WO2019134347A1 - 一种基于x射线冠脉造影图像的多角度血管重建方法 - Google Patents

一种基于x射线冠脉造影图像的多角度血管重建方法 Download PDF

Info

Publication number
WO2019134347A1
WO2019134347A1 PCT/CN2018/091165 CN2018091165W WO2019134347A1 WO 2019134347 A1 WO2019134347 A1 WO 2019134347A1 CN 2018091165 W CN2018091165 W CN 2018091165W WO 2019134347 A1 WO2019134347 A1 WO 2019134347A1
Authority
WO
WIPO (PCT)
Prior art keywords
blood vessel
segmented
dimensional
coronary angiography
vessels
Prior art date
Application number
PCT/CN2018/091165
Other languages
English (en)
French (fr)
Inventor
霍云飞
王之元
刘广志
霍勇
龚艳君
李建平
易铁慈
杨帆
Original Assignee
苏州润迈德医疗科技有限公司
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 苏州润迈德医疗科技有限公司 filed Critical 苏州润迈德医疗科技有限公司
Publication of WO2019134347A1 publication Critical patent/WO2019134347A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • 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
    • G06T2207/10116—X-ray 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular

Definitions

  • the invention belongs to the field of intersection of digital image processing and medical image, and can be applied to image analysis of X-ray coronary angiography in clinical research, in particular to a multi-angle blood vessel reconstruction method based on X-ray coronary angiography image.
  • the vascular tree can be regarded as a tubular system which is curved and extended in space as a whole, and its skeleton is a continuous space curve with a tree structure, reflecting the overall morphological characteristics of the vascular tree.
  • the traditional method is to find the matching pairs of blood vessels in the two contrast images by the outer pole line constraint, but the outer pole line constraints are prone to mismatch.
  • This method has a large error, and in the case of a missing or overlapping blood vessel, there is no guarantee that the blood vessel segment and the sampling point in the bilateral angiography image have a one-to-one correspondence.
  • Common matching methods require high image quality, take a long time, and have poor robustness in the face of individual differences in different blood vessels.
  • the object of the present invention is to provide a multi-angle blood vessel reconstruction method based on X-ray coronary angiography image, which analyzes the feature points of the blood vessels at two angles, and divides the whole blood vessel into small segments according to the feature points, and then according to each small segment The correspondence between the three is separately synthesized, thereby reducing the error caused by the direct synthesis of the entire blood vessel.
  • the technical solution of the present invention is: a multi-angle blood vessel reconstruction method based on an X-ray coronary angiography image, comprising the following steps:
  • Step S1 obtaining 2D structural data and feature points of the blood vessels on the two contrast images based on the X-ray coronary angiography images of the two different angles;
  • Step S2 segmenting the blood vessels on the corresponding contrast image according to the characteristic points of the blood vessel, and obtaining 2D structural data of each blood vessel;
  • Step S3 three-dimensional reconstruction of the two-dimensional structure data of the two segmented blood vessels on the two different angles of the X-ray coronary angiography image, and obtaining the 3D structural data of the segmented blood vessel;
  • Step S4 Step S3 is repeated until the three-dimensional reconstruction of all the segmented vessels is completed, and the reconstructed segmented vessels are merged to obtain a complete three-dimensional blood vessel.
  • the 2D structure data of the blood vessel in step S1 includes a center line, a radius, and an angle
  • the feature points of the blood vessel of step S1 include a starting point, an ending point, a plurality of narrow points, and a plurality of bifurcation points.
  • the specific method for performing three-dimensional reconstruction of the two-section blood vessels in the mapping relationship in step S3 is as follows:
  • Step a transforming the 2D structural data of the two segmented blood vessels into a square surface of the three-dimensional space by matrix transformation
  • Step b forming a square face and a spatial origin of the 2D structure data of the two segmented blood vessels to form two quadrangular pyramids respectively, and the space where the two quadrangular pyramids intersect is the actual limited space of the three-dimensional blood vessel;
  • Step c The center line of the two segmented blood vessels and the spatial origin respectively form two 3D spatial curved surfaces, and the two 3D spatial curved surfaces intersect to form an intersecting line, and the intersecting line in the actually defined space in step b is the center of the three-dimensional blood vessel. line.
  • the invention analyzes the feature points of the blood vessels at two angles, and divides the whole blood vessel into small segments according to the feature points, and then performs three-dimensional synthesis according to the corresponding relationship between each small segment, and then combines the segmented blood vessels to obtain Complete three-dimensional blood vessels, thereby reducing errors caused by direct synthesis of the entire segment of blood vessels;
  • the invention solves the multi-angle vascular matching problem of multi-angle X-ray coronary angiography images, and provides a more effective means for assisting detection of cardiovascular diseases in clinical medicine, thereby improving the reliability and accuracy of vascular matching, thereby effectively increasing The accuracy of three-dimensional reconstruction of large angiography.
  • Figure 1 is a flow chart of the present invention
  • Figure 2 is a schematic view of an X-ray coronary angiography image
  • Figure 3 is a schematic diagram of an image of an X-ray coronary angiography
  • FIG. 4 is a schematic diagram of three-dimensional blood vessel synthesis corresponding to an angle of a contrast image
  • FIG. 5 is a schematic diagram of three-dimensional blood vessel synthesis corresponding to two angles of a contrast image
  • Figure 6 is a schematic diagram of three-dimensional blood vessel synthesis at an X angle
  • Figure 7 is a schematic diagram of three-dimensional blood vessel synthesis at a Y angle
  • Figure 8 is a schematic diagram of three-dimensional blood vessel synthesis at a Z angle
  • Figure 9 is a schematic view of the correspondence of blood vessel bifurcation points
  • Figure 10 is a schematic diagram of the correspondence of blood vessel stenosis points.
  • the multi-angle blood vessel reconstruction method based on X-ray coronary angiography image of the present invention comprises the following steps:
  • Step S1 based on two different angles of X-ray coronary angiography images (refer to FIG. 2 and FIG. 3), respectively obtain 2D structural data and feature points of the blood vessels on the two contrast images, and the 2D structure data includes the center line, the radius, and Angle; feature points include a starting point, an ending point, a plurality of narrow points, and a plurality of bifurcation points;
  • Step S2 segmenting the blood vessels on the corresponding contrast image according to the characteristic points of the blood vessel, and obtaining 2D structural data of each blood vessel;
  • Step S3 three-dimensional reconstruction of the two-dimensional structure data of the two segmented blood vessels on the two different angles of the X-ray coronary angiography image, and obtaining the 3D structural data of the segmented blood vessels;
  • the specific method of three-dimensional reconstruction of segmented blood vessels is as follows:
  • Step a transforming the 2D structural data of the two segmented blood vessels into a square surface of the three-dimensional space by matrix transformation
  • Step b forming a square face and a spatial origin of the 2D structure data of the two segmented blood vessels to form two quadrangular pyramids respectively, and the space where the two quadrangular pyramids intersect is the actual limited space of the three-dimensional blood vessel;
  • Step c The center line of the two segmented blood vessels and the spatial origin respectively form two 3D spatial curved surfaces, and the two 3D spatial curved surfaces intersect to form an intersecting line, and the intersecting line in the actually defined space in step b is the center of the three-dimensional blood vessel. line;
  • Step S4 Step S3 is repeated until the three-dimensional reconstruction of all the segmented vessels is completed, and the reconstructed segmented vessels are merged to obtain a complete three-dimensional blood vessel. Referring to FIG. 4 to FIG.
  • this figure is a schematic diagram of a blood vessel bifurcation point
  • a1b1 is a blood vessel center line on plane A, where c1 is a bifurcation point on the blood vessel
  • a2b2 is a blood vessel center line on plane B, where c2 It is a bifurcation point on the blood vessel; after manual confirmation, between the two center lines, the points correspond to each other, a1 corresponds to a2, b1 corresponds to b2, and c1 corresponds to c2.
  • a1c1 corresponds to a2c2
  • c1b1 corresponds to c2b2; as described above, linear interpolation is performed between each segment to obtain N points, and the segmented blood vessels on plane A and plane B are in one-to-one correspondence.
  • a1b1 is a blood vessel center line on plane A, where d1 is a narrow point on the blood vessel;
  • a2b2 is a blood vessel center line on plane B, where d2 is the A narrow point on the blood vessel; after manual confirmation, between the two center lines, the points correspond to each other, a1 corresponds to a2, b1 corresponds to b2, and d1 corresponds to d2.
  • the narrow point divides the blood vessel into In two segments, a1d1 corresponds to a2d2, and d1b1 corresponds to d2b2; as described above, linear interpolation is performed between each segment to obtain N points, and the segmented blood vessels on plane A and plane B are in one-to-one correspondence.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

一种基于X射线冠脉造影图像的多角度血管重建方法，包括如下步骤：S1：基于两个不同角度的X射线冠脉造影图像，分别获得两造影图像上血管的2D结构数据及特征点；S2：根据血管的特征点将其对应的造影图像上的血管进行分段，并得到每段血管的2D结构数据；S3：将两个不同角度的X射线冠脉造影图像上、且呈映射关系的两分段血管的2D结构数据进行三维重建，并得到该分段血管的3D结构数据；S4：重复步骤S3直到所有分段血管三维重建完成，再将重建后的分段血管合并，即得到完整的三维血管；本方法的优点在于，依据特征点将整段血管分割成小段，然后依据每个小段之间的对应关系分别做三维合成，从而降低了整段血管直接合成造成的误差。

Description

一种基于X射线冠脉造影图像的多角度血管重建方法 技术领域
本发明属于数字图像处理与医学图像的交叉领域，可应用于临床研究中X射冠脉造影图像分析，尤其是涉及一种基于X射线冠脉造影图像的多角度血管重建方法。
背景技术
目前，国内大多数医院都用的是X射线单臂造影系统对病人做X射线造影，通过旋转造影臂得到一个对应于不同造影角度的造影图像序列。单臂造影可以很方便对病人进行不同角度的造影，但是对重建来说个缺点就是我们无法得到同一时刻的不同视角的造影图像，这给重建带来很大的困难。要重建血管的真实三维空间结构，需要得到血管至少两个不同角度的投影信息。传统方法首先提取出血管的骨架，然后通过不同视角空间约束关系，对不同视角投影图像的血管像素点进行正确匹配并重建，当血管几何形变不大，几何关系明显的时候，才能大体上恢复出血管的三维空间结构。
血管树从整体上可以看作在空间中弯曲延展的管状系统，其骨架是具有树状结构的连续空间曲线，反映了血管树的整体形态特征。对于心血管双视角造影图像的匹配问题，传统的方法是通过外极线约束来找两幅造影图像中匹配的血管点对，但是外极线约束极易发生误匹配。这种方法误差较大，在血管缺失或者重叠的情况下，并不能保证双侧造影图像中过的血管段和取样点是一一对应的关系。常见的匹配方法对图像质量要求高，耗时长，在面对不同的血管的个体差异，鲁棒性差。
鉴于传统血管匹配方法中存在的问题，很多研究者都通过在序列图像中选择处于心脏运动周期中同一时刻的造影图像作为重建的参考图像，比如舒张末期。但这种方法依然解决不了这个问题：在两个视角中，同一根血管不同段的伸缩和扭曲不同。
发明内容
本发明目的是：提供一种基于X射线冠脉造影图像的多角度血管重建 方法，通过分析两个角度血管的特征点，并依据特征点将整段血管分割成小段，然后依据每个小段之间的对应关系分别做三维合成，从而降低了整段血管直接合成造成的误差。
本发明的技术方案是：一种基于X射线冠脉造影图像的多角度血管重建方法，包括如下步骤：
步骤S1：基于两个不同角度的X射线冠脉造影图像，分别获得两造影图像上血管的2D结构数据及特征点；
步骤S2：根据血管的特征点将其对应的造影图像上的血管进行分段，并得到每段血管的2D结构数据；
步骤S3：将两个不同角度的X射线冠脉造影图像上、且呈映射关系的两分段血管的2D结构数据进行三维重建，并得到该分段血管的3D结构数据；
步骤S4：重复步骤S3直到所有分段血管三维重建完成，再将重建后的分段血管合并，即得到完整的三维血管。
作为优选的技术方案，步骤S1中血管的2D结构数据包括中心线、半径和角度；
作为优选的技术方案，步骤S1血管的特征点包括起始点、结束点、多个狭窄点和多个分叉点。
作为优选的技术方案，步骤S3中呈映射关系的两分段血管进行三维重建的具体方法如下：
步骤a：通过矩阵变换将两分段血管的2D结构数据分别变换到三维空间的一个正方形面上；
步骤b：将两分段血管的2D结构数据所在的正方形面与空间原点分别构成两个四棱锥体，两个四棱锥体相交的空间即为三维血管的实际限定空间；
步骤c：将两分段血管的中心线与空间原点分别构成两个3D空间曲面，两个3D空间曲面相交形成一条相交线，位于步骤b中实际限定空间内的相交线即为三维血管的中心线。
本发明的优点是：
1.本发明通过分析两个角度血管的特征点，并依据特征点将整段血管 分割成小段，然后依据每个小段之间的对应关系分别做三维合成，然后再将分段血管合并，得到完整的三维血管，从而降低了整段血管直接合成造成的误差；
2.本发明解决多角度X射线冠脉造影图像的多角度血管匹配问题，为临床医学心血管疾病辅助检测提供更为有效的手段，提高了血管匹配的可靠性和精确度，从而可以有效增大血管造影三维重建的精度。
附图说明
下面结合附图及实施例对本发明作进一步描述：
图1为本发明的流程图；
图2为X射线冠脉造影图像一示意图；
图3为X射线冠脉造影图像二示意图；
图4为对应造影图像一角度的三维血管合成示意图；
图5为对应造影图像二角度的三维血管合成示意图；
图6为X角度的三维血管合成示意图；
图7为Y角度的三维血管合成示意图；
图8为Z角度的三维血管合成示意图；
图9为血管分叉点对应示意图；
图10为血管狭窄点对应示意图。
具体实施方式
实施例：参照图1所示：本发明基于X射线冠脉造影图像的多角度血管重建方法，包括如下步骤：
步骤S1：基于两个不同角度的X射线冠脉造影图像(参照图2和图3所示)，分别获得两造影图像上血管的2D结构数据及特征点，2D结构数据包括中心线、半径和角度；特征点包括起始点、结束点、多个狭窄点和多个分叉点；
步骤S2：根据血管的特征点将其对应的造影图像上的血管进行分段，并得到每段血管的2D结构数据；
步骤S3：将两个不同角度的X射线冠脉造影图像上、且呈映射关系的 两分段血管的2D结构数据进行三维重建，并得到该分段血管的3D结构数据；呈映射关系的两分段血管进行三维重建的具体方法如下：
步骤a：通过矩阵变换将两分段血管的2D结构数据分别变换到三维空间的一个正方形面上；
步骤b：将两分段血管的2D结构数据所在的正方形面与空间原点分别构成两个四棱锥体，两个四棱锥体相交的空间即为三维血管的实际限定空间；
步骤c：将两分段血管的中心线与空间原点分别构成两个3D空间曲面，两个3D空间曲面相交形成一条相交线，位于步骤b中实际限定空间内的相交线即为三维血管的中心线；
步骤S4：重复步骤S3直到所有分段血管三维重建完成，再将重建后的分段血管合并，即得到完整的三维血管，参照图4至图8为多角度血管合成示意图。
参照图9，该图为血管分叉点对应示意图，a1b1是平面A上的一条血管中心线，其中c1是该血管上的一个分叉点；a2b2是平面B上的一条血管中心线，其中c2是该血管上的一个分叉点；经过人工确认后，在这两条中心线上，点与点之间是相互对应的，a1对应a2，b1对应b2，c1对应c2，此时，分叉点将血管分成两段，a1c1对应a2c2，c1b1对应c2b2；同上所述在每一小段之间进行线性插值得到N个点，并将平面A和平面B上的分段血管一一对应。
参照图10，该图为血管狭窄点对应示意图，a1b1是平面A上的一条血管中心线，其中d1是该血管上的一个狭窄点；a2b2是平面B上的一条血管中心线，其中d2是该血管上的一个狭窄点；经过人工确认后，在这两条中心线上，点与点之间是相互对应的，a1对应a2，b1对应b2，d1对应d2，此时，狭窄点将血管分成两段，a1d1对应a2d2，d1b1对应d2b2；同上所述在每一小段之间进行线性插值得到N个点，并将平面A和平面B上的分段血管一一对应。
通常在一条血管上会同时出现N个(N>＝1)分叉点和狭窄点，所以会将该血管分成N+1段，然后将两X射线冠脉造影图像上的每一段血管一一对应。
上述实施例仅例示性说明本发明的原理及其功效，而非用于限制本发明。任何熟悉此技术的人士皆可在不违背本发明的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本发明所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本发明的权利要求所涵盖。

Claims (4)

  1. 一种基于X射线冠脉造影图像的多角度血管重建方法，其特征在于，包括如下步骤：
    步骤S1：基于两个不同角度的X射线冠脉造影图像，分别获得两造影图像上血管的2D结构数据及特征点；
    步骤S2：根据血管的特征点将其对应的造影图像上的血管进行分段，并得到每段血管的2D结构数据；
    步骤S3：将两个不同角度的X射线冠脉造影图像上、且呈映射关系的两分段血管的2D结构数据进行三维重建，并得到该分段血管的3D结构数据；
    步骤S4：重复步骤S3直到所有分段血管三维重建完成，再将重建后的分段血管合并，即得到完整的三维血管。
  2. 根据权利要求1所述的基于X射线冠脉造影图像的多角度血管重建方法，其特征在于，步骤S1中血管的2D结构数据包括中心线、半径和角度；
  3. 根据权利要求1所述的基于X射线冠脉造影图像的多角度血管重建方法，其特征在于，步骤S1血管的特征点包括起始点、结束点、多个狭窄点和多个分叉点。
  4. 根据权利要求1所述的基于X射线冠脉造影图像的多角度血管重建方法，其特征在于，步骤S3中呈映射关系的两分段血管进行三维重建的具体方法如下：
    步骤a：通过矩阵变换将两分段血管的2D结构数据分别变换到三维空间的一个正方形面上；
    步骤b：将两分段血管的2D结构数据所在的正方形面与空间原点分别构成两个四棱锥体，两个四棱锥体相交的空间即为三维血管的实际限定空间；
    步骤c：将两分段血管的中心线与空间原点分别构成两个3D空间曲面，两个3D空间曲面相交形成一条相交线，位于步骤b中实际限定空间内的相交线即为三维血管的中心线。
PCT/CN2018/091165 2018-01-05 2018-06-13 一种基于x射线冠脉造影图像的多角度血管重建方法 WO2019134347A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810010079.4A CN108242075A (zh) 2018-01-05 2018-01-05 一种基于x射线冠脉造影图像的多角度血管重建方法
CN201810010079.4 2018-01-05

Publications (1)

Publication Number Publication Date
WO2019134347A1 true WO2019134347A1 (zh) 2019-07-11

Family

ID=62699384

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/091165 WO2019134347A1 (zh) 2018-01-05 2018-06-13 一种基于x射线冠脉造影图像的多角度血管重建方法

Country Status (2)

Country Link
CN (1) CN108242075A (zh)
WO (1) WO2019134347A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111166315B (zh) * 2018-11-13 2023-03-28 苏州润迈德医疗科技有限公司 基于造影图像计算瞬时无波型比率和静息态舒张期压力比率的方法
CN111166316B (zh) * 2018-11-13 2023-03-21 苏州润迈德医疗科技有限公司 基于造影图像计算造影瞬时无波型比率和造影舒张期压力比率的方法
CN109872336B (zh) * 2019-03-13 2021-07-09 数坤(北京)网络科技股份有限公司 一种血管分割方法、设备及计算机存储介质
CN112132882A (zh) * 2019-11-19 2020-12-25 苏州润迈德医疗科技有限公司 从冠状动脉二维造影图像中提取血管中心线的方法和装置
CN112419279B (zh) * 2020-11-25 2024-02-23 苏州润迈德医疗科技有限公司 二维图像选取及三维血管合成的方法和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763642A (zh) * 2009-12-31 2010-06-30 华中科技大学 一种用于冠脉造影三维重建的匹配方法
CN101799935A (zh) * 2009-12-31 2010-08-11 华中科技大学 一种单臂x射线造影图像的动态三维重建方法
JP2011156288A (ja) * 2009-02-04 2011-08-18 Toshiba Corp Ｘ線診断装置及び画像処理装置
CN107392994A (zh) * 2017-06-30 2017-11-24 深圳大学 冠脉血管的三维重建方法、装置、设备及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105894445B (zh) * 2016-03-31 2019-06-11 北京思创贯宇科技开发有限公司 一种冠脉图像处理方法和装置
CN105877767A (zh) * 2016-03-31 2016-08-24 北京思创贯宇科技开发有限公司 一种冠脉图像造影方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011156288A (ja) * 2009-02-04 2011-08-18 Toshiba Corp Ｘ線診断装置及び画像処理装置
CN101763642A (zh) * 2009-12-31 2010-06-30 华中科技大学 一种用于冠脉造影三维重建的匹配方法
CN101799935A (zh) * 2009-12-31 2010-08-11 华中科技大学 一种单臂x射线造影图像的动态三维重建方法
CN107392994A (zh) * 2017-06-30 2017-11-24 深圳大学 冠脉血管的三维重建方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN108242075A (zh) 2018-07-03

Similar Documents

Publication Publication Date Title
WO2019134347A1 (zh) 一种基于x射线冠脉造影图像的多角度血管重建方法
Blondel et al. Reconstruction of coronary arteries from a single rotational X-ray projection sequence
Liao et al. 3-D reconstruction of the coronary artery tree from multiple views of a rotational X-ray angiography
Cong et al. Quantitative analysis of deformable model-based 3-D reconstruction of coronary artery from multiple angiograms
US8542892B2 (en) Method and apparatus for compensating for motion in an imaged object
CN100361626C (zh) 分布式心脏图像多维重建与交互可视化方法
Zheng et al. Sequential reconstruction of vessel skeletons from X-ray coronary angiographic sequences
AU2006282500A2 (en) Image processing method, image processing program, and image processing device
CN109389655A (zh) 时变数据的重建
Chen et al. Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds
CN111476791B (zh) 图像处理方法、图像处理装置和非暂时性计算机可读介质
CN103077550A (zh) 一种非门控icus图像序列中血管的四维重建方法
Yang et al. External force back-projective composition and globally deformable optimization for 3-D coronary artery reconstruction
WO2023040628A1 (zh) 一种pet三维图像左心室自动转向及分割的方法
CN111009032A (zh) 基于改进外极线约束匹配的血管三维重建方法
Xiong et al. Comprehensive modeling and visualization of cardiac anatomy and physiology from CT imaging and computer simulations
Li et al. How to reconstruct 3D coronary arterial tree from two arbitrary views
Garcia Quantitative myocardial perfusion single-photon emission computed tomographic imaging: quo vadis?(Where do we go from here?)
Xiao et al. Shape context and projection geometry constrained vasculature matching for 3D reconstruction of coronary artery
Dong et al. A novel end‐to‐end deep learning solution for coronary artery segmentation from CCTA
US11317875B2 (en) Reconstruction of flow data
Shechter et al. Temporal tracking of 3D coronary arteries in projection angiograms
Yang et al. Automatic left ventricle segmentation based on multiatlas registration in 4D CT images
CN109035353B (zh) 一种基于ct图像多平面重建的血管拉直曲面重组方法
Müller et al. Interventional heart wall motion analysis with cardiac C-arm CT systems

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: 18897959

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: 18897959

Country of ref document: EP

Kind code of ref document: A1