本申请涉及医疗器械，尤其涉及介入器械的运动规划方法、系统、程序单元和存储介质。The present application relates to medical devices, and in particular to a motion planning method, system, program unit and storage medium for interventional devices.
介入治疗学是介入放射学的重要部分，它以影像诊断为基础，通过医学影像设备的引导，利用导管、穿刺针和其他介入器材，以达到治疗疾病的目的。Interventional therapy is an important part of interventional radiology. It is based on imaging diagnosis and uses catheters, puncture needles and other interventional equipment under the guidance of medical imaging equipment to achieve the purpose of treating diseases.
介入治疗涉及范围广，可以用来治疗血管性疾病，包括动静脉狭窄及闭塞性疾病、主动脉夹层、腹主动脉瘤、急性动脉出血性疾病、门脉高压、颅内血管疾病以及非血管性疾病，包括良、恶性肿瘤的治疗、原发性肝癌、肺癌、胰腺癌、子宫肌瘤等。Interventional therapy covers a wide range and can be used to treat vascular diseases, including arteriovenous stenosis and occlusive diseases, aortic dissection, abdominal aortic aneurysm, acute arterial hemorrhagic disease, portal hypertension, intracranial vascular disease and non-vascular diseases, including the treatment of benign and malignant tumors, primary liver cancer, lung cancer, pancreatic cancer, uterine fibroids, etc.
介入治疗相比外科手术大大降低了手术危险以及对器官、组织的损伤程度，达到局部治疗的目的。Compared with surgical operations, interventional therapy greatly reduces surgical risks and the degree of damage to organs and tissues, achieving the purpose of local treatment.
在进行介入手术的过程中，需要依据不同的手术目的，在手术操作前需要规划介入器械的路线。现有技术一般采用医生根据经验确定介入器械的行进路线。During the interventional surgery, the route of the interventional device needs to be planned before the operation according to different surgical purposes. In the prior art, doctors generally determine the route of the interventional device based on their experience.
发明内容Summary of the invention
本申请实施例提供介入器械的运动规划方法、系统、程序单元和存储介质，以解决相关技术存在的问题，技术方案如下：The embodiments of the present application provide a motion planning method, system, program unit and storage medium for an interventional device to solve the problems existing in the related technologies. The technical solutions are as follows:
介入器械的运动规划方法，包括以下步骤：The motion planning method of the interventional device comprises the following steps:
S01：提取组织结构中的可移动通道；S01: Extraction of movable pathways in tissue structures;
S02：确定目标操作节点在可移动通道中的表征；S02: Determine the representation of the target operation node in the movable channel;
S03：根据所述表征规划介入器械的运动。S03: Planning the movement of the interventional instrument according to the representation.
可选地，所述运动包括路径规划和轨迹规划；Optionally, the movement includes path planning and trajectory planning;
所述路径规划为空间路径，为自初始操作节点到达目标操作节点位置的路线；所述轨迹规划为时空路径，在时间维度上的表征为根据组织结构内运动状态规划介入器械的运动，在空间维度上的表征为自初始操作节点到达目标操作节点位置的路线。The path planning is a spatial path, which is the path from the initial operation node to the target operation node. The trajectory planning is a space-time path, which is characterized in the time dimension by planning the movement of the interventional device according to the motion state in the tissue structure, and in the space dimension by the route from the initial operation node to the target operation node position.
可选地，所述时空路径具体为根据分析组织结构内运动得到内运动的循环周期，根据循环周期规划介入器械的运动。Optionally, the space-time path is specifically a cycle of internal movement obtained by analyzing the internal movement of the tissue structure, and the movement of the interventional instrument is planned according to the cycle.
可选地，所述确定起始点、目标操作节点在可移动通道中的表征包括位置，以及姿态、速度、加速度中的一种或多种。Optionally, the determination of the starting point and the representation of the target operation node in the movable channel includes position, and one or more of posture, speed, and acceleration.
可选地，步骤S01中，所述组织结构以空间模型表征，所述可移动通道为组织结构空间模型中最靠近内表面中心线的内轮廓。Optionally, in step S01, the tissue structure is represented by a spatial model, and the movable channel is an inner contour closest to the center line of the inner surface in the spatial model of the tissue structure.
可选地，所述组织结构为血管，所述可移动通道为血管内剔除掉损伤空间区域后的空间区域，所述损伤区域包括但不限于夹层、钙化、动脉瘤、斑块。Optionally, the tissue structure is a blood vessel, and the movable channel is a spatial region in the blood vessel after removing a damaged spatial region, and the damaged region includes but is not limited to dissection, calcification, aneurysm, and plaque.
可选地，所述时空路径具体为根据分析组织结构内运动得到内运动的循环周期，根据循环周期规划介入器械的运动：在血管平滑肌收缩状态下，血管管腔收窄时，控制介入器械停止或控制介入器械降低移动速度或控制介入器械降低加速度；在血管平滑肌舒张状态下，血管管腔舒张时，控制介入器械启动或控制介入器械提高移动速度或控制介入器械提高加速度。Optionally, the space-time path is specifically a cycle of internal movement obtained by analyzing the movement within the tissue structure, and the movement of the interventional device is planned according to the cycle: when the vascular smooth muscle is in a contraction state and the vascular lumen is narrowed, the interventional device is controlled to stop or the interventional device is controlled to reduce the moving speed or the interventional device is controlled to reduce the acceleration; when the vascular smooth muscle is in a relaxation state and the vascular lumen is relaxed, the interventional device is controlled to start or the interventional device is controlled to increase the moving speed or the interventional device is controlled to increase the acceleration.
可选地，所述可移动通道中规划自初始操作节点到达目标操作节点位置的路线，包括以下步骤：确定目标操作节点在可移动通道中的位置；模拟所述介入器械在所述可移动通道中的运动轨迹，生成初始规划路径；根据规划路径生成执行指令，直至所述介入器械完成目标操作节点的执行指令；其中，所述初始规划路径的起点为初始操作节点，所述初始规划路径的终点为所述目标操作节点。Optionally, planning a route from an initial operation node to a target operation node in the movable channel comprises the following steps: determining the position of the target operation node in the movable channel; simulating the motion trajectory of the interventional device in the movable channel to generate an initial planned path; generating execution instructions according to the planned path until the interventional device completes the execution instructions of the target operation node; wherein the starting point of the initial planned path is the initial operation node, and the end point of the initial planned path is the target operation node.
可选地，还包括以下步骤：获取根据所述初始规划路径确定的初始操作节点；基于所述初始规划路径和所述初始操作节点所在关联路径节点的实时数据，生成形变场。Optionally, the method further includes the following steps: obtaining an initial operation node determined according to the initial planned path; and generating a deformation field based on the initial planned path and real-time data of associated path nodes where the initial operation node is located.
可选地，还包括：根据所述形变场生成执行指令，包括以下步骤：根据所述形变场生成第一运动数据；判断是否存在预设时间段内获取的第二运动数据，若存在，则配置所述第一运动数据和所述第二运动数据的权重，生成执行指令。Optionally, it also includes: generating an execution instruction according to the deformation field, including the following steps: generating first motion data according to the deformation field; determining whether there is second motion data acquired within a preset time period, and if so, configuring the weights of the first motion data and the second motion data to generate an execution instruction.
可选地，所述组织结构以空间模型表征的生成步骤为：确定进行组织结构模型数据融合的区域；根据所述区域，提取所述区域对应待生成融合模型的数据；其中，所述待生成融合模型的数据包括预制数据和/或实时数据；将所述预制数据和/或所述实时数据进行匹配，生成形变场；根据生成所述形变场的数据，生成用于介入手术的融合模型。Optionally, the steps for generating the spatial model representation of the tissue structure are: determining an area for tissue structure model data fusion; based on the area, extracting data of the fusion model to be generated corresponding to the area; wherein the data of the fusion model to be generated includes prefabricated data and/or real-time data; matching the prefabricated data and/or the real-time data to generate a deformation field; and generating a fusion model for interventional surgery based on the data for generating the deformation field.
可选地，生成所述待生成融合模型的数据的步骤，还包括：通过设置目标组织部分的特性生成至少一个划分阈值；根据所述至少一个划分阈值，将目标组织部分从所述待生成融合模型的数据中剥离出来，生成待划分图像；利用基于阈值的区域增长算法将所述待划分图像划分区域；去除各区域中的无关像素，得到各区域的关注图像；利用图割法，将所述各区域的关注图像拼接生成所述待生成融合模型的数据。Optionally, the step of generating the data of the fusion model to be generated also includes: generating at least one division threshold by setting the characteristics of the target tissue part; according to the at least one division threshold, separating the target tissue part from the data of the fusion model to be generated to generate an image to be divided; dividing the image to be divided into regions using a threshold-based region growing algorithm; removing irrelevant pixels in each region to obtain a focus image of each region; and using a graph cut method to splice the focus images of each region to generate the data of the fusion model to be generated.
可选地，通过设置目标组织部分的特性生成两个划分阈值：选择生长初始的种子点，在空间上对种子点周围邻域的像素进行搜索，选择相似像素生长，同时采用双阈值剔除无关像素；在原始图像中选取阈值范围[S1,S2]，取该范围内的中间值作为种子点平均值，从而对区域生长相似性准则进行约束：
|N-Nneed|＜μ|S1-S2|Optionally, two segmentation thresholds are generated by setting the characteristics of the target tissue part: the initial seed point of growth is selected, the pixels in the neighborhood around the seed point are searched spatially, similar pixels are selected for growth, and irrelevant pixels are eliminated by using double thresholds; a threshold range [S1 ,S2 ] is selected in the original image, and the middle value in the range is taken as the average value of the seed point, thereby constraining the similarity criterion of regional growth:
|NNneed |＜μ|S1 -S2 |
其中N表示灰度，μ是用以控制像素相似度的可调节参数，N为任一点，Nneed为种子点。获取树S和树T，搜索树S和树T的树T的生长，找到汇点，扩展树S和树T的边缘点，收集孤立点，恢复搜索树。Where N represents the grayscale, μ is an adjustable parameter to control pixel similarity, N is an arbitrary point, and Nneed is a seed point. Get tree S and tree T, search the growth of tree S and tree T, find the sink, expand the edge points of tree S and tree T, collect isolated points, and restore the search tree.
可选地，还包括以下步骤：通过设置目标组织部分的特性生成至少一个划分阈值，包括如下至少之一：根据所述目标组织部分的形状特点确定所述划分阈值；根据所述目标组织部分的损伤特征占目标组织部分的百分比设定所述划分阈值。Optionally, the method further includes the following steps: generating at least one division threshold by setting the characteristics of the target tissue portion, including at least one of the following: determining the division threshold according to the shape characteristics of the target tissue portion; setting the division threshold according to the percentage of the damage characteristics of the target tissue portion in the target tissue portion.
可选地，所述根据所述目标组织部分的形状特点确定所述划分阈值，具体为根据血管形状特点确定所述划分阈值；所述根据所述目标组织部分的损伤特征占目标组织部分的百分比设定所述划分阈值中，具体为目标组织部分的钙化点占目标组织部分的百分比设定所述划分阈值；所述根据血管形状特点确定所述划分阈值，用于提取血管区域；所述目标组织部分的钙化点占目标组织部分的百分比设定所述划分阈值，用于在血管区域分割钙化点。Optionally, the segmentation threshold is determined according to the shape characteristics of the target tissue portion, specifically, the segmentation threshold is determined according to the shape characteristics of the blood vessels; the segmentation threshold is set according to the percentage of the damage characteristics of the target tissue portion in the target tissue portion, specifically, the segmentation threshold is set according to the percentage of the calcification points in the target tissue portion in the target tissue portion; the segmentation threshold is determined according to the shape characteristics of the blood vessels, and is used to extract the blood vessel area; the calcification points in the target tissue portion account for the percentage of the target tissue portion. The division threshold is set as a percentage of , which is used to segment calcification points in the blood vessel area.
可选地，所述根据所述目标组织部分的损伤特征占目标组织部分的百分比设定所述划分阈值步骤：在分割钙化点之前对图像进行拉伸预处理：在[a,b]区间内做线性变换：
Optionally, the step of setting the segmentation threshold according to the percentage of the damage characteristics of the target tissue part to the target tissue part is as follows: performing stretching preprocessing on the image before segmenting the calcification points: performing linear transformation in the interval [a, b]:
其中图像灰度等级M；[d,c]为对[a,b]段灰度进行拉伸之后的灰度级；a，b，c，d是对原图进行灰度拉伸的调整因子；预处理后再进行Otsu分割，获得钙化点。The image grayscale level is M; [d, c] is the grayscale level after stretching the grayscale of the [a, b] segment; a, b, c, d are the adjustment factors for stretching the grayscale of the original image; after preprocessing, Otsu segmentation is performed to obtain calcification points.
可选地，获取预制数据，生成融合模型，还包括以下步骤：Optionally, obtaining prefabricated data and generating a fusion model further includes the following steps:
将所述预制地图数据根据腔体结构划分为至少一个数据块；将所述数据块作为输入，通过多层卷积神经网络来获取图像的特征；对所述特征进行筛选，将筛选后的特征组合生成融合模型。The prefabricated map data is divided into at least one data block according to the cavity structure; the data block is used as input to obtain image features through a multi-layer convolutional neural network; the features are screened, and the screened features are combined to generate a fusion model.
介入器械的运动规划系统，包括：感知模块，用于提取组织结构中的可移动通道；定位模块，用于确定目标操作节点在可移动通道中的表征；路径规划模块，用于根据所述表征规划介入器械的运动。The motion planning system of an interventional device includes: a perception module for extracting a movable channel in a tissue structure; a positioning module for determining the representation of a target operation node in the movable channel; and a path planning module for planning the motion of the interventional device according to the representation.
一种计算机程序单元，所述计算机程序单元当由处理单元运行时适于执行根据所述的方法的步骤。A computer program element, which, when run by a processing unit, is adapted to perform the steps according to the method described.
一种计算机可读介质，所述计算机可读介质上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行如上述的方法。A computer-readable medium stores computer program instructions, which, when executed by a processor, enable the processor to execute the above method.
上述技术方案中的优点或有益效果至少包括：The advantages or beneficial effects of the above technical solution include at least:
本发明通过规划介入器械运动路线的技术手段，解决了现有技术需要医生在全自动或半自动介入手术中，需要依靠个人经验为整台手术规划介入器械运动路线时存在的对医生要求高的技术问题，进而达到提高介入器械运动精准性，提高介入器械工作效率的技术效果。The present invention solves the technical problem that the prior art requires doctors to rely on personal experience to plan the movement route of the interventional instrument for the entire operation during fully automatic or semi-automatic interventional surgery through the technical means of planning the movement route of the interventional instrument, thereby achieving the technical effect of improving the movement accuracy of the interventional instrument and improving the working efficiency of the interventional instrument.
上述概述仅仅是为了说明书的目的，并不意图以任何方式进行限制。除上述描述的示意性的方面、实施方式和特征之外，通过参考附图和以下的详细描述，本申请进一步的方面、实施方式和特征将会是容易明白的。The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present application will be readily apparent by reference to the drawings and the following detailed description.
在附图中，除非另外规定，否则贯穿多个附图相同的附图标记表示相同或相似的部件或元素。这些附图不一定是按照比例绘制的。应该理解，这些附图仅描绘了根据本申请公开的一些实施方式，而不应将其视为是对本申请范围的限制。In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.
图1示出根据本专利一实施例的手术机器人的系统的结构图。FIG1 shows a structural diagram of a surgical robot system according to an embodiment of the present patent.
图2为根据本申请一实施例的手术机器人系统的模块图。FIG. 2 is a module diagram of a surgical robot system according to an embodiment of the present application.
图3为根据本发明一实施例的介入器械的运动规划方法的流程图。FIG. 3 is a flow chart of a motion planning method for an interventional device according to an embodiment of the present invention.
图4为根据本发明一实施例的介入器械的运动规划的模块图。FIG. 4 is a module diagram of motion planning of an interventional device according to an embodiment of the present invention.
图5为根据本发明一实施例的介入器械的运动规划方法执行流程图。FIG. 5 is a flowchart of a method for executing motion planning of an interventional device according to an embodiment of the present invention.
图6为根据本发明另一实施例的介入器械的运动规划方法执行流程图。FIG. 6 is a flowchart of a motion planning method for an interventional device according to another embodiment of the present invention.
图7为根据本发明另一实施例的生成融合模型的流程图。FIG. 7 is a flowchart of generating a fusion model according to another embodiment of the present invention.
图8示出根据本发明一实施例的手术机器人的服务器的结构框图。FIG8 is a block diagram showing a structure of a server of a surgical robot according to an embodiment of the present invention.
在下文中，仅简单地描述了某些示例性实施例。正如本领域技术人员可认识到的那样，在不脱离本申请的精神或范围的情况下，可通过各种不同方式修改所描述的实施例。因此，附图和描述被认为本质上是示例性的而非限制性的。In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.
术语“第一”、“第二”、“第三”等仅用于区分描述，并不表示排列序号，也不能理解为指示或暗示相对重要性。The terms "first", "second", "third", etc. are only used for distinguishing descriptions and do not indicate the order of arrangement, nor can they be understood as indicating or implying relative importance.
此外，术语“水平”、“竖直”、“悬垂”等术语并不表示要求部件绝对水平或悬垂，而是可以稍微倾斜。如“水平”仅仅是指其方向相对“竖直”而言更加水平，并不是表示该结构一定要完全水平，而是可以稍微倾斜。In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.
在本申请的描述中，需要说明的是，术语“内”、“外”、“左”、“右”、“上”、“下”等指示的方位或位置关系为基于附图所示的方位或位置关系，或者是该申请产品使用时惯常摆放的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。In the description of the present application, it should be noted that the terms "inside", "outside", "left", "right", "upper", "lower" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, or the directions or positional relationships in which the product of the application is usually placed when in use, and are only used to facilitate the description of the present application and simplify the description. The above description does not indicate or imply that the device or element must have a specific orientation, be constructed and operate in a specific orientation, and therefore should not be understood as limiting the present application.
在本申请的描述中，除非另有明确的规定和限定，术语“设置”、“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。In the description of this application, unless otherwise clearly specified and limited, the terms "set", "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements.
下面将结合附图对本申请的技术方案进行清楚、完整地描述。The technical solution of the present application will be described clearly and completely below in conjunction with the accompanying drawings.
在实际应用中，可以将主端设备和从端设备以及其中的各个模块集成在一起，由一个设备整体实现全部/部分功能，也可以将各个模块分别由不同的实体设备组成。本发明仅以图1所示的具体结构为例说明各个模块分分别由不同的实体设备组成的设置方式。具体地：In practical applications, the master-end device and the slave-end device and the modules therein can be integrated together, so that one device as a whole realizes all/part of the functions, or each module can be composed of different physical devices. The present invention only takes the specific structure shown in FIG1 as an example to illustrate the setting mode in which each module is composed of different physical devices. Specifically:
图1示出根据本专利一实施例的手术机器人的系统的结构图。如图1所示，该一种手术机器人的系统，包括：主端设备100、从端设备200、介入器械(未在图1中示出)。Fig. 1 shows a structural diagram of a surgical robot system according to an embodiment of the present invention. As shown in Fig. 1, the surgical robot system includes: a master device 100, a slave device 200, and an interventional instrument (not shown in Fig. 1).
具体地，所述主端设备100，包括：影像处理主机、第一控制器。影像处理主机、第一控制器均位于主端设备100中，未在图1中示出。Specifically, the host device 100 includes: an image processing host and a first controller. The image processing host and the first controller are both located in the host device 100 and are not shown in FIG. 1 .
所述影像处理主机可以获取患者在本次手术之前的预制地图数据。例如，患者在术前拍摄的CT照片或局部组织结构图像等。当获取了预制地图数据后，影像处理主机需要对预制地图数据进行处理，生成方便规划路径的预制组织地图。The image processing host can obtain the pre-made map data of the patient before the operation, such as CT photos or local tissue structure images taken by the patient before the operation. After obtaining the pre-made map data, the image processing host needs to process the pre-made map data to generate a pre-made tissue map that is convenient for planning the path.
在术前需要将预先获取的预制地图数据导入到主端设备中。其中，可以但不限于CT数据、局部组织结构数据等。Before surgery, the pre-acquired pre-made map data needs to be imported into the main terminal device, which may include but is not limited to CT data, local tissue structure data, etc.
具体地，若导入的预制地图数据为CT数据，则需要从CT数据中生成组织数据；再根据组织数据拼接生成预制组织地图。Specifically, if the imported prefabricated map data is CT data, it is necessary to generate tissue data from the CT data; and then generate a prefabricated tissue map based on the splicing of the tissue data.
组织数据可以包括但不限于如下之一：血管拓扑结构(通常可以使用具有分支结构的线条表示)、血管管壁范围数据(通常可以使用点云数据描述)、血液循环系统中必要的组织结构(正常组织如心脏房室结构、瓣膜和病变组织如夹层、钙化、动脉瘤等。在实际应用中可以将上述组织数据进行排列组合或取舍。Tissue data may include, but are not limited to, one of the following: vascular topology (usually represented by lines with branching structures), vascular wall range data (usually described by point cloud data), necessary tissue structures in the blood circulation system (normal tissues such as the atrioventricular structure of the heart, valves, and diseased tissues), Such as dissection, calcification, aneurysm, etc. In practical applications, the above tissue data can be arranged, combined or selected.
图2为根据本申请一实施例的手术机器人系统的模块图。FIG. 2 is a module diagram of a surgical robot system according to an embodiment of the present application.
在本实施例中术者端即主端，患者端即从端。术者端设备包括监视器、影像处理主机、术者端控制器、术者操作装置(也就是输入控制组件)。监视器，用于监视患者的整体身体状态以及手术过程。影像处理主机，用于将预制地图与术中影像设备采集的数据融合，并且生成形变场。术者操作装置(也就是输入控制组件)用于获取医生的控制指令。术者端控制器，用于根据所述形变场以及医生的控制指令，生成执行指令。In this embodiment, the operator end is the master end, and the patient end is the slave end. The operator end device includes a monitor, an image processing host, an operator end controller, and an operator operating device (that is, an input control component). The monitor is used to monitor the patient's overall physical condition and the surgical process. The image processing host is used to fuse the pre-made map with the data collected by the intraoperative imaging device and generate a deformation field. The operator operating device (that is, the input control component) is used to obtain the doctor's control instructions. The operator end controller is used to generate execution instructions based on the deformation field and the doctor's control instructions.
在生成执行指令后，由数据总线传输到患者端设备执行相应的操作。患者端设备包括介入器械驱动装置和执行端控制器。执行端控制器，用于将术者端设备发送的控制指令进行拆解。介入器械驱动装置，用于将拆解后的指令通过介入器械驱动装置控制介入器械运动。After the execution instruction is generated, it is transmitted to the patient-side device by the data bus to execute the corresponding operation. The patient-side device includes an interventional instrument drive device and an execution-side controller. The execution-side controller is used to disassemble the control instruction sent by the operator-side device. The interventional instrument drive device is used to control the movement of the interventional instrument through the interventional instrument drive device.
图3为根据本发明一实施例的介入器械的运动规划方法的流程图。FIG. 3 is a flow chart of a motion planning method for an interventional device according to an embodiment of the present invention.
在本发明介入器械的运动规划方法中包括如下步骤：The motion planning method of the interventional device of the present invention includes the following steps:
步骤S01：提取组织结构中的可移动通道；本发明中的可移动通道并不限定于血管，也可以是器官中的腔体。Step S01: extracting movable channels in the tissue structure; the movable channels in the present invention are not limited to blood vessels, but may also be cavities in organs.
步骤S02：确定目标操作节点在可移动通道中的表征；Step S02: Determine the representation of the target operation node in the movable channel;
步骤S03：根据所述表征规划介入器械的运动。Step S03: planning the movement of the interventional instrument according to the representation.
可选地，在步骤S01中，当组织结构以空间模型表征，所述可移动通道为组织结构空间模型中最靠近内表面中心线的内轮廓；当所述组织结构为血管，所述可移动通道为血管内剔除掉损伤空间区域后的空间区域，所述损伤区域包括但不限于夹层、钙化、动脉瘤、斑块。Optionally, in step S01, when the tissue structure is represented by a spatial model, the movable channel is the inner contour closest to the center line of the inner surface in the spatial model of the tissue structure; when the tissue structure is a blood vessel, the movable channel is the spatial area in the blood vessel after removing the damaged spatial area, and the damaged area includes but is not limited to dissection, calcification, aneurysm, and plaque.
在步骤S02中，所述确定起始点、目标操作节点在可移动通道中的表征包括位置，以及姿态、速度、加速度中的一种或多种。In step S02, the starting point and the target operation node in the movable channel are determined to be characterized by position, and one or more of posture, speed, and acceleration.
在步骤S03中，所述时空路径具体为根据分析组织结构内运动得到内运动的循环周期，根据循环周期规划介入器械的运动。In step S03, the space-time path is specifically to obtain the cycle of the internal movement according to the analysis of the internal movement of the tissue structure, and to plan the movement of the interventional device according to the cycle.
其中，所述时空路径具体为根据分析组织结构内运动得到内运动的循环周期，根据循环周期规划介入器械的运动：The space-time path is specifically a cycle of internal movement obtained by analyzing the internal movement of the tissue structure. During the period, the movement of the interventional device is planned according to the cycle:
在血管平滑肌收缩状态下，血管管腔收窄时，控制介入器械停止或控制介入器械降低移动速度或控制介入器械降低加速度；When the vascular smooth muscle contracts and the vascular lumen narrows, the interventional device is controlled to stop, or the interventional device is controlled to reduce the moving speed, or the interventional device is controlled to reduce the acceleration;
在血管平滑肌舒张状态下，血管管腔舒张时，控制介入器械启动或控制介入器械提高移动速度或控制介入器械提高加速度。When the vascular smooth muscle is in a state of dilation and the vascular lumen is dilated, the interventional device is controlled to start, or the interventional device is controlled to increase the moving speed, or the interventional device is controlled to increase the acceleration.
图4为根据本发明一实施例的介入器械的运动规划的模块图。如图4所示，在步骤S03中，公开了：所述介入器械运动包括路径规划和轨迹规划；所述路径规划为空间路径，为自初始操作节点到达目标操作节点位置的路线；所述轨迹规划为时空路径，在时间维度上的表征为根据组织结构内运动状态规划介入器械的运动，在空间维度上的表征为自初始操作节点到达目标操作节点位置的路线。Fig. 4 is a module diagram of the motion planning of an interventional device according to an embodiment of the present invention. As shown in Fig. 4, in step S03, it is disclosed that: the motion of the interventional device includes path planning and trajectory planning; the path planning is a spatial path, which is a route from the initial operation node to the target operation node position; the trajectory planning is a spatiotemporal path, which is characterized in the time dimension as planning the motion of the interventional device according to the motion state in the tissue structure, and in the spatial dimension as a route from the initial operation node to the target operation node position.
图5为根据本发明一实施例的介入器械的运动规划方法执行流程图。FIG. 5 is a flowchart of a method for executing motion planning of an interventional device according to an embodiment of the present invention.
如图5所示，所述可移动通道中规划自初始操作节点到达目标操作节点位置的路线，包括以下步骤：As shown in FIG5 , planning a route from an initial operation node to a target operation node in the movable channel includes the following steps:
确定目标操作节点在可移动通道中的位置；模拟所述介入器械在所述可移动通道中的运动轨迹，生成初始规划路径；根据规划路径生成执行指令，直至所述介入器械完成目标操作节点的执行指令；其中，所述初始规划路径的起点为初始操作节点，所述初始规划路径的终点为所述目标操作节点。Determine the position of the target operation node in the movable channel; simulate the motion trajectory of the interventional instrument in the movable channel to generate an initial planned path; generate execution instructions according to the planned path until the interventional instrument completes the execution instructions of the target operation node; wherein the starting point of the initial planned path is the initial operation node, and the end point of the initial planned path is the target operation node.
在实际应用中，主端设备获取预制地图数据，生成预制组织地图的步骤，可以包括：通过设置目标组织部分的特性生成至少一个划分阈值；根据所述至少一个划分阈值，将目标组织部分从预制地图数据中剥离出来；利用基于阈值的区域增长算法将图像划分区域；去除各区域中的无关像素，得到各区域的关注图像；利用图割法，将所述各区域的关注图像拼接生成所述待生成融合模型的数据。In actual applications, the master-end device obtains prefabricated map data and generates a prefabricated tissue map, which may include: generating at least one division threshold by setting the characteristics of the target tissue part; separating the target tissue part from the prefabricated map data according to the at least one division threshold; dividing the image into regions using a threshold-based region growing algorithm; removing irrelevant pixels in each region to obtain a focus image of each region; and using a graph cut method to splice the focus images of each region to generate data for the fusion model to be generated.
在实际应用中，可以采用的划分阈值的特征包括但不限于上述列举的组织数据对应的特征。在本专利具体实施例中可以以“目标组织部分的形状特点”、“目标组织部分的钙化点占目标组织部分的百分比”设定双阈值，进而利用所述双阈值划分区域，生成预制组织地图。In practical applications, the characteristics of the division thresholds that can be used include but are not limited to the characteristics corresponding to the tissue data listed above. In the specific embodiment of this patent, dual thresholds can be set based on "shape characteristics of the target tissue part" and "percentage of calcification points in the target tissue part". The dual thresholds divide the area and generate a prefabricated tissue map.
通过设置目标组织部分的特性生成至少一个划分阈值，包括如下至少之一：At least one segmentation threshold is generated by setting the characteristic of the target tissue portion, including at least one of the following:
根据所述目标组织部分的形状特点确定所述划分阈值；Determining the segmentation threshold according to the shape characteristics of the target tissue portion;
根据所述目标组织部分的损伤特征占目标组织部分的百分比设定所述划分阈值。The division threshold is set according to the percentage of the damage characteristics of the target tissue portion to the target tissue portion.
具体地，所述区域增长算法在带分割的图像中，选取一个或者多个种子点作为生长的起点，根据指定的生长规则，将图像相邻体素中与种子点性质相同或者相近的体素进行合并。合并产生新的体素作为新的种子点，如此循环直到预制地图数据中没有可以合并的体素为止，这样就对待分割图像进行了区域划分。区域生长法解决分割结果不连续的问题，可以指定不同的生长准则，得到不同的分割方法，产生不同的分割结果。Specifically, the region growing algorithm selects one or more seed points as the starting point of growth in the segmented image, and merges the voxels with the same or similar properties as the seed points in the adjacent voxels of the image according to the specified growth rules. The merging generates new voxels as new seed points, and the cycle continues until there are no voxels that can be merged in the prefabricated map data, thus dividing the image to be segmented. The region growing method solves the problem of discontinuous segmentation results. Different growth criteria can be specified to obtain different segmentation methods and produce different segmentation results.
具体地，所述图割法生成预制组织地图的步骤包括：a构造能量函数；b通过能量函数构造网络图；c通过对网络图中最大流/最小割的求解，得到能量函数的最小值。Specifically, the steps of generating a prefabricated organizational map using the graph cut method include: a. constructing an energy function; b. constructing a network graph through the energy function; and c. obtaining the minimum value of the energy function by solving the maximum flow/minimum cut in the network graph.
所述能量函数构成为：E(f)＝Edata(f)+Esmooth(f)The energy function is constructed as follows: E(f) = Edata (f) + Esmooth (f)
能量函数由约束项Edata(f)和光滑约束项Esmooth(f)构成，用于分配给定区域的惩罚。光滑约束项Esmooth(f)作为相邻像素隶属不同领域的惩罚，可以反映区域内部的连续性和边界的不连续性。The energy function consists of the constraint term Edata (f) and the smooth constraint term Esmooth (f), which is used to assign penalties to a given area. The smooth constraint term Esmooth (f) is a penalty for adjacent pixels belonging to different areas, which can reflect the continuity within the area and the discontinuity of the boundary.
所述能量函数一般形式为：
The general form of the energy function is:
根据能量函数的构造把预制组织地图中点的集合映射成为一个无向图G(v,e)，v代表图中所有的节点，即预制组织地图中的像素点；e表示连接所有临近节点的边，即相邻像素间的相邻关系，e的权重为w(i,j)。According to the construction of the energy function, the set of points in the prefabricated organizational map is mapped into an undirected graph G(v,e), where v represents all the nodes in the graph, that is, the pixels in the prefabricated organizational map; e represents the edges connecting all adjacent nodes, that is, the adjacent relationship between adjacent pixels, and the weight of e is w(i,j).
利用推进重标记方法(push relabel)和增广路径方法(Augmenting path)对最大流/最小割的求解。The maximum flow/minimum cut problem is solved by using push relabel and augmenting path methods.
具体地，最小割求解中，定义割的容量为预制组织地图划分为移除掉边的两个不相交的集合的容量和，即所有割集中容量最小的割，其表示形式为：
Specifically, in solving the minimum cut, the capacity of the cut is defined as the sum of the capacities of the two disjoint sets of the prefabricated organizational map partitioned with the edges removed, that is, the cut with the smallest capacity among all cut sets, which is expressed as:
式中cut(S,T)为割的容量，w(μ，v)为节点μ和v之间的容量值。Where cut(S,T) is the capacity of the cut, and w(μ,v) is the capacity value between nodes μ and v.
边容量表示形式为：
The edge capacity is expressed as:
其中：I(μ)、I(v)表示区域μ和区域v灰度的平均值，D(μ，v)表示区域μ和区域v之间的距离，α和β是调节参数。Where: I(μ) and I(v) represent the average grayscale values of region μ and region v, D(μ, v) represents the distance between region μ and region v, and α and β are adjustment parameters.
最小割为：
The minimum cut is:
具体地，所述设定双阈值，进而利用所述双阈值划分区域，生成预制组织地图。该部分的一具体实施例：即采用双阈值对组织数据进行预处理，采用区域生长对阈值分割后的图像进一步区域划分，区域与像素之间的关系把图像的像素或区域聚合。其关键点如下：选择生长初始的种子点，在空间上对种子点周围邻域的像素进行搜索，选择相似像素生长，同时采用双阈值剔除无关像素。Specifically, the dual threshold is set, and then the dual threshold is used to divide the region to generate a prefabricated tissue map. A specific embodiment of this part: that is, the dual threshold is used to preprocess the tissue data, and the image after threshold segmentation is further divided into regions by region growing, and the relationship between regions and pixels aggregates the pixels or regions of the image. The key points are as follows: select the initial seed point for growth, search the pixels in the neighborhood around the seed point in space, select similar pixels for growth, and use the dual threshold to eliminate irrelevant pixels.
在原始图像中选取阈值范围[S1,S2]，取该范围内的中间值作为种子点平均值，从而对区域生长相似性准则进行约束
|N-Nneed|＜μ|S1-S2|Select a threshold range [S1 ,S2 ] in the original image, and take the middle value in the range as the average value of the seed point, so as to constrain the region growth similarity criterion
|NNneed |＜μ|S1 -S2 |
其中N表示灰度，μ是用以控制像素相似度的可调节参数，N为任一点，Nneed为种子点。Where N represents the grayscale, μ is an adjustable parameter used to control pixel similarity, N is any point, and Nneed is the seed point.
获取树S和树T，搜索树S和树T的树T的生长，找到汇点，扩展树S和树T的边缘点，收集孤立点，恢复搜索树。Get tree S and tree T, search the growth of tree S and tree T, find the sink, expand the edge points of tree S and tree T, collect isolated points, and restore the search tree.
具体地，目标组织部分的钙化点占目标组织部分的百分比的获取方式是分割确定钙化点区域的一具体实施例为：Specifically, the percentage of calcification points in the target tissue portion is obtained by segmenting and determining the calcification point area. A specific embodiment is as follows:
目标组织具体为动脉血管或者其他部位血管。分割确定钙化点步骤为1)提取血管区域，2)在血管区域分割钙化点。3)计算钙化点占目标组织部分的百分比。The target tissue is specifically an artery or a blood vessel in another part. The steps of segmenting and determining the calcification points are: 1) extracting the blood vessel region, 2) segmenting the calcification points in the blood vessel region, and 3) calculating the percentage of the calcification points in the target tissue part.
也就是说，所述根据所述目标组织部分的形状特点确定所述划分阈值，具体为根据血管形状特点确定所述划分阈值；That is to say, the dividing threshold is determined according to the shape characteristics of the target tissue part, specifically, the dividing threshold is determined according to the shape characteristics of the blood vessel;
所述根据所述目标组织部分的损伤特征占目标组织部分的百分比设定所述划分阈值中，具体为目标组织部分的钙化点占目标组织部分的百分比设定所述划分阈值；The dividing threshold is set according to the percentage of the damage characteristics of the target tissue part to the target tissue part, and specifically, the dividing threshold is set according to the percentage of the calcification points of the target tissue part to the target tissue part;
所述根据血管形状特点确定所述划分阈值，用于提取血管区域；The dividing threshold is determined according to the shape characteristics of the blood vessel, and is used to extract the blood vessel area;
所述目标组织部分的钙化点占目标组织部分的百分比设定所述划分阈值，用于在血管区域分割钙化点。The division threshold is set according to the percentage of the calcification points in the target tissue part to the target tissue part, and is used to segment the calcification points in the blood vessel area.
其中1)提取血管区域一具体实施例为：A specific embodiment of 1) extracting the blood vessel region is as follows:
传统算法对血管的分割，采用服用药物使血管显影的方法，加大血管与周围组织的对比度，实现分割的目的。或者采用交互分割的方式，由医生手动圈定分割区域，对区域进行提取和测量。CT影像对主动脉定位，会受到周围灰度相近的组织器官的影响，进行连通域标记后，身体组织器官一般为形状不规则的图形，血管部分则表现为规则的圆形或椭圆形，因此可以在自影像中找到血管的位置。钙化点在连通域中为白色像素，定义各项分割所需变量，也就是分割所获得的每个连通域的特征，以便使用这些特征对图像进行分割。连通区域特征参数：Traditional algorithms use drugs to make blood vessels visible, thereby increasing the contrast between blood vessels and surrounding tissues to achieve segmentation. Alternatively, interactive segmentation can be used, where doctors manually circle the segmentation area, extract and measure the area. The positioning of the aorta by CT images will be affected by the surrounding tissues and organs with similar grayscale. After the connected domain is marked, the body's tissues and organs are generally irregularly shaped, while the blood vessels appear as regular circles or ellipses. Therefore, the location of the blood vessels can be found in the self-image. Calcification points are white pixels in the connected domain. The variables required for each segmentation are defined, that is, the features of each connected domain obtained by segmentation, so that these features can be used to segment the image. Connected region feature parameters:
连通区域面积Si＝各个区域像素点加和；The area of the connected regionSi = the sum of the pixels in each region;
连通域的外接矩形＝长length＝right-left，宽width＝bottom-top，面积Ri＝length*widthThe circumscribed rectangle of the connected domain = length = right-left, width = bottom-top, areaRi = length*width
连通域的矩形度Rectangularity of Connected Components
钙化区域面积Li＝钙化部分像素加和Calcified area Li = sum of calcified pixels
连通域的钙化度Calcification degree of connected domain
获取各个小连通区域的矩形度和钙化度之后，可以根据连通域分割需要的动脉血管图像。骨骼部分钙化程度最高，接近于1，身体各个器官钙化程度最小，接近于0，主动脉血管的钙化程度趋近于两者之间。骨骼与身体器官形状各异，矩形度不大，而主动脉血管部分的形状比较规则，矩形度很大。所以可以根据人体特定骨骼特征部分作为参考系，进而定位主动脉血管。After obtaining the rectangularity and calcification degree of each small connected area, the required arterial blood vessel image can be segmented according to the connected domain. The calcification degree of the bone part is the highest, close to 1, and the calcification degree of each organ in the body is the lowest, close to 0. The calcification degree of the aorta is close to the middle. The shape of the aorta is relatively regular and has a large rectangular degree. Therefore, the aorta can be located based on the specific bone features of the human body as a reference system.
获取血管主动脉图像之后，需要对钙化点进行分割，根据主动脉血管的位置以及钙化点相对血管的相对位置关系，提取感兴趣的区域，设图像的总像素为N，灰度总数为L，灰度值为i的像素数为Ni。令w(k)和μ(k)分别表示从灰度级0到灰度级k的像素的出现概率和平均灰度，分别表示为：
After obtaining the aortic image, the calcification points need to be segmented. According to the position of the aortic blood vessels and the relative position of the calcification points to the blood vessels, the region of interest is extracted. Let the total number of pixels in the image be N, the total number of grayscales be L, and the number of pixels with grayscale value i beNi . Let w(k) and μ(k) represent the probability of occurrence and average grayscale of pixels from grayscale level 0 to grayscale level k, respectively, and they are expressed as:
由此，所有像素的总概率为w(L-1)＝1,图像的平均灰度为μT＝μ(L-1)Therefore, the total probability of all pixels is w(L-1)=1, and the average grayscale of the image is μT =μ(L-1)
假设有M-1个阈值(0≤t1＜t2＜...＜tM-1≤L-1)，将图像分成M个像素类Cj(Cj∈[tj-1+1,...tj]；j＝1,2...,M；t0＝0，tM＝L-1)，则Cj的出现概率wj、平均灰度μj和方差为
wj＝w(tj)-w(tj-1)
Assume that there are M-1 thresholds (0≤t1 ＜t2 ＜...＜tM-1 ≤L-1), and divide the image into M pixel classes Cj (Cj ∈[tj-1 +1,...tj ]; j＝1,2...,M; t0 ＝0, tM ＝L-1), then the occurrence probability wj , average grayscale μj and variance of Cj are for
wj =w(tj )-w(tj-1 )
则内方差为
The internal variance is
其中2)在血管区域分割钙化点：2) Segmentation of calcification points in the vascular region:
以Otsu方法为基础，在输入之前对图像进行灰度拉伸预处理。Based on the Otsu method, the image is preprocessed by grayscale stretching before input.
设图像灰度等级M，在[a,b]区间内做线性变换；
Assume the image gray level M, and perform linear transformation in the interval [a, b];
[d,c]为对[a,b]段灰度进行拉伸之后的灰度级。根据主动脉血管的灰度范围选定a，b，c，d的参数值对原图进行灰度拉伸，之后再进行Otsu分割，获得钙化点像素。再计算钙化点占目标组织部分的百分比。[d,c] is the gray level after stretching the gray level of the [a,b] segment. According to the gray range of the aorta, the parameter values of a, b, c, and d are selected to stretch the gray level of the original image, and then Otsu segmentation is performed to obtain the calcification point pixels. Then the percentage of calcification points in the target tissue part is calculated.
在实际应用中，主端设备获取预制地图数据，生成预制组织地图的步骤，也可以包括：获取预制地图数据划分为至少一个数据块；将所述数据块作为输入，通过多层卷积神经网络来获取图像的特征，生成预制组织地图。In actual applications, the master device obtains prefabricated map data and generates a prefabricated organizational map, which may also include: obtaining prefabricated map data and dividing it into at least one data block; using the data block as input, obtaining image features through a multi-layer convolutional neural network, and generating a prefabricated organizational map.
根据预制组织地图即可规划出介入器械在目标组织部分中的路径，即初始规划路径。在术中可以依据初始规划路径作为参考，控制介入器械的运动。The path of the interventional device in the target tissue part can be planned according to the prefabricated tissue map, i.e., the initial planned path. During the operation, the movement of the interventional device can be controlled based on the initial planned path as a reference.
其中，初始规划路径至少包括：初始操作节点(也就是介入器械进入人体的初始位置)、目标操作节点(也就是介入器械进入人体的目标位置)。The initial planning path includes at least: an initial operation node (ie, the initial position of the interventional device entering the human body) and a target operation node (ie, the target position of the interventional device entering the human body).
初始规划路径还可以包括但不限于：从初始操作节点到目标操作节点的整体路线、在路径中对介入器械的运动规划，例如继续行进、调整位姿、到达目标操作节点后待执行的操作(除了手术治疗操作，如放置植入物、切割、穿刺等)、路径沿途的速度限制、姿态限制、运动条件限制等。The initial planned path may also include, but is not limited to: the overall route from the initial operation node to the target operation node, the motion planning of the interventional instrument in the path, such as continuing to move forward, adjusting the posture, and the operations to be performed after reaching the target operation node (except surgical treatment operations, such as implant placement, cutting, puncture, etc.), speed limits, posture limits, motion condition limits, etc. along the path.
具体地，生成初始规划路径的步骤但不限于人工制定初始规划路径或自动计算初始规划路径。也就是模拟所述介入器械在所述预制组织地图的运动轨迹，生成初始规划路径可以包括：Specifically, the step of generating the initial planning path is not limited to manually formulating the initial planning path or automatically calculating the initial planning path. That is, simulating the motion trajectory of the interventional instrument in the prefabricated tissue map, generating the initial planning path may include:
人工制定初始规划路径是指术者通过术者端设备的人机交互接口，在地图数据上选定初始操作节点、目标操作节点，影像处理主机自动计算至少一条路径。术者可通过人机交互接口选择一条路径，并在此路径的基础上进行人工编辑(包括微调路径、添加标注、添加条件限制等数据信息)。Manually formulating the initial planning path means that the operator selects the initial operation node and the target operation node on the map data through the human-computer interaction interface of the operator's terminal device, and the image processing host automatically calculates at least one path. The operator can select a path through the human-computer interaction interface and perform manual editing based on this path (including fine-tuning the path, adding annotations, adding conditional restrictions and other data information).
自动计算初始规划路径是指利用路径规划算法计算初始操作节点与目标操作节点之间的最优路径。路径规划算法包括图搜索算法。Automatically calculating the initial planning path refers to calculating the optimal path between the initial operation node and the target operation node using a path planning algorithm. The path planning algorithm includes a graph search algorithm.
根据预制地图数据就可以在术前对介入器械在人体的路径进行规划，以使得降低手术对人体健康的损伤降为最小。在介入器械在人体内运动时，需要根据术前规划的路径以及实时采集到的数据生成执行指令，使得介入器械在不偏离路径的前提下，更贴合实际患者实际的生理构造。生成执行指令后，将该执行指令发送至从端，由第二控制器控制介入设备完成执行指令。Based on the pre-made map data, the path of the interventional device in the human body can be planned before surgery. The damage of surgery to human health can be minimized. When the interventional device moves in the human body, it is necessary to generate execution instructions based on the preoperatively planned path and the real-time collected data, so that the interventional device can better fit the actual physiological structure of the actual patient without deviating from the path. After the execution instruction is generated, the execution instruction is sent to the slave end, and the second controller controls the interventional device to complete the execution instruction.
具体地，获取根据初始规划路径确定的初始操作节点。此处的初始操作节点是指介入器械进入人体的第一个节点，在实际应用中需要根据患者患病的位置确定介入器械的初始操作节点，例如，通过大腿的静脉(或动脉)接入点(初始操作节点)进入血管最终达到人体的心脏(目标操作节点)实现治疗。也就是说所述初始规划路径的起点为初始操作节点，也就是介入人体的初始位置；所述初始规划路径的终点为目标操作节点，也就是患者的患病位置。Specifically, the initial operation node determined according to the initial planning path is obtained. The initial operation node here refers to the first node where the interventional device enters the human body. In practical applications, it is necessary to determine the initial operation node of the interventional device according to the location of the patient's disease. For example, the blood vessel is entered through the thigh vein (or artery) access point (initial operation node) and finally reaches the human heart (target operation node) to achieve treatment. That is to say, the starting point of the initial planning path is the initial operation node, that is, the initial location of the interventional human body; the end point of the initial planning path is the target operation node, that is, the patient's diseased location.
图6为根据本发明另一实施例的介入器械的运动规划方法执行流程图。FIG. 6 is a flowchart of a motion planning method for an interventional device according to another embodiment of the present invention.
如图6所示，基于所述初始规划路径和所述初始操作节点所在关联路径节点的实时数据，生成第一运动数据；判断是否存在预设时间段内获取的第二运动数据，若存在，则所述第一控制器配置所述第一运动数据和所述第二运动数据的权重，生成执行指令。此处的第一运动数据是系统根据已有的数据规划出的数据，第二运动数据是指医生控制输入控制组件获取的数据。也就是说本专利所保护的系统既可以自主实现全自动控制介入器械的运动，也可以实现半自动控制介入器械的运动。As shown in Figure 6, based on the real-time data of the associated path node where the initial planned path and the initial operation node are located, the first motion data is generated; it is determined whether there is second motion data obtained within a preset time period, and if so, the first controller configures the weights of the first motion data and the second motion data, and generates an execution instruction. The first motion data here is the data planned by the system based on the existing data, and the second motion data refers to the data obtained by the doctor controlling the input control component. In other words, the system protected by this patent can autonomously realize fully automatic control of the movement of interventional instruments, and can also realize semi-automatic control of the movement of interventional instruments.
当主端设备生成了执行指令后，就将该执行指令传输给从端设备，由从端设备控制介入器械执行相应的操作。因此，主端设备需要将所述执行指令发送至所述第二控制器；所述第二控制器接受执行指令，并由第二控制器控制所述介入器械完成执行指令。When the master device generates an execution instruction, it transmits the execution instruction to the slave device, which controls the interventional device to perform the corresponding operation. Therefore, the master device needs to send the execution instruction to the second controller; the second controller receives the execution instruction and controls the interventional device to complete the execution instruction.
在实际应用中可以通过介入器械上安装的传感器(如超声波传感器)或实时影像数据(如DSA影像数据)获取介入器械的实际情况。当影像处理主机接受到介入器械完成执行指令并到达下一操作节点的信息后，将所述下一操作节点作为新的初始操作节点，第一控制器循环执行生成执行指令的步骤，直至所述介入器械完成目标操作节点的执行指令。也就是每到一个新的操作节点就规划执行到下一操作节点的需要的运动数据。In practical applications, the actual situation of the interventional instrument can be obtained through sensors (such as ultrasonic sensors) installed on the interventional instrument or real-time image data (such as DSA image data). When the image processing host receives information that the interventional instrument has completed the execution instruction and reached the next operation node, the next operation node is used as the new initial operation node, and the first controller loops to execute the step of generating the execution instruction until the interventional instrument completes the execution instruction of the target operation node. That is, every time a new operation node is reached, the required motion data for executing the next operation node is planned.
所述从端设备，用于获取所在路径的实时数据，并利用所述介入器械执行所述第一控制器发出的执行指令。The slave device is used to obtain real-time data of the path where it is located, and use the interventional instrument to execute the execution instruction issued by the first controller.
当主端设备生成了介入器械整体的控制指令，则需要将主端的控制指令传输到从端，由从端设备将整体的控制指令进行拆解，由从端的一个或多个组件执行相应的拆解后的指令。When the master device generates the overall control instructions for the interventional instrument, the master control instructions need to be transmitted to the slave device, and the slave device disassembles the overall control instructions, and one or more components of the slave execute the corresponding disassembled instructions.
具体地，所述从端设备还包括：第二控制器、从端驱动装置；Specifically, the slave device further includes: a second controller, a slave drive device;
所述第二控制器用于拆解主端设备发出执行指令，生成拆解指令；The second controller is used to disassemble the main end device to issue an execution instruction and generate a disassembly instruction;
所述从端驱动装置用于根据所述第二控制器的所述拆解指令，驱动从端的各个组件执行不同的动作，共同实现带动介入器械运动的目的。The slave-end driving device is used to drive various components of the slave end to perform different actions according to the disassembly instruction of the second controller, so as to jointly achieve the purpose of driving the interventional instrument to move.
术中控制介入器械在人体内运动的过程主要包括：根据预制地图数据/实时影像数据结合形变场以及初始规划路径对介入器械进行控制。其中，预制地图数据/实时影像数据提供坐标系，形变场提供坐标系之间的对应关系，介入器械需沿初始规划路径在人体内运动，当介入器械偏离初始路径规划时，则需要校正介入器械的执行路线。The process of controlling the movement of interventional instruments in the human body during surgery mainly includes: controlling the interventional instruments according to the pre-made map data/real-time image data combined with the deformation field and the initial planned path. Among them, the pre-made map data/real-time image data provide the coordinate system, and the deformation field provides the correspondence between the coordinate systems. The interventional instrument needs to move in the human body along the initial planned path. When the interventional instrument deviates from the initial path planning, the execution route of the interventional instrument needs to be corrected.
具体地，所述影像处理主机获取预制地图数据，生成预制组织地图。再根据所述预制组织地图和实时数据，生成形变场。所述第一控制器根据所述形变场生成执行指令；将所述执行指令发送至所述第二控制器；所述第二控制器接受执行指令，并控制所述介入器械完成执行指令。Specifically, the image processing host obtains prefabricated map data and generates a prefabricated tissue map. Then, a deformation field is generated based on the prefabricated tissue map and real-time data. The first controller generates an execution instruction based on the deformation field; sends the execution instruction to the second controller; the second controller receives the execution instruction and controls the interventional instrument to complete the execution instruction.
具体地，基于所述初始规划路径和所述初始操作节点所在关联路径节点的实时数据，生成第一运动数据，包括：Specifically, generating first motion data based on the initial planned path and the real-time data of the associated path node where the initial operation node is located includes:
获取所述初始操作节点的实际位姿和速度；Obtaining the actual position and speed of the initial operation node;
参考所述初始规划路径，利用所述实际位姿和速度，生成下一操作节点的第一运动数据；Referring to the initial planned path, and using the actual position and speed, generating first motion data of a next operation node;
所述第一运动数据包括：下一操作节点的位姿变化量和加速度变化量。The first motion data includes: a change in position and an change in acceleration of the next operation node.
也就是在每个位置时计算下一位置需要达到的速度、加速度，进而控制介入器械执行相应的操作。That is, at each position, the speed and acceleration required to be achieved at the next position are calculated, and then the interventional device is controlled to perform the corresponding operation.
所述位姿是指介入器械所在的位置和姿态。根据介入器械的需要达到的位姿可以用于控制介入器械在运动过程中的位置变化过程。即通过当前时刻的实际位姿和下一位置的位姿，确定运动过程中的介入器械的状态变化过程。The posture refers to the position and posture of the interventional device. The posture achieved according to the needs of the interventional device can be used to control the position change process of the interventional device during the movement process. The current position and the position of the next position are used to determine the state change process of the interventional device during the movement.
实际上，生成运动数据的过程是一个循环的过程，每执行到下一操作节点时，则需要根据当前操作节点的情况执行下一操作节点的运动数据。In fact, the process of generating motion data is a cyclic process. Every time the next operation node is executed, the motion data of the next operation node needs to be executed according to the situation of the current operation node.
运动数据主要包括两个部分：基于位置的运动指令和基于速度的运动指令。其中，运动指令可以包括前进/后退、旋转、控弯等操作等；基于速度的运动指令相当于运动指令的参数可以包括距离、速度、加速度等。通过将运动数据拆分到各个机械模组，进而实现从端的驱动器带动介入器械进行运动的目的。Motion data mainly includes two parts: position-based motion instructions and speed-based motion instructions. Among them, motion instructions can include forward/backward, rotation, bending control and other operations; speed-based motion instructions are equivalent to motion instruction parameters that can include distance, speed, acceleration, etc. By splitting the motion data into various mechanical modules, the purpose of driving the interventional device to move from the end driver can be achieved.
图7为根据本发明另一实施例的生成融合模型的流程图。FIG. 7 is a flowchart of generating a fusion model according to another embodiment of the present invention.
如图7所示，生成融合模型的流程包括：将所述预制地图数据根据腔体结构划分为至少一个数据块；将所述数据块作为输入，通过多层卷积神经网络来获取图像的特征；对所述特征进行筛选，将筛选后的特征组合生成融合模型。As shown in FIG7 , the process of generating a fusion model includes: dividing the prefabricated map data into at least one data block according to the cavity structure; using the data block as input to obtain image features through a multi-layer convolutional neural network; screening the features, and combining the screened features to generate a fusion model.
根据本发明的另一可选实施例一种介入器械的运动规划系统，包括：感知模块，用于提取组织结构中的可移动通道；定位模块，用于确定目标操作节点在可移动通道中的表征；路径规划模块，用于根据所述表征规划介入器械的运动。According to another optional embodiment of the present invention, a motion planning system for an interventional instrument includes: a perception module for extracting a movable channel in a tissue structure; a positioning module for determining a representation of a target operating node in the movable channel; and a path planning module for planning the movement of the interventional instrument according to the representation.
图8示出根据本发明一实施例的手术机器人的服务器的结构框图。如图8所示，该手术机器人的服务器包括：存储器810和处理器820，存储器810内存储有可在处理器820上运行的计算机程序。处理器820执行该计算机程序时实现上述实施例中的进行路径规划的步骤。存储器810和处理器820的数量可以为一个或多个。FIG8 shows a block diagram of a server of a surgical robot according to an embodiment of the present invention. As shown in FIG8 , the server of the surgical robot includes: a memory 810 and a processor 820, wherein the memory 810 stores a computer program that can be run on the processor 820. When the processor 820 executes the computer program, the path planning step in the above embodiment is implemented. The number of the memory 810 and the processor 820 can be one or more.
该手术机器人的服务器还包括：The surgical robot's server also includes:
通信接口830，用于与外界设备进行通信，进行数据交互传输。The communication interface 830 is used to communicate with external devices and perform data exchange transmission.
如果存储器810、处理器820和通信接口830独立实现，则存储器810、处理器820和通信接口830可以通过总线相互连接并完成相互间的通信。该总线可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外部设备互连(Peripheral Component Interconnect，PCI)总线或扩展工业标准体系结构(Extended Industry Standard Architecture，EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。为便于表示，图8中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。If the memory 810, the processor 820 and the communication interface 830 are implemented independently, the memory 810, the processor 820 and the communication interface 830 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. For address bus, data bus, control bus, etc. For the convenience of representation, only one thick line is used in FIG8 , but it does not mean that there is only one bus or one type of bus.
可选的，在具体实现上，如果存储器810、处理器820及通信接口830集成在一块芯片上，则存储器810、处理器820及通信接口830可以通过内部接口完成相互间的通信。Optionally, in a specific implementation, if the memory 810, the processor 820 and the communication interface 830 are integrated on a chip, the memory 810, the processor 820 and the communication interface 830 can communicate with each other through an internal interface.
本发明实施例提供了一种计算机可读存储介质，其存储有计算机程序，该程序被处理器执行时实现本申请实施例中提供的方法。An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.
本申请实施例还提供了一种芯片，该芯片包括，包括处理器，用于从存储器中调用并运行存储器中存储的指令，使得安装有芯片的通信设备执行本申请实施例提供的方法。An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.
本申请实施例还提供了一种芯片，包括：输入接口、输出接口、处理器和存储器，输入接口、输出接口、处理器以及存储器之间通过内部连接通路相连，处理器用于执行存储器中的代码，当代码被执行时，处理器用于执行申请实施例提供的方法。An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.
应理解的是，上述处理器可以是中央处理器(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(digital signal processing，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(fieldprogrammablegate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。值得说明的是，处理器可以是支持进阶精简指令集机器(advanced RISC machines，ARM)架构的处理器。It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.
进一步地，可选的，上述存储器可以包括只读存储器和随机存取存储器，还可以包括非易失性随机存取存储器。该存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以包括只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以包括随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用。例如，静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic random access memory，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used to store data. As an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输。In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包括于本申请的至少一个实施例或示例中。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或隐含地包括至少一个该特征。在本申请的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分。并且本申请的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能。Any process or method description described in the flowchart or otherwise herein can be understood as a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, which may not be in the order shown or discussed, including in a substantially simultaneous manner or in accordance with the functions involved. Execute the functions in reverse order.
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。The logic and/or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.
应理解的是，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。上述实施例方法的全部或部分步骤是可以通过程序来指令相关的硬件完成，该程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.
此外，在本申请各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。上述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读存储介质中。该存储介质可以是只读存储器，磁盘或光盘等。In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到其各种变化或替换，这些都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211731769.1ACN115998433A (en) | 2022-12-30 | 2022-12-30 | Motion planning method, system, program element and storage medium for an interventional instrument |
| CN202211731769.1 | 2022-12-30 |
| Publication Number | Publication Date |
|---|---|
| WO2024140436A1true WO2024140436A1 (en) | 2024-07-04 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/140840PendingWO2024140436A1 (en) | 2022-12-30 | 2023-12-22 | Motion planning method and system for interventional instrument, program unit, and storage medium |
| Country | Link |
|---|---|
| CN (1) | CN115998433A (en) |
| WO (1) | WO2024140436A1 (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119632674A (en)* | 2025-01-13 | 2025-03-18 | 山东大学 | A robot path planning method and system for percutaneous spinal endoscopic surgery |
| CN119770186A (en)* | 2024-12-11 | 2025-04-08 | 深圳爱博合创医疗机器人有限公司 | Interventional instrument control method and computer equipment |
| CN120388259A (en)* | 2025-04-16 | 2025-07-29 | 中国人民解放军总医院第四医学中心 | Intervention guidance method and device based on multimodal image fusion |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115998448A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | System and device for a surgical robot |
| CN115998433A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | Motion planning method, system, program element and storage medium for an interventional instrument |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106062822A (en)* | 2014-03-04 | 2016-10-26 | 赞克特机器人有限公司 | Dynamic planning method for needle insertion |
| US20170151027A1 (en)* | 2015-11-30 | 2017-06-01 | Hansen Medical, Inc. | Robot-assisted driving systems and methods |
| CN109640861A (en)* | 2016-08-31 | 2019-04-16 | 柯惠有限合伙公司 | It is planned with the access that navigation programming is used together with regulation system |
| WO2021214754A1 (en)* | 2020-04-19 | 2021-10-28 | Xact Robotics Ltd. | Optimizing checkpoint locations along an insertion trajectory of a medical instrument using data analysis |
| CN114025658A (en)* | 2019-06-27 | 2022-02-08 | 威斯康星校友研究基金会 | System and method for motion adaptation device guidance using vascular roadmaps |
| CN115003235A (en)* | 2019-11-27 | 2022-09-02 | 赞克特机器人有限公司 | Planning and updating 3D trajectories of medical instruments in real time |
| CN115439493A (en)* | 2022-09-13 | 2022-12-06 | 上海派影医疗科技有限公司 | Method and device for segmenting cancerous regions of breast tissue slices |
| CN115965667A (en)* | 2022-12-30 | 2023-04-14 | 上海术之道机器人有限公司 | Method and device for tissue structure model data fusion of interventional operation |
| CN115998433A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | Motion planning method, system, program element and storage medium for an interventional instrument |
| CN115998424A (en)* | 2022-12-12 | 2023-04-25 | 上海术之道机器人有限公司 | Apparatus, method, program element and readable medium for controlling a medical intervention device |
| CN115998448A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | System and device for a surgical robot |
| CN116269808A (en)* | 2022-12-30 | 2023-06-23 | 上海术之道机器人有限公司 | System and device for a surgical robot |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10588597B2 (en)* | 2012-12-31 | 2020-03-17 | Intuitive Surgical Operations, Inc. | Systems and methods for interventional procedure planning |
| US11351000B2 (en)* | 2014-07-28 | 2022-06-07 | Intuitive Surgical Operations, Inc. | Systems and methods for planning multiple interventional procedures |
| WO2017033365A1 (en)* | 2015-08-25 | 2017-03-02 | 川崎重工業株式会社 | Remote control robot system |
| CN114677702A (en)* | 2020-12-24 | 2022-06-28 | 上海微创卜算子医疗科技有限公司 | Hair density measurement method, electronic device and storage medium |
| CN114917029B (en)* | 2022-07-22 | 2022-10-11 | 北京唯迈医疗设备有限公司 | Interventional operation robot system, control method and medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106062822A (en)* | 2014-03-04 | 2016-10-26 | 赞克特机器人有限公司 | Dynamic planning method for needle insertion |
| US20170151027A1 (en)* | 2015-11-30 | 2017-06-01 | Hansen Medical, Inc. | Robot-assisted driving systems and methods |
| CN109640861A (en)* | 2016-08-31 | 2019-04-16 | 柯惠有限合伙公司 | It is planned with the access that navigation programming is used together with regulation system |
| CN114025658A (en)* | 2019-06-27 | 2022-02-08 | 威斯康星校友研究基金会 | System and method for motion adaptation device guidance using vascular roadmaps |
| CN115003235A (en)* | 2019-11-27 | 2022-09-02 | 赞克特机器人有限公司 | Planning and updating 3D trajectories of medical instruments in real time |
| WO2021214754A1 (en)* | 2020-04-19 | 2021-10-28 | Xact Robotics Ltd. | Optimizing checkpoint locations along an insertion trajectory of a medical instrument using data analysis |
| CN115439493A (en)* | 2022-09-13 | 2022-12-06 | 上海派影医疗科技有限公司 | Method and device for segmenting cancerous regions of breast tissue slices |
| CN115998424A (en)* | 2022-12-12 | 2023-04-25 | 上海术之道机器人有限公司 | Apparatus, method, program element and readable medium for controlling a medical intervention device |
| CN115965667A (en)* | 2022-12-30 | 2023-04-14 | 上海术之道机器人有限公司 | Method and device for tissue structure model data fusion of interventional operation |
| CN115998433A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | Motion planning method, system, program element and storage medium for an interventional instrument |
| CN115998448A (en)* | 2022-12-30 | 2023-04-25 | 上海术之道机器人有限公司 | System and device for a surgical robot |
| CN116269808A (en)* | 2022-12-30 | 2023-06-23 | 上海术之道机器人有限公司 | System and device for a surgical robot |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119770186A (en)* | 2024-12-11 | 2025-04-08 | 深圳爱博合创医疗机器人有限公司 | Interventional instrument control method and computer equipment |
| CN119632674A (en)* | 2025-01-13 | 2025-03-18 | 山东大学 | A robot path planning method and system for percutaneous spinal endoscopic surgery |
| CN120388259A (en)* | 2025-04-16 | 2025-07-29 | 中国人民解放军总医院第四医学中心 | Intervention guidance method and device based on multimodal image fusion |
| CN120388259B (en)* | 2025-04-16 | 2025-09-30 | 中国人民解放军总医院第四医学中心 | Interventional guidance method and device based on multi-mode image fusion |
| Publication number | Publication date |
|---|---|
| CN115998433A (en) | 2023-04-25 |
| Publication | Publication Date | Title |
|---|---|---|
| WO2024140436A1 (en) | Motion planning method and system for interventional instrument, program unit, and storage medium | |
| US12171592B2 (en) | System and method for identification, labeling, and tracking of a medical instrument | |
| KR101120250B1 (en) | Vascular image extraction and labeling system and method | |
| JP4524284B2 (en) | Cardiac imaging system and method for planning surgery | |
| KR20210027415A (en) | Surgical aids to provide assistance in surgery of the anatomical parts of internal organs affected by movement during surgery | |
| CN106473807B (en) | Automated ENT surgical preplanning using backtracking maze problem solution | |
| CN112102225B (en) | Registration apparatus, method for registration, and computer-readable storage medium | |
| CN111553887B (en) | Bridge blood vessel evaluation information acquisition method and device | |
| US20200242776A1 (en) | Medical image processing apparatus, medical image processing method, and system | |
| KR20220026534A (en) | Deep learning-based tissue resection planning method | |
| JP2015171437A (en) | Medical image processing apparatus, medical image processing system, and medical image processing program | |
| CN107025646B (en) | Lower limb blood vessel extraction method and device | |
| KR20200056105A (en) | Method and apparatus for calculating coronary artery calcium scoring | |
| CN114469153B (en) | Angiography device and equipment based on CT (computed tomography) image and computer readable medium | |
| CN112057165A (en) | A path planning method, device, equipment and medium | |
| JP2021526935A (en) | Automatic liver segmentation in CT | |
| WO2024140435A1 (en) | Tissue structure model data fusion method and apparatus for interventional surgery | |
| US20250228521A1 (en) | Intraluminal ultrasound vessel segment identification and associated devices, systems, and methods | |
| US11657547B2 (en) | Endoscopic surgery support apparatus, endoscopic surgery support method, and endoscopic surgery support system | |
| WO2022270150A1 (en) | Image processing device, method, and program | |
| CN115281828A (en) | A method and system for selecting the largest diameter intramedullary nail for fracture reduction | |
| US20240005495A1 (en) | Image processing device, method, and program | |
| KR102802633B1 (en) | Apparatus and Method for matching the Real Surgical Image with the 3D based Virtual Simulated Surgical Image | |
| CN118942642A (en) | Flap information processing device and storage medium | |
| US20250069220A1 (en) | Systems and methods for partitioning models of anatomical structures into functional segments |
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application | Ref document number:23910362 Country of ref document:EP Kind code of ref document:A1 | |
| NENP | Non-entry into the national phase | Ref country code:DE |