WO2018068196A1 - 一种血管脊线追踪方法及装置 - Google Patents

一种血管脊线追踪方法及装置 Download PDF

Info

Publication number
WO2018068196A1
WO2018068196A1 PCT/CN2016/101754 CN2016101754W WO2018068196A1 WO 2018068196 A1 WO2018068196 A1 WO 2018068196A1 CN 2016101754 W CN2016101754 W CN 2016101754W WO 2018068196 A1 WO2018068196 A1 WO 2018068196A1
Authority
WO
WIPO (PCT)
Prior art keywords
ridge
tracking
point
points
space
Prior art date
Application number
PCT/CN2016/101754
Other languages
English (en)
French (fr)
Inventor
周寿军
陆培
陈明扬
王澄
Original Assignee
中国科学院深圳先进技术研究院
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 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Priority to CN201680001076.3A priority Critical patent/CN106796725B/zh
Priority to PCT/CN2016/101754 priority patent/WO2018068196A1/zh
Publication of WO2018068196A1 publication Critical patent/WO2018068196A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular

Definitions

  • the present application belongs to the field of medical image processing, and in particular, to a blood vessel ridge tracking method and device.
  • vascular centerline is the key to vascular interventional path planning and surgical navigation.
  • Ridgeline tracking is a key method for extracting vascular centerline and thus has important clinical significance in cardio-cerebral vascular interventional surgery.
  • the existing ridge tracking method generally determines the initial seed point first, then detects the local extremum in the range of the fixed arc length around the seed point to determine the adjacent ridge point and update the ridge point detection direction, thus repeating the blood vessel. Extraction of the centerline.
  • the prior art method involves more iterative parameters and the algorithm implementation is more complicated.
  • the present invention provides a vascular ridge tracking method and apparatus for solving the problem that the ridge line tracking involves more iterative parameters and the algorithm implementation is more complicated in the prior art.
  • a technical solution of the present application is to provide a vascular ridge tracking method, including: performing global ridge detection on an angiographic image to determine a ridge point space;
  • Two adjacent ridge points are used as endpoints, and other ridge points on the tracking ridge line are sequentially tracked in two initial tracking directions, and the endpoints and the current tracking direction are continuously updated during the tracking process;
  • the ridge tracking process is repeated according to the updated ridge point space until the number of ridge points in the updated ridge point space is less than the first threshold.
  • vascular ridge tracking device including:
  • a ridge detection module for performing global ridge detection on an angiographic image to determine a ridge point space
  • An initial module configured to randomly select a ridge point as a tracking starting point in the ridge space, and determine two adjacent ridge points and two initial tracking directions of the tracking starting point on the tracking ridge line;
  • a tracking module for sequentially tracking two adjacent ridge points as endpoints, sequentially tracking other ridge points on the tracking ridge along two initial tracking directions, continuously updating the endpoints and tracking directions during the tracking process, and also for updating according to the The ridge point space repeats the ridge tracking process until the number of ridge points in the updated ridge point space is less than the first threshold end ridge line tracking;
  • a marking module for marking the tracked ridge line
  • the update module is used to delete the ridge points that have been traversed by the tracked ridge line and update the ridge point space.
  • the vascular ridge tracking method and device provided by the present application firstly perform global ridge detection on the angiographic image to determine the ridge point space; then randomly select a ridge point as the tracking starting point in the ridge point space to determine the tracking ridge line.
  • the ridge tracking is ended when the number is less than the first threshold.
  • the present application first determines the ridge point space, and performs ridge tracking in the ridge point space. After each ridge line is traced, the ridge point traversed by the ridge line is deleted, and the ridge line tracking process is repeated according to the updated ridge point space.
  • FIG. 1 is a flow chart of a vascular ridge tracking method according to an embodiment of the present application.
  • FIG. 2 is a flow chart of a method for determining two adjacent ridge points and an initial tracking direction according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of a process of determining two adjacent ridge points and an initial tracking direction according to an embodiment of the present application
  • FIG. 4 is a flow chart of a ridge line tracking process according to an embodiment of the present application.
  • FIG. 5 is a schematic diagram of a ridge line tracking process according to an embodiment of the present application.
  • FIG. 6 is a schematic view of a spiral tubular object according to an embodiment of the present application.
  • FIG. 7a-7c are schematic views of the ridge line tracking process of the spiral tubular target of FIG. 6;
  • FIG. 8 is a structural diagram of a blood vessel ridge tracking device according to an embodiment of the present application.
  • FIG. 1 is a schematic diagram of a vascular ridge tracking method according to an embodiment of the present application.
  • the ridge point space is first determined, and ridge line tracking is performed in the ridge point space. After each ridge line is tracked, the ridge point traversed by the ridge line is deleted, and the ridge line tracking process is repeated according to the updated ridge point space.
  • the method includes:
  • Step 101 Perform global ridge detection on the angiographic image to determine the ridge point space.
  • the ridge point of the blood vessel is a local extreme point on the angiographic image perpendicular to the direction of the blood vessel, and the ridge point space is a set of ridge points in the angiographic image, and the coordinates of each ridge point in the image are p i (x i , y i , z i ).
  • the existing method can be used to determine the ridge point, and the detection process of the ridge point in this application is not described again.
  • Step 102 randomly select a ridge point as a tracking starting point in the ridge point space, and determine two adjacent ridge points and two initial tracking directions of the tracking starting point on the tracking ridge line (the ridge line of the tracking starting point).
  • the direction of the line connecting the tracking starting point and the two adjacent ridge points is opposite, or the cosine of the angle between the two is close to -1.
  • Step 103 The two adjacent ridge points are used as the end points, and the other ridge points on the tracking ridge line are sequentially tracked in the two initial tracking directions, and the endpoints and the current tracking direction are continuously updated during the tracking process. Tracking the ridges in both directions simultaneously increases the ridge tracking speed.
  • Step 104 Mark the tracked ridge line, delete the ridge point traversed by the tracked ridge line, and update the ridge point space.
  • the marked ridge line is, for example, stored in the memory with the ridge point coordinates of the tracked ridge traversal, and the corresponding storage address is recorded.
  • Step 105 Repeat the ridge tracking process according to the updated ridge point space (including steps 102 to 104 above) until the number of ridge points in the updated ridge point space is less than the first threshold.
  • the first threshold may be set according to actual tracking requirements. Specifically, the first threshold is a constant of 3, 4, or 5.
  • the method further includes: drawing all the tracked ridge lines with unused colors to distinguish different ridge lines.
  • the determining process of the tracking starting point in step 102 is: first numbering the ridge points in the ridge point space, and generating a random integer N i (0) by using a random signal generator according to the total number N of ridge point spatial ridge points. ⁇ N i ⁇ N), and the serial number corresponding to the ridge point is used as the starting point p 0 (x 0 , y 0 , z 0 ) of the ridge tracking.
  • the process of determining the two adjacent ridge lines and the two initial tracking directions of the tracking starting point on the ridge line includes:
  • Step 201 Find a distance from any one of the ridge points in the ridge point space to the tracking starting point, and find a ridge point corresponding to the distance within the first predetermined range, and the ridge points constitute the adjacent ridge point space of the tracking starting point.
  • D i0 is the distance from any point i in the ridge point space to the tracking starting point, and the unit is pixel (pixel). Find all points of D i0 ⁇ (d 1 , d 2 ] as the neighboring ridge point set P neighbor of p 0 , where , d 1 , d 2 are the boundary values of the first predetermined range, and can be determined according to the tracking accuracy, generally d 1 is 0, and d 2 is 3.
  • Step 202 If the number of ridge points N neighbor in the adjacent ridge point space is greater than 1, calculate a direction vector of each ridge point in the space from the tracking starting point to the adjacent ridge point space, and determine that the vector dot product between the two of the direction vectors is the smallest.
  • Two direction vectors, the ridge points in the adjacent ridge point space corresponding to the two direction vectors are adjacent ridge points, and the directions corresponding to the two direction vectors are initial tracking directions.
  • Step 203 If the number of points in space o ridge the apex of N neighbor is 1 or 0, the current track is an isolated starting point p 0, p 0 deletes the current track at the starting point of the apex in space, selecting a new starting point of the track, Go to the next round of ridge tracking, that is, repeat steps 102 to 105 above.
  • p 0 is a tracking starting point
  • p 1 , p 2 , p 3 , and p 4 are neighboring ridge point sets P neighbor satisfying 0 ⁇ D i0 ⁇ 3, from p 0 to four.
  • the ridge points are used as the direction vector, and the normalized unit vector is obtained. The smallest point product is calculated.
  • p 1 and p 3 as a tracking starting point of two adjacent ridge line of the ridge where p 0, p 1 and p 0 p 0 point to point two directions
  • p 3 p 0 is the point where the center of the vessel
  • the initial tracking direction of the ridge tracking is performed online. As can be seen from Figure 3, with The angle between them is the largest, almost in a line.
  • step 103 when the foregoing step 103 is implemented, it is available.
  • i is the ith update in a ridge tracking process;
  • p -i and p i respectively represent the two endpoints in the ridge tracking process, corresponding to Figure 3,
  • two adjacent ridge points are used as end points, and the other ridge points on the tracking ridge line are sequentially tracked in two initial tracking directions, and the tracking process is continuously updated.
  • the two endpoints and the two tracking directions further include:
  • Step 401 For an end point in the tracking process, obtain a distance from any one of the ridge points in the ridge point space to the end point, and find a ridge point corresponding to the distance within the second predetermined range, and the ridge points constitute the candidate ridge point. space.
  • D ji is the distance from any point j to the endpoint i in the ridge point space, and finds all points of D ji ⁇ (d 3 , d 4 ] as the candidate ridge point space P next of p i , where d 3 , d 4 are
  • the boundary value of the second predetermined range may be determined according to the tracking accuracy.
  • the second predetermined range D ji is greater than the first predetermined range D i0 , preferably, d 3 is 0 and d 4 is 5.
  • Step 402 Calculate a candidate tracking direction according to the ridge point in the candidate ridge point space and the endpoint, and select a candidate ridge point that satisfies the following formula:
  • ⁇ is versus Angle of the For the current tracking direction
  • p i is the endpoint
  • p k is the kth candidate ridge point
  • P next is the candidate ridge point space. Tracking direction for the kth candidate, ie the direction of p i to p k .
  • p 0 is a tracking starting point
  • p i and p ⁇ i are end points
  • p i is taken as an example.
  • the selected candidate ridge point direction is the direction of p i pointing to p i+1
  • the short-distance internal curvature conversion on the center line of the blood vessel can be made small.
  • the above step 403 can ensure a smooth transition of the ridge tracking direction.
  • FIG. 6 is a three-dimensional simulation data tested by the present application, which is a spiral tubular target with a gradual aperture, in order to be closer to reality. An angiographic image in which Gaussian noise is superimposed.
  • FIGS. 7a to 7c After the spiral tubular target in FIGS. 7a to 7c is detected by the global ridge point, the operation result based on the ridge tracking method in the present application is performed in the ridge point space thereof, wherein FIG. 7a is a ridge point space, and FIG. 7b is an arrow.
  • the ridge tracking process is shown, and Figure 7c is the result of ridge tracking.
  • the ridge tracking method provided by the present application can better perform ridge tracking in the ridge point space of the tubular target to be traced, and draw the blood vessel center line.
  • the vascular ridge tracking method provided by the present application first determines the ridge point space, and performs ridge line tracking in the ridge point space. After each ridge line is traced, the ridge point traversed by the ridge line is deleted, according to the updated ridge point space.
  • the repeated ridge tracking process has the characteristics of less iterative parameters, small calculation amount and simple algorithm, and can quickly complete the ridge tracking of the blood vessel center line.
  • a vascular ridge tracking device is also provided in the embodiment of the present application, as described in the following embodiments. Since the principle of solving the problem of the device is similar to the vascular ridge tracing method, the implementation of the device can be referred to the implementation of the vascular ridge tracing method, and the repeated description will not be repeated.
  • FIG. 8 is a structural diagram of a blood vessel ridge tracking device according to an embodiment of the present application.
  • the device can be implemented in a smart terminal, such as a mobile phone, a tablet computer, or the like by a logic circuit, or can implement functions of various components by software in a functional module manner, and run on the smart terminal.
  • the device includes:
  • the ridge point detection module 801 is configured to perform global ridge detection on the angiographic image to determine the ridge point space.
  • the initial module 802 is configured to randomly select a ridge point as a tracking starting point in the ridge space, and determine two adjacent ridge points and two initial tracking directions of the tracking starting point on the tracking ridge line.
  • the tracking module 803 is configured to sequentially track the other ridge points on the tracking ridge along two initial tracking directions by using two adjacent ridge points as an endpoint, and continuously update the endpoint and the tracking direction during the tracking process;
  • the ridge point space repeats the ridge tracking process until the number of ridge points in the updated ridge point space is less than the first threshold.
  • a marking module 804 is used to mark the ridge line that has been tracked.
  • the update module 805 is configured to delete the ridge points traversed by the tracked ridge line and update the ridge point space.
  • an embodiment of the apparatus of the present application further includes a rendering module for plotting all of the tracked ridges in different colors.
  • the initial module 802 is specifically configured to: obtain a distance from any one of the ridge points in the ridge space to the tracking starting point, and find a ridge point corresponding to the distance within the first predetermined range, and the ridge points The adjacent ridge point space that constitutes the starting point of the tracking.
  • the direction vector of each ridge point in the space from the tracking starting point to the adjacent ridge point space is calculated, and two direction vectors having the smallest vector dot product between the two in the direction vector are determined.
  • the ridge points in the adjacent ridge point space corresponding to the two direction vectors are adjacent ridge points, and the directions corresponding to the two directions are the initial tracking directions.
  • the initial module 802 is further configured to: if the number of ridge points in the ridge point space is 1 or 0, delete the current tracking starting point, reselect a new tracking starting point, and enter the next round of ridge tracking.
  • the tracking module 803 is specifically configured to: for an endpoint in the tracking process, determine a distance from any one of the ridge points to the endpoint, and find a distance corresponding to the second predetermined range. A ridge point from which the candidate ridge point space is formed.
  • the candidate tracking direction is calculated according to the ridge point in the candidate ridge point space and the endpoint, and candidate ridge points satisfying the following formula are selected:
  • ⁇ is versus Angle of the For the current tracking direction
  • p i is the endpoint
  • p k is the kth candidate ridge point
  • P next is the candidate ridge point space. Tracking direction for the kth candidate, ie the direction of p i to p k .
  • the vascular ridge tracking device provided by the present application first determines a ridge point space, and performs ridge line tracking in the ridge point space. After each ridge line is traced, the ridge point traversed by the ridge line is deleted, according to the updated ridge point space.
  • the repeated ridge tracking process has the characteristics of less iterative parameters, small calculation amount and simple algorithm, and can quickly complete the ridge tracking of the blood vessel center line.
  • the embodiment of the present application further provides an electronic device, including a processor and a memory including a computer readable program, when the computer readable program is executed, causing the processor to execute the vascular ridge tracking method described in the above embodiments .
  • the embodiment of the present application further provides a computer readable program, wherein when the program is executed in an electronic device, the program causes the computer to execute the vascular ridge tracking method as described in the above embodiment in the electronic device.
  • the embodiment of the present application further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to execute the vascular ridge tracking method described in the above embodiments in the electronic device.
  • portions of the application can be implemented in hardware, software, firmware, or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals A discrete logic circuit of a circuit, an application specific integrated circuit with a suitable combination of logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), and the like.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

一种血管脊线追踪方法及装置，其中方法包括：对血管造影图像进行全局脊点探测，确定脊点空间（101）；在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向（102）；将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向（103）；标记已追踪的脊线，删除已追踪脊线所遍历过的脊点，更新脊点空间（104）；根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪（105）。该方法具有迭代参数少、计算量小、算法简单的特点，能够快速的完成血管中心线的脊线追踪。

Description

一种血管脊线追踪方法及装置 技术领域
本申请属于医学图像处理领域，特别涉及一种血管脊线追踪方法及装置。
背景技术
目前，心脑血管疾病已经严重威胁着人类的健康。随着CT血管造影、磁共振血管造影(MRA)等成像技术的发展，医学图像的后处理技术变得越来越重要。血管中心线的精确提取是血管介入路径规划和手术导航的关键，脊线追踪是一种关键的血管中心线提取方法，因而在心脑血管介入手术中具有重要的临床意义。
现有的脊线追踪方法一般是先确定初始种子点，然后在种子点为圆心，周围固定弧长范围内探测局部极值，以确定其邻近脊点并更新脊点探测方向，如此反复完成血管中心线的提取。现有技术的方法涉及到的迭代参数比较多，算法实现较为复杂。
发明内容
本申请提供一种血管脊线追踪方法及装置，用于解决现有技术中脊线追踪涉及迭代参数较多，算法实现较为复杂的问题。
为了解决上述技术问题，本申请的一技术方案为提供一种血管脊线追踪方法，包括：对血管造影图像进行全局脊点探测，确定脊点空间；
在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向；
将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向；
标记已追踪的脊线，删除已追踪脊线所遍历过的脊点，更新脊点空间；
根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪。
本申请另一技术方案为提供一种血管脊线追踪装置，包括：
脊点探测模块，用于对血管造影图像进行全局脊点探测，确定脊点空间；
初始模块，用于在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向；
追踪模块，用于将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及追踪方向；还用于根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪；
标记模块，用于标记已追踪的脊线；
更新模块，用于删除已追踪脊线所遍历过的脊点，更新脊点空间。
本申请提供的血管脊线追踪方法及装置，首先对血管造影图像进行全局脊点探测，确定脊点空间；接着在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向；将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向；标记已追踪的脊线，删除已追踪脊线所遍历过的脊点，更新脊点空间；根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪。本申请先确定脊点空间，在脊点空间内进行脊线追踪，每追踪完一条脊线后，删除该条脊线遍历过的脊点，根据更新的脊点空间重复脊线追踪过程，具有迭代参数少、计算量小、算法简单的特点，能够快速的完成血管中心线的脊线追踪。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例的血管脊线追踪方法的流程图；
图2为本申请实施例的确定两个邻近脊点及初始追踪方向方法的流程图；
图3为本申请具体实施例的确定两个邻近脊点及初始追踪方向过程的示意图；
图4为本申请实施例的脊线追踪过程的流程图；
图5为本申请实施例的脊线追踪过程的示意图；
图6为本申请一具体实施例的螺旋状的管状目标示意图；
图7a～图7c为图6螺旋管状目标进行脊线追踪过程示意图；
图8为本申请实施例的血管脊线追踪装置的结构图。
具体实施方式
为了使本申请的技术特点及效果更加明显，下面结合附图对本申请的技术方案做进一步说明，本申请也可有其他不同的具体实例来加以说明或实施，任何本领域技术人员在权利要求范围内做的等同变换均属于本申请的保护范畴。
如图1所示，图1为本申请实施例的血管脊线追踪方法的示意图。本实施例先确定脊点空间，在脊点空间内进行脊线追踪，每追踪完一条脊线后，删除该条脊线遍历过的脊点，根据更新的脊点空间重复脊线追踪过程，具有迭代参数少、计算量小、算法简单的特点，能够快速的完成血管中心线的脊线追踪。具体的，该方法包括：
步骤101：对血管造影图像进行全局脊点探测，确定脊点空间。
血管的脊点为血管造影图像上垂直于血管方向的局部极值点，脊点空间为血管造影图像中脊点的集合，每个脊点在图像中的坐标为pi(xi,yi,zi)。具体实施时，可采用现有方法确定脊点，本申请对脊点的探测过程不再赘述。
步骤102：在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线(追踪起点所在脊线)上该追踪起点的两个邻近脊点及两个初始追踪方向。
追踪起点和两个邻近脊点的连线矢量方向相反，亦或两者夹角的余弦值接近-1。
步骤103：将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向。两个方向同时追踪脊线，能够提高脊线追踪速度。
步骤104：标记已追踪的脊线，删除已追踪脊线所遍历过的脊点，更新脊点空间。
标记已追踪的脊线例如为，将已追踪脊线遍历的脊点坐标存储于存储器中，记录相应的存储地址。
步骤105：根据更新的脊点空间重复脊线追踪过程(包括上述步骤102至104)，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪。其中，第一阈值可根据实际追踪需求进行设定。具体的，如第一阈值为常数3、4或5。
进一步的，待结束脊线追踪后还包括：用不用的颜色绘制出所有已追踪的脊线，以便区分不同的脊线。
一实施例中，步骤102中追踪起点的确定过程为：先对脊点空间内的脊点进行编号，根据脊点空间脊点的总数N，利用随机信号发生器产生一个随机整数Ni(0<Ni<N)，并将该序号对应脊点作为脊线追踪的起点p0(x0,y0,z0)。
一实施例中，如图2所示，上述步骤102中，追踪起点选定后，确定追踪脊线上该追踪起点的两个邻近脊线及两个初始追踪方向的过程包括：
步骤201：求取脊点空间中任意一脊点到追踪起点的距离，找出距离在第一预定范围内对应的脊点，由该些脊点构成追踪起点的邻脊点空间。
定义pi(xi,yi,zi)为脊点空间中任意一点，p0(x0,y0,z0)为追踪起点，脊点空间中任意一脊点到追踪起点的距离计算公式为：
Figure PCTCN2016101754-appb-000001
Di0为脊点空间中任意一点i到追踪起点的距离，单位为像素(pixel)，找出Di0∈(d1,d2]的所有点作为p0的邻脊点集合Pneighbor，其中，d1,d2为第一预定范围的边界值，可根据追踪精度进行确定，一般d1为0，d2为3。
步骤202：若邻脊点空间中脊点个数Nneighbor大于1，则计算追踪起点到邻脊点空间中各脊点的方向向量，确定所述方向向量中两两之间向量点积最小的两个方向向量，该两个方向向量对应的邻脊点空间中的脊点为邻近脊点，该两个方向向量所对应的方向为初始追踪方向。
步骤203：若邻脊点空间中脊点个数Nneighbor为1或0，则当前追踪起点p0为一孤立点，在脊点空间中删除当前追踪起点p0，重新选择新的追踪起点，进入下一轮脊线追踪，即重复上述步骤102～步骤105。
一具体实施例中，如图3所示，p0为追踪起点，p1，p2，p3，p4为满足0<Di0≤3的邻脊点集合Pneighbor，由p0向四个脊点作方向向量，并求取其归一化的单位向量，经计算可得点积最小的为
Figure PCTCN2016101754-appb-000002
和
Figure PCTCN2016101754-appb-000003
所对应的单位向量，则p1和p3为追踪起点p0所在脊线上的两个邻近脊点，p0指向p1和p0指向p3的两个方向为点p0所在血管中心线上进行脊线追踪的初始追踪方向。由图3可以看出，
Figure PCTCN2016101754-appb-000004
和
Figure PCTCN2016101754-appb-000005
之间夹角最大，几乎在一条线上。
一实施例中，上述步骤103实施时，可用
Figure PCTCN2016101754-appb-000006
和
Figure PCTCN2016101754-appb-000007
分别表示脊线追踪过程中的两个追踪方向，i为一脊线追踪过程中的第i次更新；用p-i和pi分别表示脊线追踪过程中的两个端点，对应图3，端点及初始追踪方向可表示为p-1＝p1,p1＝p3,
Figure PCTCN2016101754-appb-000008
Figure PCTCN2016101754-appb-000009
一实施例中，如图4所示，上述步骤103中，将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新两个端点及两个追踪方向进一步包括：
步骤401：对于追踪过程中的一端点，求取脊点空间中任意一脊点到该端点的距离，找出距离在第二预定范围内对应的脊点，由该些脊点构成候选脊点空间。
定义pi(xi,yi,zi)为端点，pj(xj,yj,zj)为脊点空间中任意一点，脊点空间中任意一脊点到端点的距离计算公式为：
Figure PCTCN2016101754-appb-000010
Dji为脊点空间中任意一点j到端点i的距离，找出Dji∈(d3,d4]的所有点作为pi的候选脊点空间Pnext，其中，d3,d4为第二预定范围的边界值，可根据追踪精度进行确定，为了避免候选脊点空间里某条脊线上有个别断点，一般第二预定范围Dji大于第一预定范围Di0，优选的，d3为0，d4为5。
步骤402：根据候选脊点空间中的脊点及该端点计算得到候选追踪方向，筛选出满足如下公式的候选脊点：
Figure PCTCN2016101754-appb-000011
其中，θ为
Figure PCTCN2016101754-appb-000012
与
Figure PCTCN2016101754-appb-000013
的夹角，
Figure PCTCN2016101754-appb-000014
为当前追踪方向，
Figure PCTCN2016101754-appb-000015
为筛选出的候选追踪方向，pi为端点，pk为第k个候选脊点，Pnext为候选脊点空间，
Figure PCTCN2016101754-appb-000016
为第k个候选追踪方向，即pi至pk的方向。
一具体实施例中，如图5所示，p0为追踪起点，pi及p-i为端点，以pi为例，候选脊点空间共有4个候选脊点{A，B，C，D}，据此，可计算出4个候选追踪方向(由端点pi指向候选脊点A、B、C、D)，通过公式(3)，筛选出的候选脊点pi+1为C，筛选出的候选脊点方向为pi指向pi+1的方向
Figure PCTCN2016101754-appb-000017
步骤403：判断所述夹角θ是否小于第二阈值α，如α＝45°，若判断结果为是，则用筛选出的候选脊点pi+1更新该端点pi，即pi＝pi+1，筛选出的候选追踪方向
Figure PCTCN2016101754-appb-000018
更新当前追踪方向
Figure PCTCN2016101754-appb-000019
即
Figure PCTCN2016101754-appb-000020
继续追踪新的脊点；若判断结果为否，则该条追踪脊线不存在新的脊点，停止追踪新的脊点。
实施时，为了避免求
Figure PCTCN2016101754-appb-000021
与
Figure PCTCN2016101754-appb-000022
的夹角θ，还可判断
Figure PCTCN2016101754-appb-000023
是否成立。
本实施例上述步骤402能够使血管中心线上短距离内曲度变换较小。上述步骤403能保证脊线追踪方向的平滑过渡。
需要说的是，在该脊线上，另一端点p-i处沿着相反方向
Figure PCTCN2016101754-appb-000024
的追踪过程同上。当两个方向上均找不到满足条件的新的脊点时，该条血管中心线上的脊线追踪结束。
下面以一具体实施例说明本申请血管脊线追踪方法的效果，如图6所示，图6为本申请进行测试的三维仿真数据，为一孔径渐变的螺旋状的管状目标，为了更接近真实血管造影图像，该管状目标中叠加了高斯噪声。图7a～图7c中的螺旋状管状目标经过全局脊点探测后，在其脊点空间进行基于本申请中的脊线追踪方法的运行结果，其中，图7a为脊点空间，图7b用箭头表示了脊线追踪过程，图7c为脊线追踪的结果。由图7a～图7c可以看出，本申请提供的脊线追踪方法能够较好的在管状目标待追踪脊点空间内完成脊线追踪，绘制出血管中心线。
本申请提供的血管脊线追踪方法先确定脊点空间，在脊点空间内进行脊线追踪，每追踪完一条脊线后，删除该条脊线遍历过的脊点，根据更新的脊点空间重复脊线追踪过程，具有迭代参数少、计算量小、算法简单的特点，能够快速的完成血管中心线的脊线追踪。
基于同一发明构思，本申请实施例中还提供了一种血管脊线追踪装置，如下面的实施例所述。由于该装置解决问题的原理与血管脊线追踪方法相似，因此该装置的实施可以参见血管脊线追踪方法的实施，重复之处不再赘述。
如图8所示，图8为本申请实施例的血管脊线追踪装置的结构图。该装置可以通过逻辑电路实现运行于智能终端，例如手机、平板电脑等设备中，或者以功能模块的方式由软件实现各部件的功能，运行于所述智能终端上。具体的，该装置包括：
脊点探测模块801，用于对血管造影图像进行全局脊点探测，确定脊点空间。
初始模块802，用于在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向。
追踪模块803，用于将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及追踪方向；还用于根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪。
标记模块804，用于标记已追踪的脊线。
更新模块805，用于删除已追踪脊线所遍历过的脊点，更新脊点空间。
为了清楚看清追踪的脊线，本申请装置的一实施例中，还包括绘制模块，用于用不同的颜色绘制出所有已追踪的脊线。
一具体实施例中，所述初始模块802具体用于：求取脊点空间中任意一脊点到追踪起点的距离，找出距离在第一预定范围内对应的脊点，由该些脊点构成追踪起点的邻脊点空间。
若邻脊点空间中脊点个数大于1，则计算追踪起点到邻脊点空间中各脊点的方向向量，确定所述方向向量中两两之间向量点积最小的两个方向向量，该两个方向向量对应的邻脊点空间中的脊点为邻近脊点，该两个方向所对应的方向为初始追踪方向。
进一步的，所述初始模块802还用于：若脊点空间中脊点个数为1或0，则删除当前追踪起点，重新选择新的追踪起点，进入下一轮脊线追踪。
一具体实施例中，所述追踪模块803具体用于：对于追踪过程中的一端点，求取脊点空间中任意一脊点到该端点的距离，找出距离在第二预定范围内对应的脊点，由该些脊点构成候选脊点空间。
根据候选脊点空间中的脊点及该端点计算得到候选追踪方向，筛选出满足如下公式的候选脊点：
Figure PCTCN2016101754-appb-000025
其中，θ为
Figure PCTCN2016101754-appb-000026
与
Figure PCTCN2016101754-appb-000027
的夹角，
Figure PCTCN2016101754-appb-000028
为当前追踪方向，
Figure PCTCN2016101754-appb-000029
为筛选出的候选追踪方向，pi为端点，pk为第k个候选脊点，Pnext为候选脊点空间，
Figure PCTCN2016101754-appb-000030
为第k个候选追踪方向，即pi至pk的方向。
判断所述夹角θ是否小于第二阈值，若判断结果为是，则用筛选出的候选脊点更新该端点，筛选出的候选追踪方向更新当前追踪方向，继续追踪新的脊点；若判断结果为否，则该条追踪脊线不存在新的脊点，停止追踪新的脊点。
本申请提供的血管脊线追踪装置先确定脊点空间，在脊点空间内进行脊线追踪，每追踪完一条脊线后，删除该条脊线遍历过的脊点，根据更新的脊点空间重复脊线追踪过程，具有迭代参数少、计算量小、算法简单的特点，能够快速的完成血管中心线的脊线追踪。
本申请实施例还提供一种电子设备，包括处理器及包括计算机可读程序的存储器，所述计算机可读程序在被执行时使所述处理器执行上面实施例所述的血管脊线追踪方法。
本申请实施例还提供一种计算机可读程序，其中当在电子设备中执行所述程序时，所述程序使得计算机在所述电子设备中执行如上面实施例所述的血管脊线追踪方法。
本申请实施例还提供一种存储有计算机可读程序的存储介质，其中所述计算机可读程序使得计算机在电子设备中执行上面实施例所述的血管脊线追踪方法。
应当理解，本申请的各部分可以用硬件、软件、固件或者它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行***执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可以用本领域共知的下列技术中的任一项或者他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本申请是参照根据本申请实施例的方法、设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅用于说明本申请的技术方案，任何本领域普通技术人员均可在不违背本申请的精神及范畴下，对上述实施例进行修饰与改变。因此，本申请的权利保护范围应视权利要求范围为准。

Claims (10)

  1. 一种血管脊线追踪方法，其特征在于，包括：
    对血管造影图像进行全局脊点探测，确定脊点空间；
    在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向；
    将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向；
    标记已追踪的脊线，删除已追踪脊线所遍历过的脊点，更新脊点空间；
    根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪。
  2. 如权利要求1所述的血管脊线追踪方法，其特征在于，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向进一步包括：
    求取脊点空间中任意一脊点到追踪起点的距离，找出距离在第一预定范围内对应的脊点，由该些脊点构成追踪起点的邻脊点空间；
    若邻脊点空间中脊点个数大于1，则计算追踪起点到邻脊点空间中各脊点的方向向量，确定所述方向向量中两两之间向量点积最小的两个方向向量，该两个方向向量对应的邻脊点空间中的脊点为邻近脊点，该两个方向向量所对应的方向为初始追踪方向。
  3. 如权利要求2所述的血管脊线追踪方法，其特征在于，若邻脊点空间中脊点个数为1或0，则删除当前追踪起点，重新选择新的追踪起点，进入下一轮脊线追踪。
  4. 如权利要求1所述的血管脊线追踪方法，其特征在于，将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及当前追踪方向进一步包括：
    对于追踪过程中的一端点，求取脊点空间中任意一脊点到该端点的距离，找出距离在第二预定范围内对应的脊点，由该些脊点构成候选脊点空间；
    根据候选脊点空间中的脊点及该端点计算得到候选追踪方向，筛选出满足如下公式的候选脊点：
    Figure PCTCN2016101754-appb-100001
    其中，θ为
    Figure PCTCN2016101754-appb-100002
    与
    Figure PCTCN2016101754-appb-100003
    的夹角，
    Figure PCTCN2016101754-appb-100004
    为当前追踪方向，
    Figure PCTCN2016101754-appb-100005
    为筛选出的候选追踪方向，pi为端点，pk为第k个候选脊点，Pnext为候选脊点空间，
    Figure PCTCN2016101754-appb-100006
    为第k个候选追踪方向；
    判断所述夹角θ是否小于第二阈值，若判断结果为是，则用筛选出的候选脊点更新该端点，筛选出的候选追踪方向更新当前追踪方向，继续追踪新的脊点；若判断结果为否，则该条追踪脊线不存在新的脊点，停止追踪新的脊点。
  5. 如权利要求1所述的血管脊线追踪方法，其特征在于，还包括：用不同的颜色绘制出所有已追踪的脊线。
  6. 一种血管脊线追踪装置，其特征在于，包括：
    脊点探测模块，用于对血管造影图像进行全局脊点探测，确定脊点空间；
    初始模块，用于在脊点空间内随机选择一脊点作为追踪起点，确定追踪脊线上该追踪起点的两个邻近脊点及两个初始追踪方向；
    追踪模块，用于将两个邻近脊点作为端点，沿两个初始追踪方向分别顺序追踪所述追踪脊线上的其它脊点，追踪过程中不断更新端点及追踪方向；还用于根据更新的脊点空间重复脊线追踪过程，直至更新的脊点空间中的脊点个数小于第一阈值时结束脊线追踪；
    标记模块，用于标记已追踪的脊线；
    更新模块，用于删除已追踪脊线所遍历过的脊点，更新脊点空间。
  7. 如权利要求6所述的血管脊线追踪装置，其特征在于，所述初始模块具体用于：求取脊点空间中任意一脊点到追踪起点的距离，找出距离在第一预定范围内对应的脊点，由该些脊点构成追踪起点的邻脊点空间；
    若邻脊点空间中脊点个数大于1，则计算追踪起点到邻脊点空间中各脊点的方向向量，确定所述方向向量中两两之间向量点积最小的两个方向向量，该两个方向向量对应的邻脊点空间中的脊点为邻近脊点，该两个方向所对应的方向为初始追踪方向。
  8. 如权利要求7所述的血管脊线追踪装置，其特征在于，所述初始模块还用于：
    若邻脊点空间中脊点个数为1或0，则删除当前追踪起点，重新选择新的追踪起点，进入下一轮脊线追踪。
  9. 如权利要求6所述的血管脊线追踪装置，其特征在于，所述追踪模块具体用于：
    对于追踪过程中的一端点，求取脊点空间中任意一脊点到该端点的距离，找出距离在第二预定范围内对应的脊点，由该些脊点构成候选脊点空间；
    根据候选脊点空间中的脊点及该端点计算得到候选追踪方向，筛选出满足如下公式的候选脊点：
    Figure PCTCN2016101754-appb-100007
    其中，θ为
    Figure PCTCN2016101754-appb-100008
    与
    Figure PCTCN2016101754-appb-100009
    的夹角，
    Figure PCTCN2016101754-appb-100010
    为当前追踪方向，
    Figure PCTCN2016101754-appb-100011
    为筛选出的候选追踪方向，pi为端点，pk为第k个候选脊点，Pnext为候选脊点空间，
    Figure PCTCN2016101754-appb-100012
    为第k个候选追踪方向；
    判断所述夹角θ是否小于第二阈值，若判断结果为是，则用筛选出的候选脊点更新该端点，筛选出的候选追踪方向更新当前追踪方向，继续追踪新的脊点；若判断结果为否，则该条追踪脊线不存在新的脊点，停止追踪新的脊点。
  10. 如权利要求6所述的血管脊线追踪装置，其特征在于，还包括绘制模块，用于用不同的颜色绘制出所有已追踪的脊线。
PCT/CN2016/101754 2016-10-11 2016-10-11 一种血管脊线追踪方法及装置 WO2018068196A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201680001076.3A CN106796725B (zh) 2016-10-11 2016-10-11 一种血管脊线追踪方法及装置
PCT/CN2016/101754 WO2018068196A1 (zh) 2016-10-11 2016-10-11 一种血管脊线追踪方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/101754 WO2018068196A1 (zh) 2016-10-11 2016-10-11 一种血管脊线追踪方法及装置

Publications (1)

Publication Number Publication Date
WO2018068196A1 true WO2018068196A1 (zh) 2018-04-19

Family

ID=58952251

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/101754 WO2018068196A1 (zh) 2016-10-11 2016-10-11 一种血管脊线追踪方法及装置

Country Status (2)

Country Link
CN (1) CN106796725B (zh)
WO (1) WO2018068196A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107392891B (zh) * 2017-06-28 2020-03-17 深圳先进技术研究院 血管树提取方法、装置、设备及存储介质
CN107977666B (zh) * 2017-12-08 2020-04-21 深圳先进技术研究院 目标轮廓提取方法、装置、设备及存储介质
CN111640124B (zh) * 2020-05-25 2023-06-02 浙江同花顺智能科技有限公司 一种血管提取方法、装置、设备及存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101551862A (zh) * 2009-05-13 2009-10-07 西安电子科技大学 基于边界距离场的血管中心路径提取方法
US20090278846A1 (en) * 2008-05-09 2009-11-12 Siemens Corporate Research, Inc. System and method for geometric modeling of tubular structures
US20100014739A1 (en) * 2007-06-14 2010-01-21 Siemens Corporate Research, Inc. System and method for segmentation of mr flow data using fluid dynamics and tracking
CN101923713A (zh) * 2010-08-04 2010-12-22 中国科学院自动化研究所 一种提取冠状动脉血管中心线的方法
CN102819823A (zh) * 2012-01-12 2012-12-12 北京理工大学 一种从造影图像中全自动跟踪提取血管的方法
CN103324934A (zh) * 2013-06-19 2013-09-25 北京理工大学 基于平行结构检测与聚类的血管中心线自动提取方法
CN104240220A (zh) * 2013-06-17 2014-12-24 北京三星通信技术研究有限公司 用于基于图像分割血管的设备和方法
CN104282009A (zh) * 2013-07-02 2015-01-14 上海联影医疗科技有限公司 一种冠脉的提取方法
CN104318557A (zh) * 2014-10-17 2015-01-28 重庆大学 血管骨架线重构及精确管径计算方法

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100014739A1 (en) * 2007-06-14 2010-01-21 Siemens Corporate Research, Inc. System and method for segmentation of mr flow data using fluid dynamics and tracking
US20090278846A1 (en) * 2008-05-09 2009-11-12 Siemens Corporate Research, Inc. System and method for geometric modeling of tubular structures
CN101551862A (zh) * 2009-05-13 2009-10-07 西安电子科技大学 基于边界距离场的血管中心路径提取方法
CN101923713A (zh) * 2010-08-04 2010-12-22 中国科学院自动化研究所 一种提取冠状动脉血管中心线的方法
CN102819823A (zh) * 2012-01-12 2012-12-12 北京理工大学 一种从造影图像中全自动跟踪提取血管的方法
CN104240220A (zh) * 2013-06-17 2014-12-24 北京三星通信技术研究有限公司 用于基于图像分割血管的设备和方法
CN103324934A (zh) * 2013-06-19 2013-09-25 北京理工大学 基于平行结构检测与聚类的血管中心线自动提取方法
CN104282009A (zh) * 2013-07-02 2015-01-14 上海联影医疗科技有限公司 一种冠脉的提取方法
CN104318557A (zh) * 2014-10-17 2015-01-28 重庆大学 血管骨架线重构及精确管径计算方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
XIAO, RUOXIU ET AL.: "Automatic Centerline Extraction Method for X-Ray Angiographic Image", JOURNAL OF COMPUTER-AIDED DESIGN & COMPUTER GRAPHICS, vol. 25, no. 3, 31 March 2013 (2013-03-31), pages 363 - 370, ISSN: 1003-9775 *

Also Published As

Publication number Publication date
CN106796725B (zh) 2020-06-05
CN106796725A (zh) 2017-05-31

Similar Documents

Publication Publication Date Title
Estrada et al. Tree topology estimation
US10255673B2 (en) Apparatus and method for detecting object in image, and apparatus and method for computer-aided diagnosis
JP2009072576A (ja) 血管造影画像の定量的分岐解析のための方法、装置およびコンピュータプログラム
CN112085033B (zh) 一种模板匹配方法、装置、电子设备及存储介质
WO2018068196A1 (zh) 一种血管脊线追踪方法及装置
CN110084824B (zh) 基于对称水平集的舌体图像分割方法、***、设备及介质
CN113223078B (zh) 标志点的匹配方法、装置、计算机设备和存储介质
CN112712546A (zh) 一种基于孪生神经网络的目标跟踪方法
WO2020093566A1 (zh) 脑出血图像处理方法、装置、计算机设备及存储介质
CN110544255B (zh) 面向3d打印的三角网格孔洞的分割方法及***
CN113538471B (zh) 斑块的分割方法、装置、计算机设备和存储介质
CN115965750B (zh) 血管重建方法、装置、计算机设备和可读存储介质
CN107622530A (zh) 一种高效鲁棒的三角网切割方法
CN111932552B (zh) 一种主动脉建模的方法及装置
JP6293619B2 (ja) 画像処理方法および装置並びにプログラム
CN113706473A (zh) 超声图像中病灶区域的长短轴确定方法和超声设备
Zampokas et al. Real-time 3D reconstruction in minimally invasive surgery with quasi-dense matching
CN107392891B (zh) 血管树提取方法、装置、设备及存储介质
CN114565559A (zh) 一种颅内动脉瘤形态学参数半自动测量方法
CN106537451B (zh) 一种基于图像梯度矢量流场的血管脊点提取方法及装置
CN113633375A (zh) 一种虚拟支气管镜的构建方法
Shen et al. Automatic cerebral artery system labeling using registration and key points tracking
Cui et al. Fast marching and Runge–Kutta based method for centreline extraction of right coronary artery in human patients
Lu et al. Image registration based on criteria of feature point pair mutual information
CN107392999A (zh) 用于确定血管子分支的血管类型的方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16918840

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22.08.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16918840

Country of ref document: EP

Kind code of ref document: A1