技术领域Technical field
本发明实施例涉及图像处理技术，尤其涉及一种数据处理方法、装置、电子设备和存储介质。Embodiments of the present invention relate to image processing technology, and in particular, to a data processing method, device, electronic device and storage medium.
背景技术Background technique
三维超声成像系统以其形象直观的可视效果，以及由此带来的临床价值,受到了广大研究人员和医疗工作者的关注。尤其是全乳自动超声成像，对提供三维乳房提供了直观和标准化的体积数据。The three-dimensional ultrasound imaging system has attracted the attention of researchers and medical workers due to its intuitive visual effects and the clinical value it brings. In particular, automatic ultrasound imaging of the whole breast provides intuitive and standardized volume data for three-dimensional breasts.
目前全乳自动超声成像设备的探头尺寸大约为15cm，扫查开始前，探头横置，左右方向跨度为15cm。扫查过程中，探头平移向上移动，扫过整个乳房区域。At present, the probe size of the whole breast automatic ultrasound imaging equipment is about 15cm. Before the scan starts, the probe is placed horizontally with a span of 15cm in the left and right directions. During the scanning process, the probe moves upward and scans the entire breast area.
上述乳房扫查方式，即使单侧乳房左右宽度小于15cm，探头两侧区域和乳房皮肤表面贴合情况，相较于中间区域比较差，无法得到完整的、精确的乳房的体数据。In the above-mentioned breast scanning method, even if the left and right width of one breast is less than 15 cm, the fit between the two sides of the probe and the breast skin surface is poorer than that between the middle area, and complete and accurate breast volume data cannot be obtained.
发明内容Contents of the invention
本发明实施例提供一种数据处理方法、装置、电子设备和存储介质，以实现得到完整的、精确的目标对象的全局体数据的效果。Embodiments of the present invention provide a data processing method, device, electronic device and storage medium to achieve the effect of obtaining complete and accurate global volume data of a target object.
第一方面，本发明实施例提供了一种数据处理方法，该方法包括：In a first aspect, an embodiment of the present invention provides a data processing method, the method comprising:
获取目标对象的至少两个方位的三维体数据，分别提取各所述三维体数据中的至少三个特征点，并确定各所述三维体数据中的各特征点之间的对应关系；Obtain three-dimensional volume data of at least two orientations of the target object, respectively extract at least three feature points in each of the three-dimensional volume data, and determine the corresponding relationship between each feature point in each of the three-dimensional volume data;
基于各所述三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵；Based on the correspondence between the feature points in each of the three-dimensional volume data, determine the transformation matrix between the three-dimensional volume data in each orientation;
基于各所述三维体数据之间的变换矩阵，将各方位的所述三维体数据进行融合，得到所述目标对象的融合三维体数据。Based on the transformation matrix between the three-dimensional volume data, the three-dimensional volume data of each orientation are fused to obtain the fused three-dimensional volume data of the target object.
第二方面，本发明实施例还提供了一种数据处理装置，该装置包括：In a second aspect, an embodiment of the present invention further provides a data processing device, the device comprising:
信息获取模块，用于获取目标对象的至少两个方位的三维体数据，分别提取各所述三维体数据中的至少三个特征点，并确定各所述三维体数据中的各特征点之间的对应关系；The information acquisition module is used to obtain three-dimensional volume data of at least two directions of the target object, respectively extract at least three feature points in each of the three-dimensional volume data, and determine the distance between each feature point in each of the three-dimensional volume data. corresponding relationship;
变换矩阵确定模块，用于基于各所述三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵；A transformation matrix determination module, configured to determine the transformation matrix between the three-dimensional volume data in each direction based on the correspondence between the feature points in each of the three-dimensional volume data;
数据融合模块，用于基于各所述三维体数据之间的变换矩阵，将各方位的所述三维体数据进行融合，得到所述目标对象的融合三维体数据。A data fusion module is used to fuse the three-dimensional volume data in various directions based on the transformation matrix between the three-dimensional volume data to obtain the fused three-dimensional volume data of the target object.
第三方面，本发明实施例还提供了一种电子设备，该电子设备包括：In a third aspect, embodiments of the present invention further provide an electronic device, which includes:
一个或多个处理器；one or more processors;
存储装置，用于存储一个或多个程序；A storage device for storing one or more programs;
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现本发明实施例中任一所述的数据处理方法。When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement any of the data processing methods described in the embodiments of the present invention.
第四方面，本发明实施例还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行本发明实施例中任一所述的数据处理方法。In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor are used to perform any of the data processing described in the embodiments of the present invention. method.
本发明实施例的技术方案，通过根据获取的目标对象的各方位的局部的三维体数据，提取各三维体数据中的各特征点，并确定各三维体数据中的各特征点之间的对应关系，基于各三维体数据中的各特征点之间的对应关系，确定各三维体数据之间的变换矩阵，根据各三维体数据之间的变换矩阵，可将各方位的目标对象的局部三维体数据进行融合，得到目标对象的全局三维体数据，这样可直接得到整个目标对象及其周边区域的全局三维体数据，能更好的给出整个目标对象区域和周边区域的组织结构。The technical solution of the embodiment of the present invention extracts each feature point in each three-dimensional volume data based on the acquired local three-dimensional volume data at each position of the target object, and determines the correspondence between each feature point in each three-dimensional volume data. Relationship, based on the corresponding relationship between each feature point in each three-dimensional volume data, determine the transformation matrix between each three-dimensional volume data. According to the transformation matrix between each three-dimensional volume data, the local three-dimensional image of the target object in each orientation can be The volume data is fused to obtain the global three-dimensional volume data of the target object. In this way, the global three-dimensional volume data of the entire target object and its surrounding areas can be directly obtained, which can better give the organizational structure of the entire target object area and surrounding areas.
附图说明Description of drawings
图1是本发明实施例一中的数据处理方法的流程图；Figure 1 is a flow chart of the data processing method in Embodiment 1 of the present invention;
图2是本发明实施例一中的目标对象的不同方位的三维体数据的获取示意图；Figure 2 is a schematic diagram of acquiring three-dimensional volume data of a target object in different directions in Embodiment 1 of the present invention;
图3是本发明实施例一中的获取目标对象的不同方位的图像示意图；FIG3 is a schematic diagram of obtaining images of different orientations of a target object in Embodiment 1 of the present invention;
图4是本发明实施例一中的各方位的三维体数据的重叠示意图；Figure 4 is an overlapping schematic diagram of three-dimensional volume data in various directions in Embodiment 1 of the present invention;
图5是本发明实施例一中的两个方位的三维体数据的重叠区域示意图；FIG5 is a schematic diagram of overlapping regions of three-dimensional volume data in two orientations in the first embodiment of the present invention;
图6是本发明实施例一中的融合三维体数据效果示意图；FIG6 is a schematic diagram of the effect of fusing three-dimensional volume data in the first embodiment of the present invention;
图7是本发明实施例二中的各三维体数据中的各特征点之间的对应关系确定示意图；Figure 7 is a schematic diagram for determining the correspondence relationship between each feature point in each three-dimensional volume data in Embodiment 2 of the present invention;
图8是本发明实施例三中的数据处理装置的结构示意图；Figure 8 is a schematic structural diagram of a data processing device in Embodiment 3 of the present invention;
图9是本发明实施例四中的一种电子设备的结构示意图。Figure 9 is a schematic structural diagram of an electronic device in Embodiment 4 of the present invention.
具体实施方式Detailed ways
下面结合附图和实施例对本发明作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释本发明，而非对本发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本发明相关的部分而非全部结构。The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
实施例一Embodiment 1
图1为本发明实施例一提供的数据处理方法的流程图，本实施例可适用于将不同方位的目标对象的体数据进行融合，得到目标对象的全局体数据的情况，该方法可以由数据处理装置来执行，该数据处理装置可以由软件和/或硬件来实现，该数据处理装置可以配置在电子计算设备上，具体包括如下步骤：Figure 1 is a flow chart of a data processing method provided by Embodiment 1 of the present invention. This embodiment can be applied to the situation where volume data of target objects in different directions are fused to obtain global volume data of the target object. This method can be based on data The data processing device can be executed by a processing device. The data processing device can be implemented by software and/or hardware. The data processing device can be configured on an electronic computing device, and specifically includes the following steps:
S110、获取目标对象的至少两个方位的三维体数据，分别提取各三维体数据中的至少三个特征点，并确定各三维体数据中的各特征点之间的对应关系。S110. Obtain three-dimensional volume data of at least two orientations of the target object, respectively extract at least three feature points in each three-dimensional volume data, and determine the correspondence between each feature point in each three-dimensional volume data.
示例性的，这里的目标对象可以是需要进行各方位的体数据融合，得到全局体数据的对象。例如，可以是人或动物，还可以是人或动物中的某一组织、器官等。For example, the target object here may be an object for which volume data of all directions needs to be fused to obtain global volume data, for example, a human or an animal, or a tissue or organ in a human or an animal.
至少两个方位的三维体数据可以是从不同的方位获取的目标对象的三维体数据。The three-dimensional volume data of at least two orientations may be three-dimensional volume data of the target object acquired from different orientations.
具体的，参考如图2所述的目标对象的不同方位的三维体数据的获取示意图，在图2中，目标对象为人体乳房为例，从乳房的中间区域进行扫查即为AP位，在乳房中间偏中间域进行扫查即为MED位，在乳房中间偏侧向进行扫查即为LAT位。从图2中可见，AP、LAT和MED三个扫查体积，可以有效覆盖整个乳房区域，这样即可获取乳房的不同方位的三维体数据。Specifically, refer to the schematic diagram of acquiring three-dimensional volume data of the target object in different directions as shown in Figure 2. In Figure 2, the target object is the human breast as an example. Scanning from the middle area of the breast is the AP position. In Scanning the middle and lateral areas of the breast is the MED position, and scanning the middle and lateral areas of the breast is the LAT position. As can be seen from Figure 2, the three scanning volumes of AP, LAT and MED can effectively cover the entire breast area, so that three-dimensional volume data of the breast in different directions can be obtained.
需要说明的是，这里的不同方位的三维体数据是有要求的，必须是各方位的三维体数据进行组合可形成整个目标对象的全局三维体数据，即上述的AP、LAT和MED三个方位的三维体数据有效覆盖了整个乳房区域。It should be noted that there are requirements for the three-dimensional volume data at different orientations here. The three-dimensional volume data from each orientation must be combined to form the global three-dimensional volume data of the entire target object, that is, the three orientations of AP, LAT and MED mentioned above. The three-dimensional volume data effectively covers the entire breast area.
需要说明的是，若上述的AP、LAT和MED三个方位的三维体数据无法有效覆盖整个乳房区域，则还可对乳房区域的侧上、侧下等区域进行更多的扫描。以确保覆盖整个乳房区域。It should be noted that if the three-dimensional volume data in the above three directions of AP, LAT and MED cannot effectively cover the entire breast area, more scans can be performed on the upper and lower sides of the breast area. to ensure coverage of the entire breast area.
参考图3所述的获取目标对象的不同方位的图像示意图，其中，图3中左上角为横断面的图像，右下角为冠状面的图像，左下角为矢状面的图像，右上角为三维体数据的体绘制图。Refer to Figure 3 for a schematic diagram of acquiring images of a target object in different directions. In Figure 3, the upper left corner is a cross-sectional image, the lower right corner is a coronal plane image, the lower left corner is a sagittal plane image, and the upper right corner is a three-dimensional image. Volume rendering of volumetric data.
在获取到目标对象的不同方位的三维体数据后，分别提取各方位的三维体数据的至少三个特征点。After acquiring the three-dimensional volume data of the target object in different orientations, at least three feature points of the three-dimensional volume data in each orientation are respectively extracted.
这里的特征点可以是可将不同方位的三维体数据进行连接起来的体数据点。The feature points here can be volume data points that can connect three-dimensional volume data in different directions.
参考图4所述的各方位的三维体数据的重叠示意图，从图2中获取到AP、LAT和MED三个方位的三维体数据后，AP、LAT和MED三个方位的三维体数据会有重叠，重叠区域部分的体数据点即可以是特征点。Referring to the overlapping schematic diagram of the three-dimensional volume data in each direction described in Figure 4, after obtaining the three-dimensional volume data in the three directions of AP, LAT and MED from Figure 2, the three-dimensional volume data in the three directions of AP, LAT and MED will be Overlap, the volume data points in the overlapping area can be feature points.
需要说明的是，这里的分别获取的是各方位的三维体数据的至少三个特征点的原因是：为后续的计算各方位的三维体数据之间的变换矩阵做铺垫，因为只有每个方位上具有至少三个特征点才可计算各方位的三维体数据之间的变换矩阵。It should be noted that the reason why at least three feature points of the three-dimensional volume data of each orientation are obtained here is to pave the way for the subsequent calculation of the transformation matrix between the three-dimensional volume data of each orientation, because only each orientation Only when there are at least three feature points on the object can the transformation matrix between the three-dimensional volume data of each orientation be calculated.
在本发明实施例中，获取各三维体数据中的特征点的方式可以是根据预设设置的特征点的特征信息来进行匹配获取，还可以是利用神经网络模型或者算法等方式来获取。具体的特征点的获取方式在下面实施例再详细介绍。In the embodiment of the present invention, the way to obtain the feature points in each three-dimensional volume data may be to match and obtain them according to the characteristic information of the preset feature points, or to obtain them by using a neural network model or algorithm. The specific method of obtaining feature points will be introduced in detail in the following embodiments.
在获取到各三维体数据中的各特征点后，可将各三维体数据中的各特征点形成特征点集。例如，有AP、LAT和MED三个方位的三维体数据，从AP方位的三维体数据中获取到50个特征点，则将这50个特征点形成AP方位的特征点集；从LAT方位的三维体数据中获取到60个特征点，则将这60个特征点形成LAT方位的特征点集；从MED方位的三维体数据中获取到80个特征点，则将这80个特征点形成MED方位的特征点集。After obtaining each feature point in each three-dimensional volume data, each feature point in each three-dimensional volume data can be formed into a feature point set. For example, there are three-dimensional volume data in AP, LAT and MED directions. If 50 feature points are obtained from the three-dimensional volume data in AP direction, these 50 feature points will form a feature point set in AP direction; from the LAT direction, 50 feature points will be obtained. If 60 feature points are obtained from the three-dimensional volume data, these 60 feature points will form a feature point set in the LAT orientation; if 80 feature points are obtained from the three-dimensional volume data in the MED orientation, these 80 feature points will be formed into a MED The feature point set of the orientation.
在形成各方位的特征点集后，可确定各方位的特征点集中的特征点之间的对应关系。具体的例如可以是，AP方位的特征点集中的某一个特征点与LAT方位的特征点集中的哪个特征点对应，找到各方位的特征点之间的对应关系。After the feature point sets of each orientation are formed, the corresponding relationship between the feature points in the feature point set of each orientation can be determined. A specific example may be, which feature point in the feature point set in the AP direction corresponds to which feature point in the feature point set in the LAT direction, and find the correspondence between the feature points in each direction.
可选的，在所述分别提取各三维体数据中的特征点之后，所述方法还可以包括：给各三维体数据中的各特征点添加标识符。Optionally, after separately extracting the feature points in each three-dimensional volume data, the method may further include: adding an identifier to each feature point in each three-dimensional volume data.
示例性的，标识符可以是是给各三维体数据中的各特征点添加的唯一标识，例如，可以是给各三维体数据中的各特征点附上唯一编号等。For example, the identifier may be a unique identifier added to each feature point in each three-dimensional volume data. For example, it may be a unique number added to each feature point in each three-dimensional volume data.
具体的例如，有A和B两个方位的三维体数据，其中，A中的特征点有5个，B中的特征点有6个，则给A中的5个特征点分别编上编号：1、2、3、4、5，给B中的6个特征点分别编上编号：1’、2’、3’、4’、5’、6’。这样可将各特征点进行区分，避免在后续确定A中的各特征点与B中的各特征点之间的对应关系时搞混。For example, if there are three-dimensional volume data in two directions, A and B. Among them, there are 5 feature points in A and 6 feature points in B. Then each of the 5 feature points in A will be numbered: 1, 2, 3, 4, 5, number the 6 feature points in B respectively: 1', 2', 3', 4', 5', 6'. In this way, each feature point can be distinguished to avoid confusion when subsequently determining the corresponding relationship between each feature point in A and each feature point in B.
这样给各方位的三维体数据中的各特征点添加标识符后，再确定各所述三维体数据中的各特征点之间的对应关系时，不会造成各方位的三维体数据中的各特征点的混乱。In this way, after adding identifiers to each feature point in the three-dimensional volume data at each orientation, and then determining the corresponding relationship between each feature point in the three-dimensional volume data, it will not cause each feature point in the three-dimensional volume data at each orientation to Confusion of feature points.
S120、基于各三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵。S120. Based on the correspondence between the feature points in each three-dimensional volume data, determine the transformation matrix between the three-dimensional volume data in each orientation.
示例性的，当确定了各方位的三维体数据中的各特征点之间的对应关系后，可根据各方位的三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵。Exemplarily, after the correspondence between the feature points in the three-dimensional volume data at various orientations is determined, the transformation matrix between the three-dimensional volume data at various orientations may be determined according to the correspondence between the feature points in the three-dimensional volume data at various orientations.
在本发明实施例中，当确定了各方位的三维体数据中的各特征点之间的对应关系后，将一一对应的特征点记录下来。In the embodiment of the present invention, after the correspondence between the feature points in the three-dimensional volume data at each orientation is determined, the one-to-one corresponding feature points are recorded.
以任意两个方位的三维体数据为例，记第一方位的三维体数据为V1，第二方位的三维体数据为V2，记V1中与V2中具有对应关系的特征点的集合为记V2中与V1中具有对应关系的特征点的集合为/>j＝1，2，3...n，/>的对应点是/>Taking the three-dimensional volume data of any two orientations as an example, let the three-dimensional volume data of the first orientation be V1, and the three-dimensional volume data of the second orientation be V2. Let the set of feature points corresponding to V1 and V2 be Denote the set of feature points in V2 that have a corresponding relationship with V1 as/> j=1, 2, 3...n,/> The corresponding point is/>
在本发明实施例中，如图4可见，因为乳腺是软组织，所以在获取不同方位的三维体数据的时候，乳腺受压形变不同，最终得到的图像也不同。即从成像的物理过程可知，不同方位的体数据之间相差的不是刚体形变。In the embodiment of the present invention, as shown in Figure 4, because the breast is a soft tissue, when acquiring three-dimensional volume data in different directions, the breast is compressed and deformed differently, and the final images obtained are also different. That is to say, it can be known from the physical process of imaging that the difference between the volume data in different directions is not the rigid body deformation.
记任意两个方位的三维体数据之间的空间变换为T，采用参数T*表示最优空间变换，则T*可由如下优化过程求出：Denote the spatial transformation between three-dimensional volume data at any two orientations as T, and use the parameter T* to represent the optimal spatial transformation. Then T* can be obtained by the following optimization process:
可选的，所述基于各三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵，具体可以是：对于目标对象的任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据，基于两个方位的三维体数据中的各特征点之间的对应关系，根据如下公式，确定两个方位的三维体数据之间的变换矩阵：Optionally, the transformation matrix between the three-dimensional volume data of each orientation is determined based on the corresponding relationship between the feature points in each three-dimensional volume data. Specifically, it can be: for the three-dimensional volume of any two orientations of the target object. data, using the three-dimensional volume data at one orientation as the first three-dimensional volume data, and the three-dimensional volume data at the other orientation as the second three-dimensional volume data, based on the correspondence between the feature points in the three-dimensional volume data at the two orientations , according to the following formula, determine the transformation matrix between the three-dimensional volume data of the two orientations:
其中，为目标对象的第一三维体数据中与第二三维体数据中的特征点具有对应关系的特征点，/>为目标对象的第二三维体数据中与第一三维体数据中的特征点具有对应关系的特征点，/>和/>中的点一一对应，j＝1，2，3...n，T为变换矩阵；T*为最小时，T的值。in, is the feature point in the first three-dimensional volume data of the target object that has a corresponding relationship with the feature point in the second three-dimensional volume data,/> is the feature point in the second three-dimensional volume data of the target object that has a corresponding relationship with the feature point in the first three-dimensional volume data,/> and/> The points in are in one-to-one correspondence, j=1, 2, 3...n, T is the transformation matrix; T* is At minimum, the value of T.
在本发明实施例中，在计算T*时，可采集最小二乘、梯度下降和高斯牛顿(或拟牛顿、牛顿法)求解上述公式，可得到最优变换矩阵T*。In the embodiment of the present invention, when calculating T*, least squares, gradient descent and Gauss-Newton (or quasi-Newton or Newton method) can be used to solve the above formula, and the optimal transformation matrix T* can be obtained.
S130、基于各三维体数据之间的变换矩阵，将各方位的三维体数据进行融合，得到目标对象的融合三维体数据。S130 , based on the transformation matrix between the three-dimensional volume data, the three-dimensional volume data in various directions are fused to obtain fused three-dimensional volume data of the target object.
示例性的，融合三维体数据可以是将各方位的三维体数据进行融合后，形成的目标对象的全局三维体数据。For example, the fused three-dimensional volume data may be the global three-dimensional volume data of the target object formed by fusing the three-dimensional volume data of each orientation.
在得到各三维体数据中的各特征点之间的对应关系后(即配准后)，可确定各三维体数据之间的变换矩阵，在确定各三维体数据之间的变换矩阵后，可将各方位的三维体数据进行融合，得到目标对象的融合三维体数据。After obtaining the correspondence between each feature point in each three-dimensional volume data (that is, after registration), the transformation matrix between each three-dimensional volume data can be determined. After determining the transformation matrix between each three-dimensional volume data, Fusion of three-dimensional volume data from various directions is performed to obtain the fused three-dimensional volume data of the target object.
这样根据获取的目标对象的各方位的局部的三维体数据，得到目标对象的全局三维体数据，这样可直接得到整个目标对象及其周边区域的全局三维体数据，能更好的给出整个目标对象区域和周边区域的组织结构。当目标对象为医学研究的对象时，还可供医生基于目标对象的全景图像，更好理解目标对象的空间关系和病灶范围。In this way, the global three-dimensional volume data of the target object can be obtained based on the acquired local three-dimensional volume data of each direction of the target object. In this way, the global three-dimensional volume data of the entire target object and its surrounding areas can be directly obtained, which can better provide the entire target. Organization of the object area and surrounding areas. When the target object is the object of medical research, it can also allow doctors to better understand the spatial relationship and lesion range of the target object based on the panoramic image of the target object.
可选的，所述将各方位的三维体数据进行融合，得到目标对象的融合三维体数据，可以是：对于目标对象的任意两个方位的三维体数据，执行如下步骤，将两个方位的三维体数据进行融合：将其中一个方位的三维体数据作为基准三维体数据，另一方位的三维体数据作为待配准三维体数据；基于两个方位的三维体数据之间的变换矩阵，将待配准三维体数据的坐标映射到基准三维体数据的坐标系中，将两个方位的三维体数据进行融合。Optionally, the fusion of three-dimensional volume data of each orientation to obtain the fused three-dimensional volume data of the target object may be: for the three-dimensional volume data of any two orientations of the target object, perform the following steps to combine the three-dimensional volume data of the two orientations. Three-dimensional volume data is fused: the three-dimensional volume data in one direction is used as the reference three-dimensional volume data, and the three-dimensional volume data in the other direction is used as the three-dimensional volume data to be registered; based on the transformation matrix between the three-dimensional volume data in the two directions, The coordinates of the three-dimensional volume data to be registered are mapped to the coordinate system of the reference three-dimensional volume data, and the three-dimensional volume data of the two orientations are fused.
示例性的，对于任意两个方位的三维体数据，可将其中一个方位的三维体数据作为基准三维体数据，另一方位的三维体数据作为待配准三维体数据，基于两个方位的三维体数据之间的变换矩阵，将待配准三维体数据的坐标映射到基准三维体数据的坐标系中，即可实现两个方位的三维体数据的融合，即可得到融合后的三维体数据，即融合三维体数据。For example, for the three-dimensional volume data of any two orientations, the three-dimensional volume data of one orientation can be used as the reference three-dimensional volume data, and the three-dimensional volume data of the other orientation can be used as the three-dimensional volume data to be registered. Based on the three-dimensional volume data of the two orientations, The transformation matrix between volume data maps the coordinates of the three-dimensional volume data to be registered to the coordinate system of the reference three-dimensional volume data, so that the three-dimensional volume data from two directions can be fused, and the fused three-dimensional volume data can be obtained. , that is, fusion of three-dimensional volume data.
在本发明实施例中，对于两个方位以上的三维体数据，例如，对于三个方位的三维体数据而言，可以是依据上述的方法先将两个方位的三维体数据进行融合后，再将第三个方位的三维体数据与之前的两个方位的三维体数据融合后的三维体数据进行融合，得到三个方位的三维体数据的融合结果。In an embodiment of the present invention, for three-dimensional volume data in more than two orientations, for example, three-dimensional volume data in three orientations, the three-dimensional volume data in two orientations may be fused according to the above method, and then the three-dimensional volume data in the third orientation may be fused with the three-dimensional volume data obtained by fusion of the previous two orientations to obtain a fusion result of the three-dimensional volume data in three orientations.
参考图5所述的两个方位的三维体数据的重叠区域示意图，当图4中的三维体数据出现重叠时，表面两个方位的三维体数据对应的图像会出现重叠区域(如图5中的左上角的图像、左下角的图像和右下角的图像中的方框圈出来的区域为两个方位的三维体数据的重叠区域)，对于重叠区域的体素值为固定图像体素值加移动图像体素值和的一半。即对于两个图像而言，将其中一个图像作为固定图像，另一图像作为移动图像，则将移动图像置于固定图像上时(具体的可以是将移动图像的三维体数据的坐标置于固定图像的坐标系中)，重叠区域的体素值为固定图像体素值加移动图像体素值和的一半。Referring to the schematic diagram of the overlapping area of three-dimensional volume data in two directions described in Figure 5, when the three-dimensional volume data in Figure 4 overlaps, the images corresponding to the three-dimensional volume data in the two directions on the surface will have an overlapping area (as shown in Figure 5 The area enclosed by the box in the image in the upper left corner, the image in the lower left corner and the image in the lower right corner is the overlapping area of the three-dimensional volume data in the two directions), and the voxel value of the overlapping area is the fixed image voxel value plus Move half the sum of voxel values in the image. That is, for two images, one of the images is used as a fixed image and the other image is used as a moving image. When the moving image is placed on the fixed image (specifically, the coordinates of the three-dimensional volume data of the moving image can be placed on the fixed image). (in the coordinate system of the image), the voxel value of the overlapping area is half of the sum of the voxel value of the fixed image plus the voxel value of the moving image.
参考图6所述的融合三维体数据效果示意图，将目标对象的各方位的三维体数据进行融合后，得到目标对象的全局三维体数据，从图6的左下角的图像中可以看出，完整的肋骨分别位于两幅三维体数据中(即图6中的左下角图像中的M和N分别为两个方位的三维体数据中的肋骨)。经过本发明实施例的配准和融合，可以见到，两幅三维体数据中的肋骨准确的匹配在一起，全景三维体数据也正确的包含了整个肋骨范围。Referring to the schematic diagram of the effect of fused three-dimensional volume data as shown in Figure 6, after fusing the three-dimensional volume data of all directions of the target object, the global three-dimensional volume data of the target object is obtained. As can be seen from the image in the lower left corner of Figure 6, the complete The ribs are respectively located in the two pieces of three-dimensional volume data (that is, M and N in the lower left image in Figure 6 are the ribs in the three-dimensional volume data in two directions respectively). After registration and fusion according to the embodiment of the present invention, it can be seen that the ribs in the two pieces of three-dimensional volume data are accurately matched together, and the panoramic three-dimensional volume data also correctly includes the entire rib range.
本发明实施例的技术方案，通过根据获取的目标对象的各方位的局部的三维体数据，提取各三维体数据中的各特征点，并确定各三维体数据中的各特征点之间的对应关系，基于各三维体数据中的各特征点之间的对应关系，确定各三维体数据之间的变换矩阵，根据各三维体数据之间的变换矩阵，可将各方位的目标对象的局部三维体数据进行融合，得到目标对象的全局三维体数据，这样可直接得到整个目标对象及其周边区域的全局三维体数据，能更好的给出整个目标对象区域和周边区域的组织结构。The technical solution of the embodiment of the present invention extracts each feature point in each three-dimensional volume data based on the acquired local three-dimensional volume data at each position of the target object, and determines the correspondence between each feature point in each three-dimensional volume data. Relationship, based on the corresponding relationship between each feature point in each three-dimensional volume data, determine the transformation matrix between each three-dimensional volume data. According to the transformation matrix between each three-dimensional volume data, the local three-dimensional image of the target object in each orientation can be The volume data is fused to obtain the global three-dimensional volume data of the target object. In this way, the global three-dimensional volume data of the entire target object and its surrounding areas can be directly obtained, which can better give the organizational structure of the entire target object area and surrounding areas.
实施例二Embodiment 2
本发明实施例与上述实施例中各个可选方案可以结合。在本发明实施例中，具体介绍各三维体数据中特征点的提取，以及各三维体数据中各特征点之间的对应关系。The embodiment of the present invention can be combined with each optional solution in the above embodiment. In the embodiment of the present invention, the extraction of feature points in each three-dimensional volume data and the corresponding relationship between each feature point in each three-dimensional volume data are specifically introduced.
在提取各三维体数据中的至少三个特征点，并确定各所述三维体数据中的各特征点之间的对应关系，具体可以有如下两种方式：There are two specific methods for extracting at least three feature points from each three-dimensional volume data and determining the corresponding relationship between the feature points in each three-dimensional volume data:
(1)对于任一三维体数据，确定各三维体数据中满足预设条件的至少三个特征点；基于任意两个三维体数据中各特征点之间的单射关系，确定各三维体数据中的各特征点之间的对应关系。(1) For any three-dimensional volume data, determine at least three feature points in each three-dimensional volume data that meet the preset conditions; based on the injective relationship between each feature point in any two three-dimensional volume data, determine each three-dimensional volume data Correspondence between feature points in .
示例性的，对于任一方位的三维体数据而言，可将该三维体数据中的满足预设条件的至少三个体数据点抽取出来作为特征点。For example, for three-dimensional volume data in any orientation, at least three volume data points that meet preset conditions in the three-dimensional volume data can be extracted as feature points.
这里的预设条件可以是预先设置的一个条件，例如，任选一个方位的三维体数据，将该方位的三维体数据对应的图像求出其对应的高斯差分图像，然后求出高斯差分图像中的极值点的位置，即为特征点。这里的预设条件即为差分极值点。The preset condition here can be a condition set in advance, for example, select three-dimensional volume data at any orientation, calculate the corresponding Gaussian difference image from the image corresponding to the three-dimensional volume data at that orientation, and then calculate the Gaussian difference image. The location of the extreme point is the feature point. The preset condition here is the differential extreme point.
根据上述的方式可将各方位的三维体数据中的特征点均提取出来。According to the above method, feature points in the three-dimensional volume data in all directions can be extracted.
需要说明的是，上述预设条件只是一种可行的条件，还可以有其他可行的条件，这里不一一列举，但本领域技术人员应该明确，任何可提取出特征点的预设条件均属于本发明实施例的保护范围。It should be noted that the above preset condition is only a feasible condition, and there can be other feasible conditions, which are not listed here. However, those skilled in the art should make it clear that any preset condition that can extract feature points belongs to protection scope of the embodiments of the present invention.
当基于上述方式提取出特征点后，各特征点之间并不是一一对应的，这时需确定各三维体数据中各特征点之间的对应关系。具体的方式可以是基于任意两个三维体数据中各特征点之间的单射关系，确定各所述三维体数据中的各特征点之间的对应关系。After the feature points are extracted based on the above method, there is no one-to-one correspondence between the feature points. In this case, it is necessary to determine the correspondence between the feature points in each three-dimensional volume data. A specific method may be to determine the corresponding relationship between the feature points in each of the three-dimensional volume data based on the injective relationship between the feature points in any two three-dimensional volume data.
可选的，所述基于任意两个三维体数据中各特征点之间的单射关系，确定各所述三维体数据中的各特征点之间的对应关系，具体可以是：对于任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据，执行如下步骤，确定各所述三维体数据中的各特征点之间的对应关系：确定第一三维体数据中的各特征点到第二三维体数据中的各特征点的第一单映射值；确定所述第二三维体数据中的各特征点到所述第一三维体数据中的各特征点的第二单映射值；若所述第一单映射值与所述第二单映射值满足满射关系，则满足满射关系的两个特征点为具有对应关系的特征点。Optionally, based on the injective relationship between each feature point in any two three-dimensional volume data, determine the corresponding relationship between each feature point in each of the three-dimensional volume data. Specifically, it can be: for any two For the three-dimensional volume data of the orientation, use the three-dimensional volume data of one orientation as the first three-dimensional volume data, and use the three-dimensional volume data of the other orientation as the second three-dimensional volume data. Perform the following steps to determine each of the three-dimensional volume data. Correspondence between feature points: determine a first single mapping value from each feature point in the first three-dimensional volume data to each feature point in the second three-dimensional volume data; determine each feature point in the second three-dimensional volume data to the second single mapping value of each feature point in the first three-dimensional volume data; if the first single mapping value and the second single mapping value satisfy the surjective relationship, then the two features that satisfy the surjective relationship Points are feature points with corresponding relationships.
示例性的，对于任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据。Exemplarily, for any two orientations of three-dimensional volume data, the three-dimensional volume data in one orientation is used as the first three-dimensional volume data, and the three-dimensional volume data in the other orientation is used as the second three-dimensional volume data.
第一单映射值可以是第一三维体数据中的各特征点到第二三维体数据中的各特征点的映射值。The first single mapping value may be a mapping value from each feature point in the first three-dimensional volume data to each feature point in the second three-dimensional volume data.
第二单映射值可以是第二三维体数据中的各特征点到第一三维体数据中的各特征点的映射值。The second single mapping value may be a mapping value from each feature point in the second three-dimensional volume data to each feature point in the first three-dimensional volume data.
如图7所述的各三维体数据中的各特征点之间的对应关系确定示意图，其中A为第一三维体数据，B为第二三维体数据，A中的1、2、3、……、n是第一三维体数据中的各特征点，B中的1’、2’、3’、……、n’是第二三维体数据中的各特征点。As shown in Figure 7, the schematic diagram of determining the corresponding relationship between each feature point in each three-dimensional volume data, where A is the first three-dimensional volume data, B is the second three-dimensional volume data, and 1, 2, 3,... in A are ..., n is each feature point in the first three-dimensional volume data, and 1', 2', 3',..., n' in B are each feature point in the second three-dimensional volume data.
确定第一三维体数据中的各特征点到第二三维体数据中的各特征点的第一单映射值。具体的，如图7所示，可以是确定A中的1分别到B中的1’、2’、3’、……、n’的映射值，A中的2分别到B中的1’、2’、3’、……、n’的映射值，依次类推，确定出A中的各特征点分别到B中的各特征点的第一单映射值。Determine the first single mapping value of each feature point in the first three-dimensional volume data to each feature point in the second three-dimensional volume data. Specifically, as shown in FIG7 , the mapping values of 1 in A to 1', 2', 3', ..., n' in B can be determined, and the mapping values of 2 in A to 1', 2', 3', ..., n' in B can be determined, and so on, to determine the first single mapping value of each feature point in A to each feature point in B.
对应的，确定第二三维体数据中的各特征点到第一三维体数据中的各特征点的第二单映射值。具体的，如图7所示，可以是确定B中的1’分别到A中的1、2、3、……、n的映射值，B中的2’分别到A中的1、2、3、……、n的映射值，依次类推，确定出B中的各特征点分别到A中的各特征点的第二单映射值。Correspondingly, the second single mapping value of each feature point in the second three-dimensional volume data to each feature point in the first three-dimensional volume data is determined. Specifically, as shown in FIG7 , the mapping values of 1' in B to 1, 2, 3, ..., n in A can be determined, and the mapping values of 2' in B to 1, 2, 3, ..., n in A can be determined, and so on, to determine the second single mapping values of each feature point in B to each feature point in A.
若第一单映射值与第二单映射值满足满射关系，则确定具有满射关系的两个特征点为具有对应关系的特征点。If the first single mapping value and the second single mapping value satisfy a surjective relationship, then the two feature points having the surjective relationship are determined to be feature points having a corresponding relationship.
具体的例如，如图7所示，A中的1到B中的1’的第一单映射值，与B中的1’到A中的1的第二单映射值满足满射关系，则A中的1与B中的1’具有对应关系。A中的2到B中的2’的第一单映射值，与B中的2’到A中的2的第二单映射值不满足满射关系，则A中的2与B中的2’不具有对应关系。即A中的各特征点与B中的各特征点具有唯一的一一对应关系。For example, as shown in Figure 7, the first single mapping value from 1 in A to 1' in B and the second single mapping value from 1' in B to 1 in A satisfy a surjective relationship, then 1 in A has a corresponding relationship with 1' in B. The first single mapping value from 2 in A to 2' in B and the second single mapping value from 2' in B to 2 in A do not satisfy the surjective relationship, then 2 in A and 2 in B 'There is no corresponding relationship. That is, each feature point in A has a unique one-to-one correspondence with each feature point in B.
(2)基于任意两个三维体数据，首先基于预先设置的至少一个特征信息，在各三维体数据中进行特征匹配，确定各三维体数据中特征信息对应的至少一个特征点，将不同三维体数据中相同特征信息对应的各特征点之间设置对应关系；其次确定各所述三维体数据中满足预设条件的至少两个特征点，基于任意两个三维体数据中各特征点之间的单射关系，确定各所述三维体数据中的各特征点之间的对应关系。(2) Based on any two three-dimensional volume data, firstly, based on at least one feature information set in advance, feature matching is performed in each three-dimensional volume data, at least one feature point corresponding to the feature information in each three-dimensional volume data is determined, and a corresponding relationship is set between each feature point corresponding to the same feature information in different three-dimensional volume data; secondly, at least two feature points that meet preset conditions are determined in each of the three-dimensional volume data, and based on the single-shot relationship between each feature point in any two three-dimensional volume data, the corresponding relationship between each feature point in each of the three-dimensional volume data is determined.
示例性的，特征信息可以是预先设置的特征点的特征信息。For example, the feature information may be feature information of preset feature points.
具体的例如，以在各三维体数据中各获取到的特征点为三个为例，以图2中的目标对象为乳房为例，获取了AP、LAT和MED三个方位的三维体数据，由于目标对象明确(即是乳房)，则在这三个方位的三维体数据的共同区域为乳头区域，即这里的特征信息可以是乳头。For example, taking the three feature points obtained in each three-dimensional volume data as an example, and taking the target object in Figure 2 as the breast as an example, three-dimensional volume data in three directions of AP, LAT and MED are obtained. Since the target object is clear (that is, the breast), the common area of the three-dimensional volume data in these three directions is the nipple area, that is, the feature information here can be the nipple.
有乳头区域明确后，乳头区域的位置也就明确了，将各方位的三维体数据与乳头区域(特征信息)的体数据点进行匹配，则可确定各方位的三维体数据中的一个特征点。Once the nipple region is identified, the location of the nipple region is also identified. By matching the three-dimensional volume data in various directions with the volume data points of the nipple region (feature information), a feature point in the three-dimensional volume data in various directions can be determined.
由于乳头区域是明确的，在确定各方位的三维体数据中的这一个特征点的过程中，各方位的三维体数据中的这一个特征点之间的对应关系也就对应确定，即可直接设置不同三维体数据中相同特征信息对应的这一个特征点之间的对应关系。Since the nipple area is clear, in the process of determining the feature point in the three-dimensional data of various orientations, the correspondence between the feature points in the three-dimensional data of various orientations is also determined accordingly, and the correspondence between the feature points corresponding to the same feature information in different three-dimensional data can be directly set.
具体的可以是，在获取AP、LAT和MED三个方位的三维体数据之前，医生会标记出每个方位的三维体数据中的如图的位置，所以，相邻两个方位的三维体数据中乳头位置，可以作为一对对应特征点。Specifically, before obtaining the three-dimensional volume data of AP, LAT and MED, the doctor will mark the position as shown in the figure in the three-dimensional volume data of each direction. Therefore, the three-dimensional volume data of two adjacent directions are The central nipple position can be used as a pair of corresponding feature points.
在基于特征信息获取到一个特征点后，再利用上述的方式(1)基于预设条件可获取到另外两个特征点，将这两个特征点基于上述的方式(1)可确定其对应关系。After obtaining one feature point based on the feature information, the other two feature points can be obtained based on the preset conditions using the above method (1), and their corresponding relationship can be determined based on the two feature points based on the above method (1). .
这样即可找到各三维体数据中的三个特征点，以及各三维体数据中的三个特征点之间的对应关系。In this way, the three feature points in each three-dimensional volume data and the corresponding relationship between the three feature points in each three-dimensional volume data can be found.
即这里可以是根据预先设置的至少一个特征信息，例如可以是乳头区域信息，基于乳头区域信息确定其中的一个特征点，当特征了该特征点后，也就确定了该特征点的对应关系。然后再基于上述的方式(1)将满足预设条件(例如可以是满足差分图像极值点)的两个特征点确定为剩下的两个特征点，然后基于方式(1)可确定各三维体数据中这两个特征点之间的对应关系。这样即可确定各方位的三维体数据中的至少三个特征点，以及各方位的三维体数据中的至少三个特征点之间的对应关系。That is, one of the feature points may be determined based on at least one preset feature information, such as nipple area information. After the feature point is characterized, the corresponding relationship of the feature point is determined. Then based on the above method (1), the two feature points that meet the preset conditions (for example, they can meet the extreme points of the differential image) are determined as the remaining two feature points, and then based on the method (1), each three-dimensional Correspondence between these two feature points in volume data. In this way, at least three feature points in the three-dimensional volume data at each orientation can be determined, and the corresponding relationship between at least three feature points in the three-dimensional volume data at each orientation can be determined.
这样通过上述两种方式可确定各方位的三维体数据中的各特征点，并确定了各三维体数据中的各特征点之间的对应关系，这样以便后续基于各三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵，以便各方位的三维体数据进行融合，得到目标对象的全局三维体数据。In this way, through the above two methods, each feature point in the three-dimensional volume data at each orientation can be determined, and the corresponding relationship between each feature point in each three-dimensional volume data can be determined, so that subsequent work can be based on each feature in each three-dimensional volume data. The correspondence relationship between points determines the transformation matrix between the three-dimensional volume data of each orientation, so that the three-dimensional volume data of each orientation can be fused to obtain the global three-dimensional volume data of the target object.
需要说明的是，上述的两种确定各方位的三维体数据中的各特征点，并确定了各三维体数据中的各特征点之间的对应关系的方法，用户可根据需求自行选取其中的一种方式或两种方式，这里不做限定。当然，用户也可同时选取这两种方式。It should be noted that the above two methods of determining the feature points in the three-dimensional volume data of each orientation and determining the corresponding relationship between the feature points in each three-dimensional volume data, the user can select one or both of the methods according to the needs, and there is no limitation here. Of course, the user can also select both methods at the same time.
需要说明的是，在确定各三维体数据中的至少三个特征点，以及各三维体数据中的至少三个特征点之间的对应关系时，若选取上述的两种方式，则这两种方式的结果可相互映证，提高了特征点的确定精确性，以及各特征点之间的对应关系的精确性。It should be noted that when determining at least three feature points in each three-dimensional volume data and the correspondence between at least three feature points in each three-dimensional volume data, if the above two methods are selected, these two methods The results of the method can corroborate each other, which improves the accuracy of determining the feature points and the accuracy of the correspondence between the feature points.
本发明实施例的技术方案，通过确定各方位的三维体数据中的各特征点，并确定了各三维体数据中的各特征点之间的对应关系的方法，以便后续基于各三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵，以便各方位的三维体数据进行融合，得到目标对象的全局三维体数据。The technical solution of the embodiment of the present invention determines each feature point in the three-dimensional volume data at each position and determines the corresponding relationship between each feature point in each three-dimensional volume data, so that subsequent operations can be based on the three-dimensional volume data. The corresponding relationship between each feature point is determined, and the transformation matrix between the three-dimensional volume data of each orientation is determined so that the three-dimensional volume data of each orientation can be fused to obtain the global three-dimensional volume data of the target object.
实施例三Embodiment 3
图8为本发明实施例三提供的数据处理装置的结构示意图，如图8所示，该装置包括：信息获取模块31、变换矩阵确定模块32和数据融合模块33。Figure 8 is a schematic structural diagram of a data processing device provided in Embodiment 3 of the present invention. As shown in Figure 8, the device includes: an information acquisition module 31, a transformation matrix determination module 32 and a data fusion module 33.
其中，信息获取模块31，用于获取目标对象的至少两个方位的三维体数据，分别提取各所述三维体数据中的至少三个特征点，并确定各所述三维体数据中的各特征点之间的对应关系；Among them, the information acquisition module 31 is used to obtain three-dimensional volume data of at least two directions of the target object, respectively extract at least three feature points in each of the three-dimensional volume data, and determine each feature in each of the three-dimensional volume data. Correspondence between points;
变换矩阵确定模块32，用于基于各所述三维体数据中的各特征点之间的对应关系，确定各方位的三维体数据之间的变换矩阵；The transformation matrix determination module 32 is used to determine the transformation matrix between the three-dimensional volume data in each direction based on the correspondence between the feature points in each of the three-dimensional volume data;
数据融合模块33，用于基于各所述三维体数据之间的变换矩阵，将各方位的所述三维体数据进行融合，得到所述目标对象的融合三维体数据。The data fusion module 33 is used to fuse the three-dimensional volume data in each direction based on the transformation matrix between the three-dimensional volume data to obtain the fused three-dimensional volume data of the target object.
在上述实施例的技术方案的基础上，信息获取模块31包括：Based on the technical solutions of the above embodiments, the information acquisition module 31 includes:
第一对应关系确定单元，用于基于预先设置的至少一个特征信息，在各所述三维体数据中进行特征匹配，确定各所述三维体数据中所述特征信息对应的至少三个特征点；将不同三维体数据中相同特征信息对应的各特征点之间设置对应关系；A first correspondence determination unit configured to perform feature matching in each of the three-dimensional volume data based on at least one preset feature information, and determine at least three feature points corresponding to the feature information in each of the three-dimensional volume data; Set corresponding relationships between feature points corresponding to the same feature information in different three-dimensional volume data;
第二对应关系确定单元，用于确定各所述三维体数据中满足预设条件的至少两个特征点；基于任意两个三维体数据中各特征点之间的单射关系，确定各所述三维体数据中的各特征点之间的对应关系。The second correspondence relationship determination unit is used to determine at least two feature points in each of the three-dimensional volume data that meet the preset conditions; based on the injective relationship between the feature points in any two three-dimensional volume data, determine each of the three-dimensional volume data. Correspondence between feature points in three-dimensional volume data.
在上述实施例的技术方案的基础上，信息获取模块31还可以包括：Based on the technical solutions of the above embodiments, the information acquisition module 31 may also include:
第三对应关系确定单元，用于对于任一三维体数据，确定各所述三维体数据中满足预设条件的至少三个特征点；用于基于任意两个三维体数据中各特征点之间的单射关系，确定各所述三维体数据中的各特征点之间的对应关系。The third correspondence determination unit is used to determine, for any three-dimensional volume data, at least three feature points that meet the preset conditions in each of the three-dimensional volume data; and is used to determine the relationship between the feature points in any two three-dimensional volume data based on The injective relationship determines the corresponding relationship between each feature point in each of the three-dimensional volume data.
在上述实施例的技术方案的基础上，第二对应关系确定单元或第三对应关系确定单元包括：Based on the technical solutions of the above embodiments, the second correspondence determination unit or the third correspondence determination unit includes:
第一单映射值确定子单元，用于对于任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据，确定第一三维体数据中的各特征点到第二三维体数据中的各特征点的第一单映射值；a first single mapping value determining subunit, for determining, for any two orientations of three-dimensional volume data, a first single mapping value from each feature point in the first three-dimensional volume data to each feature point in the second three-dimensional volume data by taking the three-dimensional volume data in one orientation as the first three-dimensional volume data and taking the three-dimensional volume data in the other orientation as the second three-dimensional volume data;
第二单映射值确定子单元，用于对于任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据，确定所述第二三维体数据中的各特征点到所述第一三维体数据中的各特征点的第二单映射值；The second single mapping value determination subunit is used to use the three-dimensional volume data of any two orientations as the first three-dimensional volume data and the three-dimensional volume data of the other orientation as the second three-dimensional volume data. , determine a second single mapping value from each feature point in the second three-dimensional volume data to each feature point in the first three-dimensional volume data;
对应关系确定子单元，用于若所述第一单映射值与所述第二单映射值满足满射关系，则满足满射关系的两个特征点为具有对应关系的特征点。The corresponding relationship determining subunit is used for, if the first single mapping value and the second single mapping value satisfy a surjective relationship, then the two feature points satisfying the surjective relationship are feature points having a corresponding relationship.
在上述实施例的技术方案的基础上，变换矩阵确定模块32具体用于：Based on the technical solutions of the above embodiments, the transformation matrix determination module 32 is specifically used to:
对于目标对象的任意两个方位的三维体数据，将其中一个方位的三维体数据作为第一三维体数据，将另一方位的三维体数据作为第二三维体数据，基于两个方位的三维体数据中的各特征点之间的对应关系，根据如下公式，确定两个方位的三维体数据之间的变换矩阵：For the three-dimensional volume data of any two directions of the target object, the three-dimensional volume data of one direction is used as the first three-dimensional volume data, and the three-dimensional volume data of the other direction is used as the second three-dimensional volume data. Based on the three-dimensional volume data of the two directions, The correspondence between each feature point in the data determines the transformation matrix between the three-dimensional volume data in two directions according to the following formula:
其中，为所述目标对象的第一三维体数据中与第二三维体数据中的特征点具有对应关系的特征点，/>为所述目标对象的第二三维体数据中与第一三维体数据中的特征点具有对应关系的特征点，/>和/>中的点一一对应，j＝1，2，3...n，T为变换矩阵；T*为最小时，T的值。in, are the feature points in the first three-dimensional volume data of the target object that have a corresponding relationship with the feature points in the second three-dimensional volume data,/> are the feature points in the second three-dimensional volume data of the target object that have a corresponding relationship with the feature points in the first three-dimensional volume data,/> and/> The points in are in one-to-one correspondence, j=1, 2, 3...n, T is the transformation matrix; T* is At minimum, the value of T.
在上述实施例的技术方案的基础上，数据融合模块33具体用于：Based on the technical solution of the above embodiment, the data fusion module 33 is specifically used for:
对于目标对象的任意两个方位的三维体数据，将其中一个方位的三维体数据作为基准三维体数据，另一方位的三维体数据作为待配准三维体数据；基于两个方位的三维体数据之间的变换矩阵，将待配准三维体数据的坐标映射到基准三维体数据的坐标系中，将两个方位的所述三维体数据进行融合。For the three-dimensional volume data of any two orientations of the target object, the three-dimensional volume data of one orientation is used as the reference three-dimensional volume data, and the three-dimensional volume data of the other orientation is used as the three-dimensional volume data to be registered; based on the three-dimensional volume data of the two orientations The transformation matrix between them maps the coordinates of the three-dimensional volume data to be registered to the coordinate system of the reference three-dimensional volume data, and fuses the three-dimensional volume data in two directions.
在上述实施例的技术方案的基础上，信息获取模块31还可以包括：Based on the technical solutions of the above embodiments, the information acquisition module 31 may also include:
标识符添加单元，用于给各所述三维体数据中的各特征点添加标识符。The identifier adding unit is used to add an identifier to each feature point in the three-dimensional volume data.
本发明实施例所提供的数据处理装置可执行本发明任意实施例所提供的数据处理方法，具备执行方法相应的功能模块和有益效果。The data processing device provided in the embodiment of the present invention can execute the data processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
实施例四Embodiment 4
图9为本发明实施例四提供的一种电子设备的结构示意图，如图9所示，该电子设备包括处理器70、存储器71、输入装置72和输出装置73；电子设备中处理器70的数量可以是一个或多个，图9中以一个处理器70为例；电子设备中的处理器70、存储器71、输入装置72和输出装置73可以通过总线或其他方式连接，图9中以通过总线连接为例。Figure 9 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention. As shown in Figure 9, the electronic device includes a processor 70, a memory 71, an input device 72 and an output device 73; The number may be one or more. In Figure 9 , one processor 70 is taken as an example. The processor 70 , memory 71 , input device 72 and output device 73 in the electronic device may be connected through a bus or other means. In Figure 9 , a processor 70 is used as an example. Take bus connection as an example.
存储器71作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序以及模块，如本发明实施例中的数据处理方法对应的程序指令/模块(例如，信息获取模块31、变换矩阵确定模块32和数据融合模块33)。处理器70通过运行存储在存储器71中的软件程序、指令以及模块，从而执行电子设备的各种功能应用以及数据处理，即实现上述的数据处理方法。As a computer-readable storage medium, the memory 71 can be used to store software programs, computer-executable programs and modules, such as program instructions/modules corresponding to the data processing method in the embodiment of the present invention (for example, information acquisition module 31, transformation matrix Determination module 32 and data fusion module 33). The processor 70 executes software programs, instructions and modules stored in the memory 71 to execute various functional applications and data processing of the electronic device, that is, to implement the above-mentioned data processing method.
存储器71可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器71可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器71可进一步包括相对于处理器70远程设置的存储器，这些远程存储器可以通过网络连接至电子设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。The memory 71 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system and at least one application program required for a function; the stored data area may store data created according to the use of the terminal, etc. In addition, the memory 71 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 71 may further include memory located remotely relative to processor 70 , and these remote memories may be connected to the electronic device through a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks and combinations thereof.
输入装置72可用于接收输入的数字或字符信息，以及产生与电子设备的用户设置以及功能控制有关的键信号输入。输出装置73可包括显示屏等显示设备。The input device 72 may be used to receive inputted numeric or character information and to generate key signal inputs related to user settings and function control of the electronic device. The output device 73 may include a display device such as a display screen.
实施例五Embodiment 5
本发明实施例五还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种数据处理方法。Embodiment 5 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a data processing method when executed by a computer processor.
当然,本发明实施例所提供的一种包含计算机可执行指令的存储介质,其计算机可执行指令不限于如上所述的方法操作,还可以执行本发明任意实施例所提供的数据处理方法中的相关操作。Of course, the embodiments of the present invention provide a storage medium containing computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and can also perform the data processing methods provided by any embodiment of the present invention. Related operations.
通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到，本发明可借助软件及必需的通用硬件来实现，当然也可以通过硬件实现，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(RandomAccess Memory,RAM)、闪存(FLASH)、硬盘或光盘等，包括若干指令用以使得一台计算机电子设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述的方法。From the above description of the implementation, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware. Of course, it can also be implemented with hardware, but in many cases the former is a better implementation. . Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence or that contributes to the existing technology. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk. , read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions to make a computer electronic device (which can be a personal computer , server, or network device, etc.) to perform the methods described in various embodiments of the present invention.
值得注意的是，上述数据处理装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各功能单元的具体名称也只是为了便于相互区分，并不用于限制本发明的保护范围。It is worth noting that in the embodiment of the above-mentioned data processing device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
注意，上述仅为本发明的较佳实施例及所运用技术原理。本领域技术人员会理解，本发明不限于这里所述的特定实施例，对本领域技术人员来说能够进行各种明显的变化、重新调整和替代而不会脱离本发明的保护范围。因此，虽然通过以上实施例对本发明进行了较为详细的说明，但是本发明不仅仅限于以上实施例，在不脱离本发明构思的情况下，还可以包括更多其他等效实施例，而本发明的范围由所附的权利要求范围决定。Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011541156.2ACN112598808B (en) | 2020-12-23 | 2020-12-23 | Data processing method, device, electronic equipment and storage medium |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011541156.2ACN112598808B (en) | 2020-12-23 | 2020-12-23 | Data processing method, device, electronic equipment and storage medium |
| Publication Number | Publication Date |
|---|---|
| CN112598808A CN112598808A (en) | 2021-04-02 |
| CN112598808Btrue CN112598808B (en) | 2024-04-02 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011541156.2AActiveCN112598808B (en) | 2020-12-23 | 2020-12-23 | Data processing method, device, electronic equipment and storage medium |
| Country | Link |
|---|---|
| CN (1) | CN112598808B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115965570A (en)* | 2021-10-13 | 2023-04-14 | 青岛海信医疗设备股份有限公司 | Method for generating three-dimensional panorama of ultrasonic breast and ultrasonic equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1317146A2 (en)* | 2001-12-03 | 2003-06-04 | Monolith Co., Ltd. | Image matching method and apparatus |
| JP2009020761A (en)* | 2007-07-12 | 2009-01-29 | Toshiba Corp | Image processing apparatus and method |
| EP2575106A1 (en)* | 2011-09-30 | 2013-04-03 | BrainLAB AG | Method and device for displaying changes in medical image data |
| JP2014150855A (en)* | 2013-02-06 | 2014-08-25 | Mitsubishi Electric Corp | Breast diagnosis assist system and breast data processing method |
| EP3276575A1 (en)* | 2016-07-25 | 2018-01-31 | Nuctech Company Limited | Method, apparatus and system for reconstructing images of 3d surface |
| CN108573532A (en)* | 2018-04-16 | 2018-09-25 | 北京市神经外科研究所 | A kind of methods of exhibiting and device, computer storage media of mixed model |
| CN109087382A (en)* | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN111325779A (en)* | 2020-02-07 | 2020-06-23 | 贝壳技术有限公司 | Point cloud registration method and device, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8090429B2 (en)* | 2004-06-30 | 2012-01-03 | Siemens Medical Solutions Usa, Inc. | Systems and methods for localized image registration and fusion |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1317146A2 (en)* | 2001-12-03 | 2003-06-04 | Monolith Co., Ltd. | Image matching method and apparatus |
| JP2009020761A (en)* | 2007-07-12 | 2009-01-29 | Toshiba Corp | Image processing apparatus and method |
| EP2575106A1 (en)* | 2011-09-30 | 2013-04-03 | BrainLAB AG | Method and device for displaying changes in medical image data |
| JP2014150855A (en)* | 2013-02-06 | 2014-08-25 | Mitsubishi Electric Corp | Breast diagnosis assist system and breast data processing method |
| EP3276575A1 (en)* | 2016-07-25 | 2018-01-31 | Nuctech Company Limited | Method, apparatus and system for reconstructing images of 3d surface |
| CN108573532A (en)* | 2018-04-16 | 2018-09-25 | 北京市神经外科研究所 | A kind of methods of exhibiting and device, computer storage media of mixed model |
| CN109087382A (en)* | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN111325779A (en)* | 2020-02-07 | 2020-06-23 | 贝壳技术有限公司 | Point cloud registration method and device, electronic equipment and storage medium |
| Publication number | Publication date |
|---|---|
| CN112598808A (en) | 2021-04-02 |
| Publication | Publication Date | Title |
|---|---|---|
| CN108520519B (en) | Image processing method and device and computer readable storage medium | |
| KR102018565B1 (en) | Method, apparatus and program for constructing surgical simulation information | |
| CN109754396B (en) | Image registration method, apparatus, computer equipment and storage medium | |
| CN107909622B (en) | Model generation method, medical imaging scanning planning method and medical imaging system | |
| US10607420B2 (en) | Methods of using an imaging apparatus in augmented reality, in medical imaging and nonmedical imaging | |
| CN110288653B (en) | A multi-angle ultrasound image fusion method, system and electronic device | |
| CN113397704B (en) | Robot positioning method, device, system and computer equipment | |
| CN104424647A (en) | Method and apparatus for registering medical images | |
| EP3910592A1 (en) | Image matching method, apparatus and device, and storage medium | |
| US20190290241A1 (en) | Correcting probe induced deformation in an ultrasound fusing imaging system | |
| CN115187550B (en) | Target registration method, device, equipment, storage medium and program product | |
| CN117731322A (en) | Ultrasonic imaging method, device and readable storage medium | |
| CN106157282A (en) | Image processing system and method | |
| US10621728B2 (en) | Internal organ localization in computed tomography (CT) images | |
| JP6944492B2 (en) | Image acquisition method, related equipment and readable storage medium | |
| WO2023246521A1 (en) | Method, apparatus and electronic device for lesion localization based on mixed reality | |
| CN112598808B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN114155150A (en) | Image stitching method and device applied to large parallax scene | |
| CN116091516A (en) | Medical image registration method, medical image system and ultrasonic imaging system | |
| CN108670302B (en) | A 3D structure reconstruction method of spine based on 2.5D ultrasound wide-field imaging | |
| CN115619790A (en) | Mixed perspective method, system and equipment based on binocular positioning | |
| CN109934798A (en) | Internal object information labeling method and device, electronic equipment, storage medium | |
| WO2023232129A1 (en) | Three-dimensional-model processing method and apparatus, and electronic device | |
| CN113658106B (en) | An automatic diagnosis system for liver lesions based on abdominal enhanced CT | |
| CN112767415B (en) | Chest scanning area automatic determination method, device, equipment and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |