定标尺尺寸为10mm,刻度间的像素数为Num,则像素的物理长度p可以由

Figure BDA0001974374900000112
决定,p的单位为mm/pixel。Let the size of the fixed ruler be 10mm, and the number of pixels between the scales be Num, then the physical length p of the pixels can be given by
Figure BDA0001974374900000112
Determined, the unit of p is mm/pixel.

(4)把血管管径的像素大小转换为物理大小(4) Convert the pixel size of the vessel diameter to the physical size

每个标记点测得的像素与p相乘就可知视网膜血管管径宽度的物理大小。By multiplying the pixels measured by each marker point with p, the physical size of the diameter of the retinal blood vessels can be known.

如图2所示,本发明实施例提供的眼底图像视网膜血管管径自动量化系统包括:视盘检测模块1、预处理与血管分割模块2、血管宽度测量与应用模块3。As shown in FIG. 2 , the system for automatic quantification of retinal vessel diameters in fundus images provided by the embodiment of the present invention includes: an optic disc detection module 1 , a preprocessing and vessel segmentation module 2 , and a vessel width measurement and application module 3 .

视盘检测模块1,用于实现视网膜图像盘检测。The optic disc detection module 1 is used to realize retinal image disc detection.

预处理与血管分割模块2,用于改善图像质量,提取视网膜血管。Preprocessing and vessel segmentation module 2 is used to improve image quality and extract retinal vessels.

血管宽度测量与应用模块3,用于实现视网膜血管管径测量和给临床医生提供参考。The blood vessel width measurement and application module 3 is used to measure the diameter of retinal blood vessels and provide references for clinicians.

下面结合具体的实施例对本发明的应用原理作详细的描述。The application principle of the present invention will be described in detail below in conjunction with specific embodiments.

视网膜视盘检测:Retinal Optic Disc Detection:

如图4所示,本发明实施例提供的粗定位过程:寻找视盘质心,找到质心后粗定位为圆形,截取子图像。As shown in FIG. 4 , the rough positioning process provided by the embodiment of the present invention: find the centroid of the optic disc, and after finding the centroid, roughly position it as a circle, and intercept the sub-image.

如图5所示,本发明实施例提供的精定位过程为:动态跟踪过程图、跟踪结果图、跟踪曲线加粗、精定位结果。As shown in FIG. 5 , the fine positioning process provided by the embodiment of the present invention is: dynamic tracking process diagram, tracking result diagram, tracking curve thickening, and fine positioning result.

预处理与视网膜血管分割:Preprocessing and retinal vessel segmentation:

如图6所示,本发明实施例提供的预处理与视网膜血管分割过程为:原始图像、对比度增强图像、血管初始分割、去除干扰后的血管。As shown in FIG. 6 , the preprocessing and retinal vessel segmentation process provided by the embodiment of the present invention includes: original image, contrast-enhanced image, initial vessel segmentation, and vessel after interference removal.

视网膜血管宽度测量:Retinal Vessel Width Measurement:

如图7所示,本发明实施例提供的视网膜血管宽度测量过程为:截取血管、边缘检测、移除孤立噪声、旋转血管、建立标尺、测量结果。As shown in FIG. 7 , the measurement process of the retinal blood vessel width provided by the embodiment of the present invention includes: intercepting the blood vessel, detecting the edge, removing isolated noise, rotating the blood vessel, establishing a scale, and measuring the result.

以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.

Claims (2)

1.一种眼底图像视网膜血管管径自动量化方法,其特征在于,所述眼底图像视网膜血管管径自动量化方法包括以下步骤:1. a method for automatic quantification of retinal blood vessel caliber in fundus image, characterized in that, the automatic quantification method for retinal blood vessel caliber in described fundus image comprises the following steps: 步骤一,对利用粗细定位相结合的两步定位法检测视盘;Step 1, the optic disc is detected by a two-step positioning method combining coarse and fine positioning; 步骤二,对眼底图像预处理,进行去噪和增强处理,采用多尺度方法把视网膜血管从眼底图像背景中分离出来,剔除分割中存在的伪血管;Step 2, preprocessing the fundus image, performing denoising and enhancement processing, using a multi-scale method to separate the retinal blood vessels from the background of the fundus image, and eliminating the pseudo blood vessels that exist in the segmentation; 步骤三,采用边界法测量血管管径,并将结果显示在系统界面上;Step 3, using the boundary method to measure the diameter of the blood vessel, and display the result on the system interface; 所述步骤一中,自动检测视盘中视盘定位是眼底图像视网膜血管跟踪、黄斑和病变提取工作的基础:In the first step, the positioning of the optic disc in the automatic detection of the optic disc is the basis of retinal blood vessel tracking, macula and lesion extraction in fundus images: (1)视盘粗定位(1) Coarse positioning of optic disc 根据眼底图像的灰度分布情况对图像二值化,采用数学形态学知识,去除部分干扰,获得视盘区间,粗定位视盘质心,将视盘粗定位为圆形;假设视盘质心为O,分别沿O点的水平和垂直方向找到视盘边缘上下点A、B和左右点C、D,共四点,利用最小二乘法拟合圆寻求质心,然后获取视盘子图像;Binarize the image according to the gray distribution of the fundus image, use mathematical morphology knowledge to remove part of the interference, obtain the optic disc interval, roughly locate the centroid of the optic disc, and roughly position the optic disc as a circle; assume that the centroid of the optic disc is O, respectively along the O In the horizontal and vertical directions of the points, find the upper and lower points A, B and the left and right points C, D on the edge of the optic disc, a total of four points, use the least square method to fit the circle to find the center of mass, and then obtain the sub-image of the optic disc; 质心O的坐标(xo,yo)计算如下:The coordinates (x o , y o ) of the centroid O are calculated as follows:
Figure FDA0004136028310000011
Figure FDA0004136028310000011
其中xi和yi分别为视盘边缘点的横坐标和纵坐标,N为视盘边缘点的总数;Wherein x i and y i are the abscissa and ordinate of the optic disc edge points respectively, and N is the total number of the optic disc edge points; 在误差平方和最小的原则下,圆参数的最小二乘估计为:Under the principle of the minimum sum of squared errors, the least squares estimation of the circle parameters is: X=(UTU)-1UTV=U-1V (2)X=(U T U) -1 U T V=U -1 V (2) 其中in
Figure FDA0004136028310000012
Figure FDA0004136028310000012
(x1,y1),(x2,y2),(x3,y3)是A、B、C、D中的任意3点的坐标,将4种情况下的圆心坐标均值分别作为视盘质心坐标;(x 1 , y 1 ), (x 2 , y 2 ), (x 3 , y 3 ) are the coordinates of any three points in A, B, C, and D, and the mean values of the circle center coordinates in the four cases are respectively taken as Optic disc centroid coordinates; (2)视盘精定位(2) Optic disc fine positioning 利用视盘亮度信息和局部血管信息来粗定位视盘,采用基于非重新初始化的变分水平集的动态轮廓跟踪方法方便地得到最佳的视盘边界曲线,具有很好的容错性和健壮性,实现视盘的精确定位:Use the optic disc brightness information and local blood vessel information to roughly locate the optic disc, and use the dynamic contour tracking method based on the non-reinitialized variational level set to conveniently obtain the best optic disc boundary curve, which has good fault tolerance and robustness, and realizes the optic disc The precise location of: 图像能量函数表示为:The image energy function is expressed as:
Figure FDA0004136028310000021
Figure FDA0004136028310000021
式中Ω表图像域,
Figure FDA0004136028310000022
为符号距离函数;
Figure FDA0004136028310000023
其中d是点(x,y)到曲线的最短距离,
Figure FDA0004136028310000024
表惩罚项,它确保水平集函数为符号距离函数,μ为惩罚项权重,常系数λ和v,λ>0,δ(■)是Dirac函数,停止函数
Figure FDA0004136028310000025
H(·)是Heaviside函数;
In the formula, Ω represents the image domain,
Figure FDA0004136028310000022
is a signed distance function;
Figure FDA0004136028310000023
where d is the shortest distance from the point (x,y) to the curve,
Figure FDA0004136028310000024
Table penalty item, which ensures that the level set function is a signed distance function, μ is the weight of the penalty item, constant coefficients λ and v, λ>0, δ(■) is the Dirac function, and the stop function
Figure FDA0004136028310000025
H( ) is the Heaviside function;
所述步骤二中,个别图像出现畸变现象,采用线性内插值法和归一化图像处理方法实现畸变校正;对于眼底图像成像过程中,非理想采集条件以及成像传感器特征差异影响,所采集到图像存在噪声、光照不均匀、图像对比度较低问题;预处理主要包括图像去噪和对比度增强、数学形态学处理;In the second step, distortion occurs in individual images, and the distortion correction is realized by using the linear interpolation method and the normalized image processing method; during the imaging process of the fundus image, due to the influence of non-ideal acquisition conditions and differences in imaging sensor characteristics, the collected images There are problems of noise, uneven illumination, and low image contrast; preprocessing mainly includes image denoising, contrast enhancement, and mathematical morphology processing; (1)基于Contourlet变换的眼底图像去噪和对比度增强;在Contourlet域采用软阈值去噪的方法抑制噪声;采用非线性增强算子对变换的各带通方向子带系数做增强处理,经反变换得到对比度增强图像;(1) Fundus image denoising and contrast enhancement based on Contourlet transform; in the Contourlet domain, the soft threshold denoising method is used to suppress noise; the non-linear enhancement operator is used to enhance the transformed sub-band coefficients in each band-pass direction, and after inversion transform to obtain a contrast-enhanced image; 非线性增强算子如下:The nonlinear enhancement operator is as follows: E(xi,j)=xi,j.sign(xi,j).tanh(b.u).(1+c.exp(-u.u)         (4)E(xi ,j )=xi ,j .sign(xi ,j ).tanh(bu).(1+c.exp(-uu) (4) 其中,
Figure FDA0004136028310000026
in,
Figure FDA0004136028310000026
(2)基于多尺度分析线性跟踪的视网膜血管分割(2) Retinal vessel segmentation based on multi-scale analysis linear tracking 将图像表示成多个尺度,利用多尺度分析方法对视网膜血管分割为在不同尺度下提取不同区域和宽度大小血管;首先从图像中选取一部分种子像素后开始跟踪,在跟踪过程中对满足条件的像素点赋予较高置信度,跟踪结束后对所有像素点置信度矩阵进行量化,获得最初血管;The image is expressed in multiple scales, and the multi-scale analysis method is used to segment the retinal blood vessels into blood vessels of different regions and widths at different scales; first, a part of the seed pixels are selected from the image to start tracking, and during the tracking process, the satisfying conditions are selected The pixels are given higher confidence, and after the tracking is completed, the confidence matrix of all pixels is quantified to obtain the initial blood vessel; ①线性跟踪初始种子的选取① Selection of initial seed for linear tracking 跟踪初始种子的血管路径定义为:Tracing the vessel path for the initial seed is defined as: Vs={(x,y:Tlow<I(x,y)<Thigh) (5)V s ={(x,y:T low <I(x,y)<T high ) (5) Vs为选取的种子序列,I(x,y)表示图像在点(x,y)处像素的灰度级,Tlow和Thigh是图像最小灰度值和最高灰度值,通过图像中血管区域的大小来估计,像素低于Tlow的点属于视网膜图像血管较暗区域,像素高于Thigh的点,其属于视网膜图像血管较亮区域,这些像素点的置信度较高;V s is the selected seed sequence, I(x, y) represents the gray level of the image pixel at point (x, y), T low and T high are the minimum gray value and the highest gray value of the image, through the image The size of the blood vessel area is estimated. The points with pixels lower than T low belong to the darker area of retinal blood vessels, and the points with pixels higher than T high belong to the brighter area of retinal image blood vessels. The confidence of these pixels is higher; 线性跟踪过程中,将属于血管像素的置信度保存在序列Cw中,若置信度矩阵中某个像素的置信度较高,则其属于血管的概率也相对较高;初始时,将置信度矩阵中所有尺度下的元素都设置为0;In the process of linear tracking, the confidence degree of the pixel belonging to the blood vessel is stored in the sequence Cw . If the confidence degree of a certain pixel in the confidence matrix is high, the probability that it belongs to the blood vessel is relatively high; initially, the confidence degree The elements of all scales in the matrix are set to 0; Cw(x,y):=0 (6)C w (x, y): = 0 (6) ②线性跟踪的初始化②Initialization of linear tracking 视网膜血管线性跟踪的初始化过程用式(7)表示:The initialization process of linear tracking of retinal blood vessels is expressed by formula (7): k:=1,Vc(k):=Vs(t),Cc:={} (7)k:=1, V c (k):=V s (t), C c :={} (7) 其中,Vc为当前循环变量t下跟踪得到的像素序列,Cc为新跟踪像素序列;Among them, V c is the pixel sequence obtained by tracking under the current loop variable t, and C c is the new tracking pixel sequence; ③新跟踪像素的估计③ Estimation of new tracking pixels 当前跟踪的像素点为最后一个进入Vc的对象,Cc是一个由候选像素点构成的序列,候选像素点就是当前跟踪像素周围最近的8个像素点,不含Vc的点,如式(8)所示:The currently tracked pixel is the last object that enters Vc , and Cc is a sequence composed of candidate pixels, and the candidate pixels are the nearest 8 pixels around the current tracking pixel, excluding Vc , as shown in the formula As shown in (8): Cc=N8(Vc(k))-Vc (8)C c = N 8 (V c (k)) - V c (8) 将当前的跟踪像素加入到Vc中,如式(9)所示:Add the current tracking pixel to Vc , as shown in formula (9): k:=k+1,Vc(k):=(x,y) (9)k:=k+1, V c (k):=(x,y) (9) 则置信度矩阵Cw更新为:Then the confidence matrix C w is updated as: Cw(x,y):=Cw(x,y)+1,(x,y):=(xc,yc) (10)C w (x,y):=C w (x,y)+1,(x,y):=(x c ,y c ) (10) 式(9)中所有参数值均小于T时,开始寻找下一个种子像素点(t:=t+1);When all parameter values are less than T in the formula (9), start to look for the next seed pixel point (t:=t+1); ④多尺度线性跟踪④Multi-scale linear tracking 按照一定尺度对所有种子点进行重复跟踪,尺度数由视网膜图像中待检测血管的宽度决定,若视网膜图像中血管有较大的可变性,则其对应的尺度数目也比较多;经过多次仿真实验,尺度W=3,5,7,9,11时比较恰当;Repeatedly track all seed points according to a certain scale. The number of scales is determined by the width of the blood vessels to be detected in the retinal image. If the blood vessels in the retinal image have greater variability, the number of corresponding scales is also relatively large; after multiple simulations For experiments, scales W=3, 5, 7, 9, 11 are more appropriate; ⑤视网膜血管的初始提取⑤ Initial extraction of retinal blood vessels 采用映射量化法对血管进行初始估计;最初的血管是由置信度矩阵中大于TC的像素点构建,TC值等于尺度W的值;Use the mapping quantification method to initially estimate the blood vessels; the initial blood vessels are constructed from pixels larger than T C in the confidence matrix, and the T C value is equal to the value of the scale W; 所述步骤三中,边界法测量血管管径具体过程,如下:In the third step, the specific process of measuring the vascular diameter by the boundary method is as follows: (1)血管测量图像区域选择(1) Selection of blood vessel measurement image area 从分割出来的视网膜血管图像中,选择感兴趣的区域截取血管子图像做边缘检测,然后对子图像的血管进行宽度测量,减少处理的时间;From the segmented retinal blood vessel image, select the region of interest to intercept the blood vessel sub-image for edge detection, and then measure the width of the blood vessel in the sub-image to reduce the processing time; (2)血管管径宽度的计算(2) Calculation of vessel diameter width 子图像中的血管方向尽量与水平方向平行,如果不是水平的,采用旋转角度的方法,使其尽量平行水平方向;采用最小距离法实现视网膜血管管径宽度的自动测量;The direction of the blood vessels in the sub-image should be parallel to the horizontal direction as much as possible. If it is not horizontal, use the method of rotation angle to make it parallel to the horizontal direction as much as possible; use the minimum distance method to realize the automatic measurement of the diameter and width of retinal blood vessels; 对垂直方向上下边缘点的坐标,利用两点间的距离公式计算,算出距离值作为血管宽度值,表示为:For the coordinates of the upper and lower edge points in the vertical direction, use the distance formula between two points to calculate, and calculate the distance value as the blood vessel width value, expressed as:
Figure FDA0004136028310000041
Figure FDA0004136028310000041
其中,wi是i列的宽度值,(xi,yi)和(xj,yj)分别是血管上下边缘的坐标;距离法具有适应范围广、稳定性好、精度高的优点;Among them, w i is the width value of column i, (x i , y i ) and (x j , y j ) are the coordinates of the upper and lower edges of blood vessels respectively; the distance method has the advantages of wide adaptability, good stability and high precision; (3)标尺定位及像素间距计算(3) Ruler positioning and pixel spacing calculation 为把以像素标定的血管管径转变为血管管径的实际大小,需测量像素间距,因此,必须解决在图像中对标尺定位;In order to convert the vascular caliber calibrated by pixels into the actual size of the vascular caliber, it is necessary to measure the pixel spacing, therefore, it is necessary to solve the positioning of the ruler in the image; 通过最小刻度值与相邻刻度线之间的像素个数计算出像素的物理长度;在与截取子图像同样大小的图像中设定标尺,尺度为10mm×10mm,对标尺图像进行边缘检测处理之后,得到的是二值图像,设标尺的像素值为1,背景的像素值为0;对二值化标尺图像从上到下遍历二值图像,计算其像素数目;Calculate the physical length of the pixel by the number of pixels between the minimum scale value and the adjacent scale line; set the scale in the image of the same size as the intercepted sub-image, the scale is 10mm×10mm, and perform edge detection processing on the scale image , what is obtained is a binary image, the pixel value of the scale is set to 1, and the pixel value of the background is 0; the binary image is traversed from top to bottom for the binary scale image, and the number of pixels is calculated; 设固定标尺尺寸为10mm,刻度间的像素数为Num,则像素的物理长度p由
Figure FDA0004136028310000051
决定,p的单位为mm/pixel;
Let the size of the fixed ruler be 10mm, and the number of pixels between the scales be Num, then the physical length p of the pixels is given by
Figure FDA0004136028310000051
Decision, the unit of p is mm/pixel;
(4)把血管管径的像素大小转换为物理大小(4) Convert the pixel size of the vessel diameter to the physical size 每个标记点测得像素与p相乘就知视网膜血管管径宽度的物理大小。The physical size of the diameter of the retinal blood vessels can be known by multiplying the pixel measured by each marker point with p.
2.一种实现权利要求1所述眼底图像视网膜血管管径自动量化方法的眼底图像视网膜血管管径自动量化系统,其特征在于,所述眼底图像视网膜血管管径自动量化系统包括:2. A fundus image retinal vessel diameter automatic quantification system that realizes the method for automatically quantifying the retinal vessel diameter of the fundus image of claim 1, wherein the automatic quantification system for the retinal vessel diameter of the fundus image comprises: 视盘检测模块,用于实现眼底图像视盘检测;The optic disc detection module is used to realize the optic disc detection of the fundus image; 图像预处理与分割模块,用于实现眼底图像去噪和对比度增强、视网膜血管分割与边缘检测;Image preprocessing and segmentation module, used to achieve fundus image denoising and contrast enhancement, retinal vessel segmentation and edge detection; 量化与应用模块,用于实现视网膜血管管径测量、临床早期预测及辅助诊断。The quantification and application module is used to realize retinal vessel diameter measurement, early clinical prediction and auxiliary diagnosis.
CN201910128419.8A 2019-02-21 2019-02-21 An automatic quantification method of retinal vessel diameter in fundus images Active CN109829942B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910128419.8A CN109829942B (en) 2019-02-21 2019-02-21 An automatic quantification method of retinal vessel diameter in fundus images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910128419.8A CN109829942B (en) 2019-02-21 2019-02-21 An automatic quantification method of retinal vessel diameter in fundus images

Publications (2)

Publication Number Publication Date
CN109829942A CN109829942A (en) 2019-05-31
CN109829942B true CN109829942B (en) 2023-04-28

Family

ID=66863968

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910128419.8A Active CN109829942B (en) 2019-02-21 2019-02-21 An automatic quantification method of retinal vessel diameter in fundus images

Country Status (1)

Country Link
CN (1) CN109829942B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110448267B (en) * 2019-09-06 2021-05-25 重庆贝奥新视野医疗设备有限公司 Multimode fundus dynamic imaging analysis system and method
CN112668360A (en) * 2019-10-15 2021-04-16 深圳市理邦精密仪器股份有限公司 Pupil measuring method and device, medical equipment and storage medium
CN111489353B (en) * 2020-05-07 2023-06-23 清华大学深圳国际研究生院 Fundus image fovea positioning method
CN112617789A (en) * 2020-07-28 2021-04-09 上海大学 Laser speckle blood flow imaging method and system
CN113643353B (en) * 2020-09-04 2024-02-06 深圳硅基智能科技有限公司 Measurement method for enhancing resolution of vascular caliber of fundus image
CN111840794B (en) * 2020-09-07 2024-05-10 复旦大学附属眼耳鼻喉科医院 Method and system for rapidly measuring implantation depth of cochlear implant electrode
CN112826442B (en) * 2020-12-31 2024-06-25 上海鹰瞳医疗科技有限公司 Psychological state identification method and equipment based on fundus image
CN113344895A (en) * 2021-06-23 2021-09-03 依未科技(北京)有限公司 High-precision fundus blood vessel diameter measuring method, device, medium and equipment
CN113724315B (en) * 2021-09-03 2024-04-02 上海海事大学 Fundus retina blood vessel width measuring method, electronic equipment and computer readable storage medium
CN114119579B (en) * 2021-10-08 2024-06-21 北京理工大学 Retinal image main blood vessel identification method based on blood vessel structure similarity
CN117952994B (en) * 2024-03-27 2024-06-21 北京智想创源科技有限公司 Cardiovascular CT image intelligent segmentation method
CN118340580A (en) * 2024-05-11 2024-07-16 梦石科技(北京)有限公司 Portable venipuncture operation system based on random walk and graph cut deformation model

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108986106A (en) * 2017-12-15 2018-12-11 浙江中医药大学 Retinal vessel automatic division method towards glaucoma clinical diagnosis

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1691714A4 (en) * 2003-11-25 2010-01-27 F D Cardio Ltd Stent positioning using inflation tube
US20050157939A1 (en) * 2004-01-16 2005-07-21 Mark Arsenault Processes, products and systems for enhancing images of blood vessels
JP5778579B2 (en) * 2008-10-14 2015-09-16 ライトラボ・イメージング・インコーポレーテッド Stent strut detection using optical coherence tomography and related methods for measurement and display
CN101984916B (en) * 2010-11-17 2012-10-31 哈尔滨工程大学 Measurement method of blood vessel diameter based on digital image processing technology
JP6358590B2 (en) * 2013-08-09 2018-07-18 富士通株式会社 Blood vessel data generation device, blood vessel data generation method, and blood vessel data generation program
US9757023B2 (en) * 2015-05-27 2017-09-12 The Regents Of The University Of Michigan Optic disc detection in retinal autofluorescence images
CN107292835B (en) * 2017-05-31 2020-03-13 瑞达昇医疗科技(大连)有限公司 Method and device for automatically vectorizing retinal blood vessels of fundus image
CN109166124B (en) * 2018-11-20 2021-12-14 中南大学 A Quantitative Method for Retinal Vascular Morphology Based on Connected Regions

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108986106A (en) * 2017-12-15 2018-12-11 浙江中医药大学 Retinal vessel automatic division method towards glaucoma clinical diagnosis

Also Published As

Publication number Publication date
CN109829942A (en) 2019-05-31

Similar Documents

Publication Publication Date Title
CN109829942B (en) An automatic quantification method of retinal vessel diameter in fundus images
WO2022063198A1 (en) Lung image processing method, apparatus and device
CN103810709B (en) Eye fundus image based on blood vessel projects method for registering images with SD-OCT
CN106056118B (en) A kind of identification method of counting for cell
WO2022007352A1 (en) Three-dimensional choroidal vessel imaging and quantitative analysis method and apparatus based on optical coherence tomography system
CN107644420B (en) Vascular image segmentation method and MRI system based on centerline extraction
CN104463140B (en) A kind of colored eye fundus image optic disk automatic positioning method
CN104091346B (en) Full-automatic CT image coronary artery calcification score calculating method
CN107798679B (en) Breast region segmentation and calcification detection method in mammography images
CN104143190B (en) The dividing method and system organized in CT images
CN104414636B (en) Cerebral microbleeds computer-aided detection system based on MRI
CN104616307B (en) A kind of lung CT image adhesion vascular type nodule detection methods
US20180025495A1 (en) Systems and methods of choroidal neovascularization detection using optical coherence tomography angiography
CN104794721B (en) A kind of quick optic disk localization method based on multiple dimensioned spot detection
WO2011022783A1 (en) Feature detection and measurement in retinal images
CN109816655B (en) Pulmonary nodule image feature detection method based on CT image
CN106157279A (en) Eye fundus image lesion detection method based on morphological segment
CN108257126A (en) The blood vessel detection and method for registering, equipment and application of three-dimensional retina OCT image
CN110706218B (en) Breast tumor positioning analysis method based on dynamic enhanced magnetic resonance imaging
Gao et al. Accurate lung segmentation for X-ray CT images
CN118115466A (en) Fundus pseudo focus detection method
CN106384343A (en) Morphological processing based hard exudation area detecting method
CN110060261A (en) A kind of blood vessel segmentation method based on Optical coherence tomography imaging system
CN113012127A (en) Cardiothoracic ratio measuring method based on chest medical image
CN106372593B (en) Optic disk area positioning method based on vascular convergence

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant