WO2022127783A1 - 一种基于血管分支配准的冠状动脉三维重建方法及系统 - Google Patents

一种基于血管分支配准的冠状动脉三维重建方法及系统 Download PDF

Info

Publication number
WO2022127783A1
WO2022127783A1 PCT/CN2021/137892 CN2021137892W WO2022127783A1 WO 2022127783 A1 WO2022127783 A1 WO 2022127783A1 CN 2021137892 W CN2021137892 W CN 2021137892W WO 2022127783 A1 WO2022127783 A1 WO 2022127783A1
Authority
WO
WIPO (PCT)
Prior art keywords
coronary
dimensional
image
coronary angiography
dimensional reconstruction
Prior art date
Application number
PCT/CN2021/137892
Other languages
English (en)
French (fr)
Inventor
刘治
曹艳坤
Original Assignee
山东大学
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 山东大学 filed Critical 山东大学
Priority to US17/911,292 priority Critical patent/US11842439B2/en
Publication of WO2022127783A1 publication Critical patent/WO2022127783A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/41—Medical
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images

Definitions

  • the invention belongs to the field of three-dimensional modeling, and in particular relates to a method and system for three-dimensional reconstruction of coronary arteries based on blood vessel classification criteria.
  • Coronary heart disease is a major disease that seriously endangers the health of the world and Chinese people.
  • CAG coronary angiography
  • IVUS intravascular ultrasound
  • CAG as the current "gold standard” for the diagnosis of coronary heart disease, can determine the presence or absence of coronary stenosis, the location and degree of stenosis, etc.
  • IVUS uses a cardiac catheter to introduce an ultrasound probe into the blood vessel cavity for detection, and can obtain the lumen area of the blood vessel. , fine anatomical information such as wall thickness and plaque in blood vessels.
  • CAG cannot provide structural information and lesion degree of the vessel wall.
  • the current three-dimensional reconstruction methods of intravascular ultrasound images only rely on IVUS information, and do not fuse CAG information, so the spatial location of the coronary artery where the lesion is located cannot be obtained.
  • Some coronary three-dimensional reconstruction methods fuse CAG and IVUS for three-dimensional reconstruction, but The blood vessel branch information is not referenced during fusion, and it is necessary to manually determine the starting point.
  • the inventors found that in clinical practice, many patients underwent IVUS first and then CAG, or CAG first and then angiography. It is impossible to determine whether the reference point of IVUS is consistent with that of CAG. registration caused great difficulties.
  • the present invention provides a method and system for three-dimensional reconstruction of coronary artery based on blood vessel classification criteria, which utilizes the method of automatic matching of blood vessel branches to fuse CAG and IVUS images and create a three-dimensional reconstruction method.
  • Reconstruction on the premise of improving speed and accuracy, is more conducive to the intuitive judgment of doctors, and is of great significance to the auxiliary diagnosis of diseases.
  • a first aspect of the present invention provides a method for three-dimensional reconstruction of coronary artery based on vascular classification criteria, comprising:
  • the segmented intravascular ultrasound and endocardium images are registered to the three-dimensional centerline of the coronary angiography to perform three-dimensional reconstruction of the coronary arteries.
  • a second aspect of the present invention provides a three-dimensional reconstruction system for coronary artery based on vascular classification criteria, comprising:
  • an image processing module which is used for classifying bifurcated vessels and normal vessels in intravascular ultrasound images and segmenting the inner and outer membranes respectively; extracting three-dimensional centerlines in coronary angiography images;
  • a keypoint automatic registration module which is used to locate vessel branches and automatically match keypoints of coronary angiography images
  • the three-dimensional reconstruction module is used for registering the segmented intravascular ultrasound inner and outer membrane images to the three-dimensional centerline of the coronary angiography according to the key points of the coronary angiography image, so as to perform three-dimensional reconstruction of the coronary arteries.
  • a third aspect of the present invention provides a computer-readable storage medium.
  • a fourth aspect of the present invention provides a computer apparatus.
  • a computer device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, when the processor executes the program, the three-dimensional coronary artery aligning based on the blood vessel division as described above is realized Steps in the reconstruction method.
  • the internal bifurcated blood vessels and normal blood vessels in the IVUS (intravascular ultrasound) image are classified, and then segmented respectively, and the centerline of the CAG (coronary angiography) image is extracted.
  • the centerline of the image and the CAG image is registered, and the CAG image and the IVUS image are fused and 3D reconstructed by the method of automatic blood vessel branch matching.
  • the auxiliary diagnosis is of great significance.
  • FIG. 1 is a flowchart of a method for three-dimensional reconstruction of coronary artery based on vascular classification criteria according to an embodiment of the present invention
  • Fig. 2 is the IVUS classification and segmentation frame diagram based on the multi-task network of the embodiment of the present invention
  • FIG. 3 is a flowchart of a method for automatic registration of key points according to an embodiment of the present invention.
  • the method for three-dimensional reconstruction of coronary artery based on vascular classification criteria in this embodiment includes:
  • S101 Classify the bifurcated blood vessels and normal blood vessels in the intravascular ultrasound image and segment the inner and outer membranes respectively; extract the three-dimensional centerline in the coronary angiography image.
  • intravascular ultrasound images are classified and segmented by a multi-task deep network.
  • this embodiment mainly has two functions, one is to classify the branch blood vessels and normal blood vessels of the IVUS image, and output the number of frames where the branch blood vessels are located and the total number of consecutive frames; the other is to classify the branch blood vessels and the normal blood vessels.
  • the inner and outer membranes of normal blood vessels are segmented, and the segmentation results are output. Furthermore, the two features constrain each other to improve the accuracy of classification and segmentation.
  • the two-dimensional centerline in the coronary angiography image is first extracted, and then the three-dimensional centerline is extracted according to two coronary angiography planes.
  • the method for extracting the two-dimensional centerline in the coronary angiography image includes, but is not limited to, a tracking-based method or a dynamic programming method.
  • the three-dimensional centerline is extracted according to the two imaging planes, including but not limited to various coordinate changes using spatial geometric relationships to obtain the three-dimensional centerline.
  • S102 Locate the branch of the blood vessel and automatically match the key points of the coronary angiography image.
  • the step of automatic registration of key points includes two parts: branch information extraction and identification and matching.
  • the first branch The length information is compared with the length of each branch in the coronary angiography image.
  • the distance between the first branch and the second branch in the intravascular ultrasound image is used to find out whether the next branch of the coronary angiography image matches, and if so, continue to search for the second branch in the intravascular ultrasound image that matches the second branch in the intravascular ultrasound image.
  • the matching rate here is inversely proportional to the length error, that is, the smaller the error of the vessel branch length information in the intravascular ultrasound image and the branch length in the coronary angiography image, the greater the matching rate.
  • the matching rate reaches the maximum.
  • the blood vessel branch information mainly includes the starting frame number of the branch and the total number of consecutive frames.
  • the frame rate and retraction rate of IVUS are known. According to this, the diameter of the IVUS 1 of the branch blood vessel can be calculated.
  • the calculation formula is as follows:
  • S103 Register the segmented intravascular ultrasound inner and outer membrane images on the three-dimensional centerline of the coronary angiography according to the key points of the coronary angiography image, and perform three-dimensional reconstruction of the coronary arteries.
  • positioning and orientation analysis is performed according to the three-dimensional centerline of coronary angiography images and the segmented intravascular ultrasound image sequence, so as to complete the fusion of coronary angiography images and intravascular ultrasound images.
  • the three-dimensional reconstruction step includes three-dimensional centerline reconstruction and surface reconstruction.
  • Three-dimensional centerline reconstruction includes, but is not limited to, three-dimensional centerline reconstruction using the principle of biplane perspective combined with epipolar constraints.
  • Surface reconstruction includes, but is not limited to, the use of the Frenet-Serret frame for IVUS orientation and surface fitting.
  • the algorithm for obtaining the coronary vessel model by fusion includes, but is not limited to, methods such as surface reconstruction, volume reconstruction VTK, and the like.
  • the internal bifurcated blood vessels and normal blood vessels in the IVUS (intravascular ultrasound) image are first classified, and then segmented respectively, and the centerline of the CAG (coronary angiography) image is extracted. , register the center line of the IVUS image and the CAG image, and use the method of automatic blood vessel branch matching to fuse the CAG image and the IVUS image and reconstruct it in three dimensions.
  • the centerline of the IVUS image and the CAG image register the center line of the IVUS image and the CAG image, and use the method of automatic blood vessel branch matching to fuse the CAG image and the IVUS image and reconstruct it in three dimensions.
  • it is more helpful for doctors to make intuitive judgments. is of great significance for the auxiliary diagnosis of diseases.
  • this embodiment provides a three-dimensional reconstruction system for coronary artery based on blood vessel classification alignment, which includes:
  • an image processing module which is used for classifying bifurcated blood vessels and normal blood vessels in intravascular ultrasound images and segmenting the inner and outer membranes respectively; extracting three-dimensional centerlines in coronary angiography images;
  • a keypoint automatic registration module which is used to locate vessel branches and automatically match keypoints of coronary angiography images
  • the three-dimensional reconstruction model is used for registering the segmented intravascular ultrasound inner and outer membrane images to the three-dimensional centerline of the coronary angiography according to the key points of the coronary angiography image, so as to perform three-dimensional reconstruction of the coronary arteries.
  • the modules in the three-dimensional coronary reconstruction system based on the vascular classification criteria in this embodiment correspond to the steps in the three-dimensional coronary reconstruction method based on the vascular classification criteria in the first embodiment, and the specific implementation process is the same. No longer exhaustive.
  • the image acquisition module 1 is used for both the intravascular ultrasound image and the coronary angiography image to acquire images.
  • the image acquisition module includes an IVUS image acquisition module and a CAG image acquisition module, wherein the IVUS image acquisition module is used to acquire IVUS image information, and the CAG image acquisition module is used to acquire CAG image information.
  • IVUS images are intravascular ultrasound images; CAG images are coronary angiography images.
  • This embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps in the three-dimensional reconstruction method for coronary artery based on the blood vessel classification standard described in the first embodiment above .
  • This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, when the processor executes the program, the computer program based on the first embodiment described above is implemented.
  • Vascular segmentation governs steps in a method for quasi-coronary three-dimensional reconstruction.
  • embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, optical storage, and the like.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements the functions specified in the flow or flows of the flowcharts and/or the block or blocks of the block diagrams.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM) or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Graphics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

本发明属于三维建模领域，提供了一种基于血管分支配准的冠状动脉三维重建方法及系统。其中，基于血管分支配准的冠状动脉三维重建方法包括将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；定位血管分支并自动匹配冠状动脉造影图像的关键点；根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。其利用血管分支自动匹配的方法对冠状动脉造影图像与血管内超声图像进行融合并三维重建，在提高速度和精准度的前提下，更有助于医生的直观判断，对于疾病的辅助诊断有着重大意义。

Description

一种基于血管分支配准的冠状动脉三维重建方法及系统 技术领域
本发明属于三维建模领域，尤其涉及一种基于血管分支配准的冠状动脉三维重建方法及系统。
背景技术
本部分的陈述仅仅是提供了与本发明相关的背景技术信息，不必然构成在先技术。
冠心病(CHD)是严重危害世界及国人健康的重大疾病。目前患者如果被诊断为CHD，冠状动脉造影(CAG)和血管内超声(IVUS)是最常用于诊断和治疗CHD的方式。其中，CAG作为目前冠心病诊断的“金标准”，可以明确冠状动脉有无狭窄、狭窄的部位及程度等，IVUS是利用心导管将超声探头导入血管腔内进行探测，可以得到血管的腔面积、壁厚和血管的斑块等微细解剖信息。但是CAG无法提供血管壁的结构信息和病变程度。由于目前导管技术的限制，IVUS超声导管还不能顺利通过严重病变的部位，通过IVUS也无法获得病变所在冠状动脉的空间位置。融合CAG与IVUS的信息，将两种成像方式的优点结合起来将大大提高冠心病的诊断和治疗的效率。基于CAG与IVUS的三维血管重建可以对各种心血管疾病的组织表征进行准确的评估和诊断，从而获得最佳的治疗选择。这种三维重建的方式可以监测和研究动脉粥样硬化斑块的动态发展和进展，从而最小化或省略血管造影在临床治疗期间用于临床中导航和手术，减少手术时间和造影剂的使用。
目前的血管内超声图像三维重建方法只依赖于IVUS信息，并未融合CAG信息，无法获得病变所在冠状动脉的空间位置；而且有的冠状动脉三维重建方法虽然将CAG与IVUS融合进行三维重建，但是融合时并未参考血管分支信息，需要人工手动的去确定起始点。发明人发现，在临床中，很多病人都是先做的IVUS后来又做的CAG，或者先做的CAG又做的动脉造影，无法确定IVUS的基准点与CAG的是否一致，对两者之间的配准造成很大的困难。
发明内容
为了解决上述背景技术中存在的至少一项技术问题，本发明提供一种基于血管分支配准的冠状动脉三维重建方法及系统，其利用血管分支自动匹配的方法对CAG与IVUS图像进行融合并三维重建，在提高速度和精准度的前提下，更有助于医生的直观判断，对于疾病的辅助诊断有着重大意义。
为了实现上述目的，本发明采用如下技术方案：
本发明的第一个方面提供一种基于血管分支配准的冠状动脉三维重建方法，其包括：
将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；
定位血管分支并自动匹配冠状动脉造影图像的关键点；
根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
本发明的第二个方面提供一种基于血管分支配准的冠状动脉三维重建系统，其包括：
图像处理模块，其用于将血管内超声图像中的分叉血管和正常血管分类并 分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；
关键点自动配准模块，其用于定位血管分支并自动匹配冠状动脉造影图像的关键点；
三维重建模块，其用于根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
本发明的第三个方面提供一种计算机可读存储介质。
一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上述所述的基于血管分支配准的冠状动脉三维重建方法中的步骤。
本发明的第四个方面提供一种计算机设备。
一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上述所述的基于血管分支配准的冠状动脉三维重建方法中的步骤。
与现有技术相比，本发明的有益效果是：
首先将IVUS(血管内超声)图像中内分叉血管和正常血管进行分类，然后分别对其进行分割，对CAG(冠状动脉造影)图像进行中心线提取，根据得到的血管的分支情况，将IVUS图像与CAG图像的中心线配准，利用血管分支自动匹配的方法对CAG图像与IVUS图像进行融合并三维重建，在提高速度和精准度的前提下，更有助于医生的直观判断，对于疾病的辅助诊断有着重大意义。
本发明附加方面的优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
附图说明
构成本发明的一部分的说明书附图用来提供对本发明的进一步理解，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。
图1是本发明实施例的基于血管分支配准的冠状动脉三维重建方法流程图；
图2是本发明实施例的基于多任务网络的IVUS分类与分割框架图；
图3是本发明实施例的关键点自动配准的方法流程图。
具体实施方式
下面结合附图与实施例对本发明作进一步说明。
应该指出，以下详细说明都是例示性的，旨在对本发明提供进一步的说明。除非另有指明，本文使用的所有技术和科学术语具有与本发明所属技术领域的普通技术人员通常理解的相同含义。
需要注意的是，这里所使用的术语仅是为了描述具体实施方式，而非意图限制根据本发明的示例性实施方式。如在这里所使用的，除非上下文另外明确指出，否则单数形式也意图包括复数形式，此外，还应当理解的是，当在本说明书中使用术语“包含”和/或“包括”时，其指明存在特征、步骤、操作、器件、组件和/或它们的组合。
实施例一
参照图1，本实施例的基于血管分支配准的冠状动脉三维重建方法，其包括：
S101：将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线。
在具体实施中，采集血管内超声图像和冠状动脉造影图像之后，对血管内超声图像和冠状动脉造影图像分别进行相应处理。
在本实施例中，通过多任务深度网络对血管内超声图像进行分类和分割。
如图2所示，本实施例的主要有两个功能，一个是对IVUS图像的分支血管和正常血管进行分类，并输出分支血管所在的帧数以及连续总帧数；一个是对分支血管和正常血管的内外膜进行分割，并输出分割结果。此外，两个功能互相约束，以提高分类和分割的精度。
在具体实施中，在提取冠状动脉造影图像中的三维中心线的过程中，首先提取冠状动脉造影图像中的二维中心线，再根据两个冠状动脉造影平面提取三维中心线。
此处需要说明的是，提取冠状动脉造影图像中的二维中心线的方法包括但不限于基于跟踪方法或动态规划方法。
具体地，根据两个造影平面提取三维的中心线，包括但不限于各种利用空间几何关系进行坐标变化从而得到三维中心线。
S102：定位血管分支并自动匹配冠状动脉造影图像的关键点。
在该步骤中，关键点自动配准的步骤包括分支信息提取和识别匹配两部分。
具体地，在将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上的过程中，根据血管内超声图像的分类和分割得到的血管分支信息，然后将第一个分支的长度信息，与冠状动脉造影图像中的各个分支长度进行对比查找。当匹配率达到最大时，以血管内超声图像中第一个分支与第二个的距离查找冠状动脉造影图像的下一个分支是否匹配，若是匹配则继续查找血管内超声图像中第二个分支与第三个分支是否匹配，若是没有则返回上一步选择第二匹配的分支继续查找，以此类推，直至所有血管内超声图像与冠状动脉造影图像中所有得分支全部匹配上，实现关键点自动配准，如图3所示。
其中，此处的匹配率与长度误差呈反比，也就是，血管内超声图像的血管 分支长度信息与冠状动脉造影图像中的分支长度误差越小，匹配率越大。当血管内超声图像的血管分支长度信息与冠状动脉造影图像中的分支长度相等时，匹配率达到最大。
血管分支信息主要包括分支的起始帧数以及连续帧数的总和，IVUS的帧速率和回撤速率已知，根据此可计算出分支血管口IVUS l的直径大小，计算公式如下所示：
Figure PCTCN2021137892-appb-000001
S103：根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
具体地，在冠状动脉的三维重建的过程中，根据冠状动脉造影图像的三维中心线和分割好的血管内超声图像序列进行定位定向分析，从而完成冠状动脉造影图像和血管内超声图像的融合而获得冠状动脉血管模型。
其中，三维重建步骤包括三维中心线重建以及表面重建。三维中心线重建包括但不限于使用双平面透视原理结合极线约束进行三维中心线重建。表面重建包括但不限于使用Frenet-Serret标架进行IVUS的方向定位，并进行表面拟合。
此处可以理解的是，融合获得冠状动脉血管模型的算法包括但不限于面重建、体重建VTK等方法。
本实施例首先将IVUS(血管内超声)图像中内分叉血管和正常血管进行分类，然后分别对其进行分割，对CAG(冠状动脉造影)图像进行中心线提取，根据得到的血管的分支情况，将IVUS图像与CAG图像的中心线配准，利用血管分支自动匹配的方法对CAG图像与IVUS图像进行融合并三维重建，在提高速度和精准度的前提下，更有助于医生的直观判断，对于疾病的辅助诊断有着 重大意义。
实施例二
参照图1，本实施例提供了一种基于血管分支配准的冠状动脉三维重建系统，其包括：
图像处理模块，其用于将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；
关键点自动配准模块，其用于定位血管分支并自动匹配冠状动脉造影图像的关键点；
三维重建模，其用于根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
本实施例的基于血管分支配准的冠状动脉三维重建系统中各个模块与实施例一中的基于血管分支配准的冠状动脉三维重建方法中的各个步骤一一对应，其具体实施过程相同，此处不再累述。
在具体实施中，血管内超声图像和冠状动脉造影图像均采用图像采集模块1实现图像的采集。其中，图像采集模块包括IVUS图像采集模块和CAG图像采集模块，其中，IVUS图像采集模块用来采集IVUS图像信息，CAG图像采集模块用来采集CAG图像信息。其中，IVUS图像为血管内超声图像；CAG图像为冠状动脉造影图像。
实施例三
本实施例提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上述实施例一所述的基于血管分支配准的冠状动脉三 维重建方法中的步骤。
实施例四
本实施例提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上述实施例一所述的基于血管分支配准的冠状动脉三维重建方法中的步骤。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用硬件实施例、软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、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。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random AccessMemory，RAM)等。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种基于血管分支配准的冠状动脉三维重建方法，其特征在于，包括：
    将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；
    定位血管分支并自动匹配冠状动脉造影图像的关键点；
    根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
  2. 如权利要求1所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，通过多任务深度网络对血管内超声图像进行分类和分割。
  3. 如权利要求1所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，在提取冠状动脉造影图像中的三维中心线的过程中，首先提取冠状动脉造影图像中的二维中心线，再根据两个冠状动脉造影平面提取三维中心线。
  4. 如权利要求3所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，基于跟踪方法或动态规划方法提取冠状动脉造影图像中的二维中心线。
  5. 如权利要求1所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，在冠状动脉的三维重建的过程中，根据冠状动脉造影图像的三维中心线和分割好的血管内超声图像序列进行定位定向分析，从而完成冠状动脉造影图像和血管内超声图像的融合而获得冠状动脉血管模型。
  6. 如权利要求1所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，在将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上的过程中，根据血管内超声图像的分类和分割得到的血管分支信息，然后将第一个分支的长度信息，与冠状动脉造影图像中的各个分支长度进行对比查找。
  7. 如权利要求6所述的基于血管分支配准的冠状动脉三维重建方法，其特征在于，当血管内超声图像的第一个分支的长度与冠状动脉造影图像中的一个分支长度相等，达到匹配率最大时，以血管内超声图像中第一个分支与第二个的距离查找冠状动脉造影图像的下一个分支是否匹配，若是匹配则继续查找血管内超声图像中第二个分支与第三个分支是否匹配，若是没有则返回上一步选择第二匹配的分支继续查找，以此类推，直至所有血管内超声图像与冠状动脉造影图像中所有得分支全部匹配上，实现关键点自动配准。
  8. 一种基于血管分支配准的冠状动脉三维重建系统，其特征在于，包括：
    图像处理模块，其用于将血管内超声图像中的分叉血管和正常血管分类并分别进行内外膜分割；提取冠状动脉造影图像中的三维中心线；
    关键点自动配准模块，其用于定位血管分支并自动匹配冠状动脉造影图像的关键点；
    三维重建模块，其用于根据所述冠状动脉造影图像的关键点将分割后的血管内超声内外膜图像配准到冠状动脉造影的三维中心线上，进行冠状动脉的三维重建。
  9. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，该程序被处理器执行时实现如权利要求1-7中任一项所述的基于血管分支配准的冠状动脉三维重建方法中的步骤。
  10. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现如权利要求1-7中任一项所述的基于血管分支配准的冠状动脉三维重建方法中的步骤。
PCT/CN2021/137892 2020-12-15 2021-12-14 一种基于血管分支配准的冠状动脉三维重建方法及系统 WO2022127783A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/911,292 US11842439B2 (en) 2020-12-15 2021-12-14 Method and system for 3D reconstruction of coronary artery based on vascular branch registration

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011480218.3A CN112652052B (zh) 2020-12-15 2020-12-15 一种基于血管分支配准的冠状动脉三维重建方法及系统
CN202011480218.3 2020-12-15

Publications (1)

Publication Number Publication Date
WO2022127783A1 true WO2022127783A1 (zh) 2022-06-23

Family

ID=75354786

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137892 WO2022127783A1 (zh) 2020-12-15 2021-12-14 一种基于血管分支配准的冠状动脉三维重建方法及系统

Country Status (3)

Country Link
US (1) US11842439B2 (zh)
CN (1) CN112652052B (zh)
WO (1) WO2022127783A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112652052B (zh) 2020-12-15 2022-07-22 山东大学 一种基于血管分支配准的冠状动脉三维重建方法及系统
CN113450322B (zh) * 2021-06-22 2024-05-24 东软医疗系统股份有限公司 一种冠状动脉的起源异常判断方法和装置
CN113487616B (zh) * 2021-07-06 2024-03-19 中国医学科学院阜外医院 一种使用连续多帧图像构建完整结构血管树结构的方法
CN113470060B (zh) * 2021-07-08 2023-03-21 西北工业大学 基于ct影像的冠状动脉多角度曲面重建可视化方法
CN113768547B (zh) * 2021-09-14 2024-03-22 南京超维景生物科技有限公司 冠状动脉成像方法及装置、存储介质及电子设备
CN113724377B (zh) * 2021-11-01 2022-03-11 杭州晟视科技有限公司 冠脉血管的三维重建方法、装置、电子设备及存储介质
CN114224388B (zh) * 2021-12-31 2023-07-28 山东大学 基于多频率超声的颈动脉三维重建方法及系统
CN117064446B (zh) * 2023-10-13 2024-01-12 山东大学 基于血管内超声的血管动态三维重建系统
CN117976155A (zh) * 2024-04-01 2024-05-03 杭州脉流科技有限公司 基于造影剂示踪曲线获得冠脉功能学参数的方法、计算机设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120059253A1 (en) * 2010-06-29 2012-03-08 Siemens Aktiengesellschaft Method and System for Image Based Device Tracking for Co-registration of Angiography and Intravascular Ultrasound Images
CN103284760A (zh) * 2013-06-08 2013-09-11 哈尔滨工程大学 一种基于导管路径的扩展超声血管成像方法及装置
CN111063018A (zh) * 2019-11-08 2020-04-24 山东大学 一种基于深度学习的血管内超声图像三维重建方法及系统
CN112652052A (zh) * 2020-12-15 2021-04-13 山东大学 一种基于血管分支配准的冠状动脉三维重建方法及系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2644319C (en) * 2006-03-01 2016-01-05 The Brigham And Women's Hospital, Inc. Artery imaging system
CN101422352B (zh) * 2008-12-10 2011-07-13 华北电力大学（保定） 一种交互式冠状动脉虚拟血管镜的实现方法
US9814433B2 (en) * 2012-10-24 2017-11-14 Cathworks Ltd. Creating a vascular tree model
US10206646B2 (en) * 2016-03-10 2019-02-19 Siemens Healthcare Gmbh Method and system for extracting centerline representation of vascular structures in medical images via optimal paths in computational flow fields
US11017531B2 (en) * 2017-03-09 2021-05-25 Cathworks Ltd Shell-constrained localization of vasculature
CN107392994B (zh) * 2017-06-30 2018-11-06 深圳大学 冠脉血管的三维重建方法、装置、设备及存储介质
EP3909016A1 (en) * 2019-01-13 2021-11-17 Lightlab Imaging, Inc. Systems and methods for classification of arterial image regions and features thereof
EP3884868A1 (en) * 2020-03-26 2021-09-29 Pie Medical Imaging BV Method and system for registering intra-object data with extra-object data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120059253A1 (en) * 2010-06-29 2012-03-08 Siemens Aktiengesellschaft Method and System for Image Based Device Tracking for Co-registration of Angiography and Intravascular Ultrasound Images
CN103284760A (zh) * 2013-06-08 2013-09-11 哈尔滨工程大学 一种基于导管路径的扩展超声血管成像方法及装置
CN111063018A (zh) * 2019-11-08 2020-04-24 山东大学 一种基于深度学习的血管内超声图像三维重建方法及系统
CN112652052A (zh) * 2020-12-15 2021-04-13 山东大学 一种基于血管分支配准的冠状动脉三维重建方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WANG HUANLI: "Three-dimensional Reconstruction Study and Implementation Based on Intravascular Ultrasound Imaging", CHINESE MASTER'S THESES FULL-TEXT DATABASE, INFORMATION SCIENCE, 15 March 2015 (2015-03-15), XP055943454 *

Also Published As

Publication number Publication date
CN112652052B (zh) 2022-07-22
US20230128130A1 (en) 2023-04-27
CN112652052A (zh) 2021-04-13
US11842439B2 (en) 2023-12-12

Similar Documents

Publication Publication Date Title
WO2022127783A1 (zh) 一种基于血管分支配准的冠状动脉三维重建方法及系统
Lebre et al. Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme
CN106097298B (zh) 基于球空间划分的冠状动脉自动分段与解剖学标记方法
CN109360209B (zh) 一种冠状血管分割方法及系统
CN112837306A (zh) 基于深度学习和中智理论的冠状动脉病变功能学定量方法
Lebre et al. Automatic 3-d skeleton-based segmentation of liver vessels from mri and ct for couinaud representation
Philip et al. Convolutional neural networks for automated fetal cardiac assessment using 4D B-mode ultrasound
CN113470060B (zh) 基于ct影像的冠状动脉多角度曲面重建可视化方法
Ma et al. A coronary artery segmentation method based on region growing with variable sector search area
Lidayova et al. Skeleton-based fast, fully automated generation of vessel tree structure for clinical evaluation of blood vessel systems
Qi et al. Examinee-examiner network: Weakly supervised accurate coronary lumen segmentation using centerline constraint
Sheng et al. Extraction method of coronary artery blood vessel centerline in CT coronary angiography
Olszewski et al. Multidimensional segmentation of coronary intravascular ultrasound images using knowledge-based methods
CN114343693A (zh) 一种主动脉夹层诊断方法和装置
Zhang et al. Mesenteric vasculature-guided small bowel segmentation on high-resolution 3D CT angiography scans
Chakshu et al. Automating fractional flow reserve (FFR) calculation from CT scans: A rapid workflow using unsupervised learning and computational fluid dynamics
Benjamin et al. Comparative analysis of image based uterus fibroid detection and classification using deep learning
Marquering et al. Coronary CT angiography: IVUS image fusion for quantitative plaque and stenosis analyses
Jawaid et al. Automated quantification of non-calcified coronary plaques in cardiac CT angiographic imagery
Karim et al. Left atrium pulmonary veins: segmentation and quantification for planning atrial fibrillation ablation
Sakellarios et al. IVUS image processing methodologies
Huang et al. Vessel filtering and segmentation of coronary CT angiographic images
Andrikos et al. A new method for the 3D reconstruction of coronary bifurcations pre and post the angioplasty procedure using the QCA
Altalhi et al. Computation of aortic geometry using mr and ct 3d images
Khan et al. A New Technique for Reducing the Segmentation Error of Left Ventricle Contours using Magnetic Resonance Images

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: 21905712

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21905712

Country of ref document: EP

Kind code of ref document: A1

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 08.08.2023)