CN117958966A - Intraoperative path correction method and device for vascular interventional operation - Google Patents

Intraoperative path correction method and device for vascular interventional operation Download PDF

Info

Publication number
CN117958966A
CN117958966A CN202410126996.4A CN202410126996A CN117958966A CN 117958966 A CN117958966 A CN 117958966A CN 202410126996 A CN202410126996 A CN 202410126996A CN 117958966 A CN117958966 A CN 117958966A
Authority
CN
China
Prior art keywords
target
path
dimensional
initial
mapping
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202410126996.4A
Other languages
Chinese (zh)
Inventor
张瑜
马骏
郑凌霄
兰宏志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Raysight Intelligent Medical Technology Co Ltd
Original Assignee
Shenzhen Raysight Intelligent Medical Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Raysight Intelligent Medical Technology Co Ltd filed Critical Shenzhen Raysight Intelligent Medical Technology Co Ltd
Priority to CN202410126996.4A priority Critical patent/CN117958966A/en
Publication of CN117958966A publication Critical patent/CN117958966A/en
Pending legal-status Critical Current

Links

Landscapes

  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The application provides a method and a device for correcting an intraoperative path of a vascular interventional operation, comprising the following steps: acquiring a predetermined initial coronary three-dimensional model marked with a preoperative three-dimensional path; acquiring an initial two-dimensional contrast image at the current moment in operation and a contrast shooting angle of the initial two-dimensional contrast image; performing rotation processing on the initial coronary artery three-dimensional model according to the radiography shooting angle to obtain a target coronary artery three-dimensional model; performing mapping matching treatment on the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with the mapping blood vessel outline of the target blood vessel segment and the path in mapping operation; and sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast images to obtain the target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation. Therefore, the validity and the consistency of the determined intraoperative path are ensured by fusing preoperative path information and intraoperative path information, so that the efficiency and the accuracy of the operation can be effectively improved.

Description

Intraoperative path correction method and device for vascular interventional operation
Technical Field
The application relates to the technical field of surgical navigation, in particular to a method and a device for correcting an intraoperative path of a vascular interventional operation.
Background
The vascular intervention robot is medical equipment for performing vascular intervention operation, integrates high-tech means, has comprehensive performances of operation image guidance, minimally invasive operation and the like, organically combines a robot technology with the vascular intervention operation, and can be matched with a doctor to finish the vascular intervention operation rapidly and accurately. In the vascular intervention operation, a doctor operates a vascular intervention robot, and introduces special precise instruments such as a catheter, a guide wire and the like in the vascular intervention operation into a human body in a man-machine interaction mode to diagnose and locally treat in-vivo pathological conditions.
For better completion of vascular interventional procedures, it is important to determine the path of travel of the guidewire. The existing path determining method comprises the following two ways: 1. in PCI operation, if there is no path planning of preoperative three-dimensional CCTA, doctors often carry out the path planning in operation according to own experience, and a manual or semi-automatic method is adopted to carry out the path planning in operation; 2. if the path planning of the preoperative three-dimensional CCTA exists, a series of morphological and functional information is acquired, a certain reference can be given to the path planning in the operation, and a doctor is assisted to complete the path planning in the operation by a manual or semi-automatic method.
However, the two schemes have the following problems that in scheme 1, the resolution ratio is higher than that of CT by directly taking coronary angiography as a reference, but only two-dimensional information is provided, and three-dimensional space information is lacked; second, although two-dimensional coronary angiography can accurately calculate the vascular stenosis rate, it is difficult to determine the type of lesion (plaque) causing the stenosis. Because of the lack of partial information, experienced doctors are required to analyze and determine the path of the guide wire, which firstly increases the burden of the doctors and increases the pressure of medical resources; furthermore, the time during PCI surgery is valuable, the patient is suffering from radiation hazards, more complex protocol determinations require longer decision time, increase physician stress, decrease surgical safety, and increase radiation hazards to the patient. Scheme 2 after the CCTA three-dimensional model and other morphological and functional metrics are obtained, these important information are not combined with the intra-operative information, so that there may be a deviation in the obtained path.
Disclosure of Invention
Accordingly, the present application aims to provide a method and a device for correcting an intraoperative path of a vascular interventional operation, which ensure the effectiveness and consistency of a determined intraoperative path by fusing preoperative path information and intraoperative path information, thereby effectively improving the efficiency and accuracy of the operation.
The embodiment of the application provides an intraoperative path correction method for vascular interventional operation, which comprises the following steps:
Acquiring a predetermined initial coronary three-dimensional model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point;
acquiring an initial two-dimensional contrast image at the current moment in operation and a contrast shooting angle of the initial two-dimensional contrast image;
Performing rotation processing on the initial coronary artery three-dimensional model according to the radiography shooting angle to obtain a target coronary artery three-dimensional model consistent with the initial two-dimensional radiography image shooting angle;
Performing mapping matching processing on the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with a mapping blood vessel contour of a target blood vessel segment and a path in mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path;
and sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast images to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
Optionally, the rotating the initial coronary artery three-dimensional model according to the imaging angle to obtain a target coronary artery three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging, including:
determining a rotation matrix according to the contrast shooting angle;
Performing rotation processing on the initial coronary three-dimensional model according to the rotation matrix to determine a target coronary three-dimensional model; the shooting angle of the target coronary artery three-dimensional model is the same as that of the initial two-dimensional contrast image.
Optionally, the performing mapping matching processing on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with a mapped vessel contour of a target vessel segment and a path in mapping operation includes:
Acquiring a three-dimensional coronary contour of the target vessel end and a preoperative three-dimensional path of the target vessel end from the target coronary three-dimensional model;
According to the matching relation between the target coronary artery three-dimensional model and the initial two-dimensional contrast image, mapping the three-dimensional coronary artery outline and the preoperative three-dimensional path to corresponding positions in the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image; and the candidate two-dimensional contrast images are marked with the mapped vessel contours and the paths in mapping operation after the mapping treatment.
Optionally, the sequentially correcting the mapped vessel contour and the path in the mapping operation in the candidate two-dimensional radiography image to obtain a target two-dimensional radiography image marked with the target vessel contour and the path in the target operation, including:
extracting a local image block comprising the mapped blood vessel outline from the candidate two-dimensional contrast image, and simultaneously acquiring blood vessel attribute information of the target blood vessel segment;
the candidate two-dimensional contrast image, the local image block and the blood vessel attribute information of the target blood vessel segment are input into a pre-trained contour correction model together, and the blood vessel contour in the candidate two-dimensional contrast image is corrected to obtain the target blood vessel contour;
acquiring relevant parameters of a target medical instrument used in vascular interventional operation;
Correcting the mapping operation path according to the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the appointed parameter information in the current path information of the mapping operation path, and determining the target operation path.
Optionally, the correcting the mapping intra-operation path according to the target blood vessel profile, the blood vessel attribute information of the target blood vessel segment, the related parameter of the target medical device, and the specified parameter information in the current path information of the mapping intra-operation path, to determine the target intra-operation path, includes:
And fusing and inputting the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the current path information of the mapping operation path into a pre-trained path correction model to obtain the target operation path so as to finish correction of the mapping operation path.
Optionally, the relevant parameters include instrument position information, and the correcting the mapping intra-operative path according to the target vessel profile, vessel attribute information of the target vessel segment, relevant parameters of the target medical instrument, and specified parameter information in current path information of the mapping intra-operative path, to determine the target intra-operative path includes:
Determining an initial starting point, at least one candidate path key point and an end point according to the current path information of the path in the mapping operation;
correcting the initial starting point and screening all candidate path key points according to the instrument position information of the target medical instrument to determine a target starting point and at least one target path key point;
and under the constraint of the target vessel contour, performing curve fitting processing according to the target starting point, at least one target path key point and the target ending point, and determining the target intraoperative path.
The embodiment of the application also provides an intraoperative path correction device for vascular interventional operation, which comprises:
The first acquisition module is used for acquiring a predetermined initial coronary three-dimensional model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point;
The second acquisition module is used for acquiring an initial two-dimensional contrast image at the current moment in the operation and a contrast shooting angle of the initial two-dimensional contrast image;
the rotation module is used for carrying out rotation processing on the initial coronary three-dimensional model according to the radiography shooting angle to obtain a target coronary three-dimensional model consistent with the initial two-dimensional radiography image shooting angle;
The mapping module is used for carrying out mapping matching processing on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with the mapping blood vessel outline of the target blood vessel segment and the path in the mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path;
and the correction module is used for sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
Optionally, when the rotation module is configured to perform rotation processing on the initial coronary three-dimensional model according to the imaging angle, to obtain a target coronary three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging, the rotation module is configured to:
determining a rotation matrix according to the contrast shooting angle;
Performing rotation processing on the initial coronary three-dimensional model according to the rotation matrix to determine a target coronary three-dimensional model; the shooting angle of the target coronary artery three-dimensional model is the same as that of the initial two-dimensional contrast image.
Optionally, when the mapping module is configured to perform mapping matching processing on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image labeled with a mapped vessel contour of a target vessel segment and a mapping intra-operative path, the mapping module is configured to:
Acquiring a three-dimensional coronary contour of the target vessel end and a preoperative three-dimensional path of the target vessel end from the target coronary three-dimensional model;
According to the matching relation between the target coronary artery three-dimensional model and the initial two-dimensional contrast image, mapping the three-dimensional coronary artery outline and the preoperative three-dimensional path to corresponding positions in the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image; and the candidate two-dimensional contrast images are marked with the mapped vessel contours and the paths in mapping operation after the mapping treatment.
Optionally, when the correction module is configured to sequentially correct the mapped vessel contour and the mapping intra-operative path in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image labeled with the target vessel contour and the target intra-operative path, the correction module is configured to:
extracting a local image block comprising the mapped blood vessel outline from the candidate two-dimensional contrast image, and simultaneously acquiring blood vessel attribute information of the target blood vessel segment;
the candidate two-dimensional contrast image, the local image block and the blood vessel attribute information of the target blood vessel segment are input into a pre-trained contour correction model together, and the blood vessel contour in the candidate two-dimensional contrast image is corrected to obtain the target blood vessel contour;
acquiring relevant parameters of a target medical instrument used in vascular interventional operation;
Correcting the mapping operation path according to the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the appointed parameter information in the current path information of the mapping operation path, and determining the target operation path.
Optionally, the correction module is configured to, when determining the target intra-operative path, correct the intra-operative path according to the target vessel profile, vessel attribute information of the target vessel segment, related parameters of the target medical apparatus, and specified parameter information in current path information of the intra-operative path, where the correction module is configured to:
And fusing and inputting the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the current path information of the mapping operation path into a pre-trained path correction model to obtain the target operation path so as to finish correction of the mapping operation path.
Optionally, the relevant parameters include instrument position information, and the correction module is configured to, when correcting the mapping intra-operative path according to the target vessel profile, vessel attribute information of the target vessel segment, relevant parameters of the target medical instrument, and specified parameter information in current path information of the mapping intra-operative path, determine the target intra-operative path:
Determining an initial starting point, at least one candidate path key point and an end point according to the current path information of the path in the mapping operation;
correcting the initial starting point and screening all candidate path key points according to the instrument position information of the target medical instrument to determine a target starting point and at least one target path key point;
and under the constraint of the target vessel contour, performing curve fitting processing according to the target starting point, at least one target path key point and the target ending point, and determining the target intraoperative path.
The embodiment of the application also provides electronic equipment, which comprises: the system comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate through the bus when the electronic device is running, and the machine-readable instructions are executed by the processor to perform the steps of the intra-operative path correction method as described above.
The embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for intra-operative path correction as described above.
The embodiment of the application provides an intraoperative path correction method and device for vascular interventional operation, wherein the intraoperative path correction method comprises the following steps: acquiring a predetermined initial coronary three-dimensional model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point; acquiring an initial two-dimensional contrast image at the current moment in operation and a contrast shooting angle of the initial two-dimensional contrast image; performing rotation processing on the initial coronary artery three-dimensional model according to the radiography shooting angle to obtain a target coronary artery three-dimensional model consistent with the initial two-dimensional radiography image shooting angle; performing mapping matching processing on the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with a mapping blood vessel contour of a target blood vessel segment and a path in mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path; and sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast images to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
In this way, the application performs real-time path correction during surgery by matching and combining the three-dimensional coronary model and the path determined before surgery and correcting the variability existing after the combination.
Therefore, the scheme has the following advantages:
1) The method and the device make full use of the advantages of the coronary artery CT radiography and the coronary artery radiography, complement each other, and can accurately match and display important information in vascular interventional operation.
2) The automatic path correction of the scheme can quickly and accurately compensate the deviation between preoperative three-dimensional path planning and real-time operation coronary angiography images, and the effectiveness and consistency of the paths are guaranteed by combining actual conditions on the basis of good preoperative optimal paths.
3) The scheme provides a multi-mode image matching function for doctors, and the comprehensive important information is fused and displayed, so that the operation efficiency and accuracy are improved.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for correcting an intra-operative path of a vascular interventional procedure according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an initial three-dimensional coronary model and related information provided by the present application;
FIG. 3 is a schematic diagram of a contrast shooting angle determining process according to the present application;
FIG. 4 is a schematic view of a rotation result of a three-dimensional model of coronary artery according to the present application;
FIG. 5 is a schematic illustration of a three-dimensional model of a target coronary artery and an initial two-dimensional contrast image provided by the present application;
FIG. 6 is a schematic diagram of a contour correction process according to the present application;
FIG. 7is a second schematic diagram of a contour correction process according to the present application;
FIG. 8 is a schematic diagram of a path correction process according to the present application;
FIG. 9 is a second schematic diagram of a path correction process according to the present application;
fig. 10 is a schematic structural diagram of an intra-operative path correction device for vascular intervention according to an embodiment of the present application;
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without making any inventive effort falls within the scope of protection of the present application.
For better completion of vascular interventional procedures, it is important to determine the path of travel of the guidewire. The existing path determining method comprises the following two ways: 1. in PCI operation, if there is no path planning of preoperative three-dimensional CCTA, doctors often carry out the path planning in operation according to own experience, and a manual or semi-automatic method is adopted to carry out the path planning in operation; 2. if the path planning of the preoperative three-dimensional CCTA exists, a series of morphological and functional information is acquired, a certain reference can be given to the path planning in the operation, and a doctor is assisted to complete the path planning in the operation by a manual or semi-automatic method.
However, the two schemes have the following problems that in scheme 1, the resolution ratio is higher than that of CT by directly taking coronary angiography as a reference, but only two-dimensional information is provided, and three-dimensional space information is lacked; second, although two-dimensional coronary angiography can accurately calculate the vascular stenosis rate, it is difficult to determine the type of lesion (plaque) causing the stenosis. Because of the lack of partial information, experienced doctors are required to analyze and determine the path of the guide wire, which firstly increases the burden of the doctors and increases the pressure of medical resources; furthermore, the time during PCI surgery is valuable, the patient is suffering from radiation hazards, more complex protocol determinations require longer decision time, increase physician stress, decrease surgical safety, and increase radiation hazards to the patient. Scheme 2 after the CCTA three-dimensional model and other morphological and functional metrics are obtained, these important information are not combined with the intra-operative information, so that there may be a deviation in the obtained path.
Based on the above, the embodiment of the application provides a method and a device for correcting an intraoperative path of a vascular interventional operation, which ensure the effectiveness and consistency of a determined intraoperative path by fusing preoperative path information and intraoperative path information, thereby effectively improving the efficiency and the accuracy of the operation.
Referring to fig. 1, fig. 1 is a flowchart of a method for correcting an intra-operative path of a vascular interventional procedure according to an embodiment of the present application. As shown in fig. 1, the method for correcting an intra-operative path provided by the embodiment of the application includes:
S101, acquiring a predetermined initial coronary three-dimensional model.
In this step, the initial coronary three-dimensional model is labeled with a preoperative three-dimensional path in the target vessel segment from the start point to the end point.
Here, the initial coronary three-dimensional model is a model determined preoperatively from a coronary CT contrast image. The coronary CT contrast is a three-dimensional contrast image.
When the initial coronary three-dimensional model is acquired, model information of the model and blood vessel attribute information of coronary blood vessels included in the model are acquired simultaneously. The blood vessel attribute information includes morphological information and functional information.
For example, the spatial coordinates of the three-dimensional model and the spatial coordinates of the three-dimensional optimal path point can be included; coordinates on the central line of the three-dimensional coronary artery tree, CT-FFR value corresponding to each point, stenosis rate, plaque type and the like.
The term "coronary CT imaging" is also referred to as CCTA, and "coronary CT angiography (CCTA) refers to a process of scanning a coronary artery by a plurality of spiral CT lines after intravenous injection of a proper contrast medium, so as to understand the condition of a coronary lesion. The method is one of simple, effective and noninvasive methods for diagnosing and predicting early coronary artery diseases, and has certain advantages for measuring coronary calcified plaque load, knowing coronary vessel wall and external coronary condition, checking congenital coronary dysplasia, coronary heart disease stent implantation and follow-up visit after coronary artery bypass grafting. The resolution is about 0.3 mm/pixel for three-dimensional images.
For example, referring to fig. 2, fig. 2 is a schematic diagram of an initial three-dimensional coronary model and related information provided by the present application. As shown in fig. 2, at the time of intra-operative path correction, an initial coronary three-dimensional model and corresponding model information thereof, and blood vessel attribute information of a coronary blood vessel included therein are acquired.
S102, acquiring an initial two-dimensional contrast image at the current moment in the operation and a contrast shooting angle of the initial two-dimensional contrast image.
Here, the current time in the operation is any time before the catheter in the operation does not enter the target vessel segment, and may also be any time when the catheter enters the target vessel segment.
In contrast, the image is also called CAG, and it should be noted that, at present, coronary angiography is a common and effective method for diagnosing coronary atherosclerotic heart disease (coronary heart disease). The selective coronary angiography is to make percutaneous puncture into lower limb femoral artery by using angiography machine through specially-made shaped cardiac catheter, make it move along descending aorta to root of ascending aorta, then search for left or right coronary artery mouth for insertion, and inject contrast medium so as to make coronary artery develop. The main trunk of the whole left or right coronary artery and the blood vessel cavities of the branches of the main trunk can be clearly displayed, whether the blood vessel exists in a narrow focus can be known, clear diagnosis can be made on the lesion part, the range, the severity, the condition of the blood vessel wall and the like, and the treatment scheme (intervention, operation or medical treatment) can be determined, and the treatment effect can be judged. The method is a safer and reliable invasive diagnosis technology, is widely applied to clinic and is considered as a gold standard for diagnosing coronary heart disease. The resolution is about 0.2 mm/pixel for two-dimensional time sequence dynamic image.
The imaging angle is determined by the X-ray light source and the receiver when the patient is lying on the operating table according to a preset posture.
For example, referring to fig. 3, fig. 3 is a schematic diagram illustrating a process of determining a shooting angle of contrast according to the present application, as shown in fig. 3, in order to shoot an initial two-dimensional coronary angiography from different angles, an X-ray source and a receiver rotate around two rotation axes, and an angle generated around a first rotation axis is a first angle, and an angle generated around a second rotation axis is a second angle. The first angle and the second angle are contrast shooting angles.
And S103, carrying out rotation processing on the initial coronary artery three-dimensional model according to the radiography shooting angle to obtain a target coronary artery three-dimensional model consistent with the initial two-dimensional radiography image shooting angle.
In this step, the view angle of the target coronary three-dimensional model is consistent with the two-dimensional contrast image.
In one embodiment of the present application, the rotating the initial coronary artery three-dimensional model according to the imaging angle to obtain a target coronary artery three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging includes:
S1031, determining a rotation matrix according to the contrast shooting angle.
S1032, carrying out rotation processing on the initial coronary artery three-dimensional model according to the rotation matrix, and determining a target coronary artery three-dimensional model.
For step S1031, determining a rotation matrix for rotating the initial coronary three-dimensional model to the initial two-dimensional contrast image view according to the contrast shooting angle in combination with the model parameters of the initial coronary three-dimensional model.
For step S1032, the three-dimensional model of the target coronary artery is the same as the photographing angle of the initial two-dimensional contrast image.
For example, according to the rotation matrix, a calculation formula of the target coronary three-dimensional model is determined as follows:
Wherein [ X C,YC,ZC ] represents a new coordinate after rotation, [ X W,YW,ZW ] represents a coordinate before rotation, alpha is a first angle in the imaging angles, and beta is a second angle in the imaging angles. And carrying out coordinate transformation on each point of the initial coronary three-dimensional model to obtain a matching image with the initial two-dimensional contrast image shadow, thereby obtaining the target coronary three-dimensional model.
For example, referring to fig. 4 and 5, fig. 4 is a schematic diagram of a rotation result of a three-dimensional coronary model provided by the present application, and fig. 5 is a schematic diagram of a three-dimensional coronary model and an initial two-dimensional contrast image provided by the present application. As shown in fig. 4, the initial coronary three-dimensional model is rotated to the target coronary three-dimensional model by image rotation by simulating the photographing condition of the initial two-dimensional contrast image. As shown in fig. 5, it can be clearly determined that the visual field conditions of the two images are almost identical.
And S104, carrying out mapping matching processing on the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with the mapping blood vessel outline of the target blood vessel segment and the path in the mapping operation.
Here, the intra-mapping path is determined from the pre-operative three-dimensional path.
In one embodiment of the present application, the mapping matching processing is performed on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image labeled with a mapped vessel contour of a target vessel segment and a path in mapping operation, including:
S1041, acquiring a three-dimensional coronary outline of the target blood vessel end and a preoperative three-dimensional path of the target blood vessel segment from the target coronary three-dimensional model.
S1042, mapping the three-dimensional coronary artery outline and the preoperative three-dimensional path to corresponding positions in the initial two-dimensional contrast image according to the matching relation between the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image; and the candidate two-dimensional contrast images are marked with the mapped vessel contours and the paths in mapping operation after the mapping treatment.
The matched target coronary three-dimensional model and the initial two-dimensional contrast image are subjected to mapping comparison, and the mapping of the coronary contour points and the pre-operation three-dimensional path mapping are sequentially included.
And S105, sequentially correcting the mapping blood vessel outline and the mapping intraoperative path in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the target intraoperative path.
In one embodiment of the present application, the sequentially correcting the mapping vessel contour and the mapping intra-operative path in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image marked with a target vessel contour and a target intra-operative path includes:
S1051, extracting a local image block comprising the mapped blood vessel outline from the candidate two-dimensional contrast image, and simultaneously acquiring blood vessel attribute information of the target blood vessel segment.
S1052, the candidate two-dimensional contrast image, the local image block and the blood vessel attribute information of the target blood vessel segment are input into a pre-trained contour correction model together, and the blood vessel contour in the candidate two-dimensional contrast image is corrected to obtain the target blood vessel contour.
S1053, acquiring relevant parameters of a target medical instrument used in the vascular interventional operation.
S1054, correcting the mapping operation path according to the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the appointed parameter information in the current path information of the mapping operation path, and determining the target operation path.
For step S1051, the local image block may be acquired through image segmentation processing, and the blood vessel attribute information of the target blood vessel segment includes blood vessel functional information and blood vessel morphology information of each position of the target blood vessel segment. By way of example, the vessel attribute information includes CT-FFR (fractional flow reserve), plaque type, stenosis rate, etc.
Aiming at step S1052, the contour correction model pairs a large number of contours with accurate manual marks and local image blocks, then randomly offsets the contours to slightly offset the edges of the vascular lumen, then inputs the offset contours and the local images into a neural network, carries out error calculation on the predicted contours and the manual marks contours obtained by prediction, returns the predicted contours and the manual marks to the neural network in a counter-propagation mode, and continuously and iteratively adjusts parameters of the neural network to enable the predicted contours to be continuously close to the manual marks, thereby achieving convergence, namely, the deviation is not reduced any more, and further obtaining the contour correction model.
For example, referring to fig. 6 and 7, fig. 6 is one of the contour correction process diagrams provided by the present application, and fig. 7 is the second of the contour correction process diagrams provided by the present application. Here, the vessel contour is corrected by means of a deep neural network.
For step S1053, the target medical device may be a guidewire or catheter, and the related parameters may include structural parameters as well as physical parameters.
In an embodiment of the present application, in step S1054, the correcting the mapping intra-operative path according to the target vessel profile, the vessel attribute information of the target vessel segment, the related parameters of the target medical device, and the specified parameter information in the current path information of the mapping intra-operative path, to determine the target intra-operative path includes: and fusing and inputting the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the current path information of the mapping operation path into a pre-trained path correction model to obtain the target operation path so as to finish correction of the mapping operation path.
The method comprises the steps of collecting a large number of coronary angiography PCI operation images in advance, extracting contour point coordinates of a guide wire and a lumen in the coronary angiography PCI operation images, recording the most realistic operation scene, taking the coronary angiography and the coordinates of the guide wire and the contour as training data and labels, manufacturing a simulated mapping path by slightly perturbing a path point, training a network, calculating deviation between a predicted result and a real label, transmitting the deviation back to a neural network by a back propagation mode, and continuously and iteratively adjusting parameters of the neural network to ensure that the predicted contour is continuously close to a manual mark to achieve convergence, thereby obtaining the path correction model.
In another embodiment of the present application, in step S1054, the relevant parameters include instrument position information, and the correcting the mapping path according to the target vessel profile, vessel attribute information of the target vessel segment, relevant parameters of the target medical instrument, and specified parameter information in current path information of the mapping path, and determining the target path includes: determining an initial starting point, at least one candidate path key point and an end point according to the current path information of the path in the mapping operation; correcting the initial starting point and screening all candidate path key points according to the instrument position information of the target medical instrument to determine a target starting point and at least one target path key point; and under the constraint of the target vessel contour, performing curve fitting processing according to the target starting point, at least one target path key point and the target ending point, and determining the target intraoperative path.
Here, the curve fitting process may employ a Spline curve fitting.
The method comprises the steps of determining a target starting point position through instrument position information of a target medical instrument, and guaranteeing real-time correction of a path in operation, so that accuracy of interventional operation is improved.
For example, referring to fig. 8 and 9, fig. 8 is one of the path correction process diagrams provided by the present application, and fig. 9 is the second of the path correction process diagrams provided by the present application. Here, two correction schemes are provided, one is curve fitting and one is a deep neural network. It should be noted that the above two schemes are only exemplary illustrations of the application per se.
To this end, the entire three-dimensional path is mapped to two dimensions and the process of making corrections is completed.
Referring to fig. 10, fig. 10 is a schematic structural diagram of an intra-operative path correction device for vascular intervention according to an embodiment of the present application. As shown in fig. 10, the intra-operative path correction device 200 includes:
A first acquisition module 210 for acquiring a predetermined initial three-dimensional coronary model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point;
a second obtaining module 220, configured to obtain an initial two-dimensional contrast image and a contrast shooting angle thereof at a current moment in an operation;
The rotation module 230 is configured to perform rotation processing on the initial coronary artery three-dimensional model according to the imaging angle, so as to obtain a target coronary artery three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging;
the mapping module 240 is configured to perform a mapping matching process on the target coronary three-dimensional model and the initial two-dimensional contrast image, so as to obtain a candidate two-dimensional contrast image labeled with a mapped vessel contour of the target vessel segment and a path in mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path;
And the correction module 250 is used for sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast images to obtain the target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
Optionally, when the rotation module 230 is configured to perform rotation processing on the initial coronary three-dimensional model according to the imaging angle, to obtain a target coronary three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging, the rotation module 230 is configured to:
determining a rotation matrix according to the contrast shooting angle;
Performing rotation processing on the initial coronary three-dimensional model according to the rotation matrix to determine a target coronary three-dimensional model; the shooting angle of the target coronary artery three-dimensional model is the same as that of the initial two-dimensional contrast image.
Optionally, when the mapping module 240 is configured to perform a mapping matching process on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image labeled with a mapped vessel contour of the target vessel segment and a path in mapping operation, the mapping module 240 is configured to:
Acquiring a three-dimensional coronary contour of the target vessel end and a preoperative three-dimensional path of the target vessel end from the target coronary three-dimensional model;
According to the matching relation between the target coronary artery three-dimensional model and the initial two-dimensional contrast image, mapping the three-dimensional coronary artery outline and the preoperative three-dimensional path to corresponding positions in the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image; and the candidate two-dimensional contrast images are marked with the mapped vessel contours and the paths in mapping operation after the mapping treatment.
Optionally, when the correction module 250 is configured to sequentially correct the mapped vessel contour and the mapping intra-operative path in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image labeled with the target vessel contour and the target intra-operative path, the correction module 250 is configured to:
extracting a local image block comprising the mapped blood vessel outline from the candidate two-dimensional contrast image, and simultaneously acquiring blood vessel attribute information of the target blood vessel segment;
the candidate two-dimensional contrast image, the local image block and the blood vessel attribute information of the target blood vessel segment are input into a pre-trained contour correction model together, and the blood vessel contour in the candidate two-dimensional contrast image is corrected to obtain the target blood vessel contour;
acquiring relevant parameters of a target medical instrument used in vascular interventional operation;
Correcting the mapping operation path according to the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the appointed parameter information in the current path information of the mapping operation path, and determining the target operation path.
Optionally, when the correction module 250 is configured to correct the mapping intra-operative path according to the target blood vessel profile, the blood vessel attribute information of the target blood vessel segment, the related parameter of the target medical device, and the specified parameter information in the current path information of the mapping intra-operative path, the correction module 250 is configured to:
And fusing and inputting the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the current path information of the mapping operation path into a pre-trained path correction model to obtain the target operation path so as to finish correction of the mapping operation path.
Optionally, the relevant parameters include instrument position information, and the correction module 250 is configured to, when correcting the mapping intra-operative path according to the target vessel profile, vessel attribute information of the target vessel segment, relevant parameters of the target medical instrument, and specified parameter information in current path information of the mapping intra-operative path, determine the target intra-operative path, perform:
Determining an initial starting point, at least one candidate path key point and an end point according to the current path information of the path in the mapping operation;
correcting the initial starting point and screening all candidate path key points according to the instrument position information of the target medical instrument to determine a target starting point and at least one target path key point;
and under the constraint of the target vessel contour, performing curve fitting processing according to the target starting point, at least one target path key point and the target ending point, and determining the target intraoperative path.
Referring to fig. 11, fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 11, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.
The memory 520 stores machine-readable instructions executable by the processor 510, and when the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps in the method embodiments shown in the foregoing fig. 9 may be executed, and the specific implementation may refer to the method embodiments and will not be described herein.
The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program may execute the steps in the method embodiments shown in the foregoing fig. to fig. 9 when the computer program is executed by a processor, and a specific implementation manner may refer to the method embodiments and is not repeated herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims (10)

1. An intra-operative path correction method for vascular interventional procedures, the intra-operative path correction method comprising:
Acquiring a predetermined initial coronary three-dimensional model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point;
acquiring an initial two-dimensional contrast image at the current moment in operation and a contrast shooting angle of the initial two-dimensional contrast image;
Performing rotation processing on the initial coronary artery three-dimensional model according to the radiography shooting angle to obtain a target coronary artery three-dimensional model consistent with the initial two-dimensional radiography image shooting angle;
Performing mapping matching processing on the target coronary artery three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with a mapping blood vessel contour of a target blood vessel segment and a path in mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path;
and sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast images to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
2. The method according to claim 1, wherein the rotating the initial coronary three-dimensional model according to the imaging angle to obtain a target coronary three-dimensional model consistent with the imaging angle of the initial two-dimensional imaging comprises:
determining a rotation matrix according to the contrast shooting angle;
Performing rotation processing on the initial coronary three-dimensional model according to the rotation matrix to determine a target coronary three-dimensional model; the shooting angle of the target coronary artery three-dimensional model is the same as that of the initial two-dimensional contrast image.
3. The method according to claim 1, wherein performing a mapping matching process on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a mapped vessel contour labeled with a target vessel segment and a candidate two-dimensional contrast image of the path in the mapping process comprises:
Acquiring a three-dimensional coronary contour of the target vessel end and a preoperative three-dimensional path of the target vessel end from the target coronary three-dimensional model;
According to the matching relation between the target coronary artery three-dimensional model and the initial two-dimensional contrast image, mapping the three-dimensional coronary artery outline and the preoperative three-dimensional path to corresponding positions in the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image; and the candidate two-dimensional contrast images are marked with the mapped vessel contours and the paths in mapping operation after the mapping treatment.
4. The method for correcting an intra-operative path according to claim 1, wherein sequentially correcting the mapped vessel contour and the intra-operative path in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image labeled with a target vessel contour and a target intra-operative path comprises:
extracting a local image block comprising the mapped blood vessel outline from the candidate two-dimensional contrast image, and simultaneously acquiring blood vessel attribute information of the target blood vessel segment;
the candidate two-dimensional contrast image, the local image block and the blood vessel attribute information of the target blood vessel segment are input into a pre-trained contour correction model together, and the blood vessel contour in the candidate two-dimensional contrast image is corrected to obtain the target blood vessel contour;
acquiring relevant parameters of a target medical instrument used in vascular interventional operation;
Correcting the mapping operation path according to the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the appointed parameter information in the current path information of the mapping operation path, and determining the target operation path.
5. The method according to claim 4, wherein the step of correcting the mapping intra-operative path based on the target vessel profile, vessel attribute information of the target vessel segment, related parameters of the target medical device, and specified parameter information in current path information of the mapping intra-operative path, and determining the target intra-operative path includes:
And fusing and inputting the target blood vessel outline, the blood vessel attribute information of the target blood vessel section, the related parameters of the target medical instrument and the current path information of the mapping operation path into a pre-trained path correction model to obtain the target operation path so as to finish correction of the mapping operation path.
6. The method according to claim 4, wherein the relevant parameters include instrument position information, and the determining the target intra-operative path by correcting the intra-operative path according to the target vessel profile, vessel attribute information of the target vessel segment, relevant parameters of the target medical instrument, and specified parameter information in current path information of the intra-operative path includes:
Determining an initial starting point, at least one candidate path key point and an end point according to the current path information of the path in the mapping operation;
correcting the initial starting point and screening all candidate path key points according to the instrument position information of the target medical instrument to determine a target starting point and at least one target path key point;
and under the constraint of the target vessel contour, performing curve fitting processing according to the target starting point, at least one target path key point and the target ending point, and determining the target intraoperative path.
7. An intraoperative path correction device for vascular interventional procedures, the intraoperative path correction device comprising:
The first acquisition module is used for acquiring a predetermined initial coronary three-dimensional model; wherein the initial coronary three-dimensional model is marked with a preoperative three-dimensional path in a target vessel segment from a starting point to an ending point;
The second acquisition module is used for acquiring an initial two-dimensional contrast image at the current moment in the operation and a contrast shooting angle of the initial two-dimensional contrast image;
the rotation module is used for carrying out rotation processing on the initial coronary three-dimensional model according to the radiography shooting angle to obtain a target coronary three-dimensional model consistent with the initial two-dimensional radiography image shooting angle;
The mapping module is used for carrying out mapping matching processing on the target coronary three-dimensional model and the initial two-dimensional contrast image to obtain a candidate two-dimensional contrast image marked with the mapping blood vessel outline of the target blood vessel segment and the path in the mapping operation; the intra-mapping path is determined according to the preoperative three-dimensional path;
and the correction module is used for sequentially correcting the mapping blood vessel outline and the path in the mapping operation in the candidate two-dimensional contrast image to obtain a target two-dimensional contrast image marked with the target blood vessel outline and the path in the target operation.
8. The apparatus according to claim 7, wherein the rotation module, when performing rotation processing on the initial coronary three-dimensional model according to the imaging angle, is configured to:
determining a rotation matrix according to the contrast shooting angle;
Performing rotation processing on the initial coronary three-dimensional model according to the rotation matrix to determine a target coronary three-dimensional model; the shooting angle of the target coronary artery three-dimensional model is the same as that of the initial two-dimensional contrast image.
9. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of the method of intra-operative path correction according to any one of claims 1 to 6.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the intra-operative path correction method according to any one of claims 1 to 6.
CN202410126996.4A 2024-01-29 2024-01-29 Intraoperative path correction method and device for vascular interventional operation Pending CN117958966A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410126996.4A CN117958966A (en) 2024-01-29 2024-01-29 Intraoperative path correction method and device for vascular interventional operation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410126996.4A CN117958966A (en) 2024-01-29 2024-01-29 Intraoperative path correction method and device for vascular interventional operation

Publications (1)

Publication Number Publication Date
CN117958966A true CN117958966A (en) 2024-05-03

Family

ID=90860360

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410126996.4A Pending CN117958966A (en) 2024-01-29 2024-01-29 Intraoperative path correction method and device for vascular interventional operation

Country Status (1)

Country Link
CN (1) CN117958966A (en)

Similar Documents

Publication Publication Date Title
JP7039442B2 (en) How to create a blood vessel model
JP4374234B2 (en) Method and apparatus for medical invasive treatment planning
JP4771409B2 (en) Method and system for aligning a three-dimensional model of an anatomical region and a projected image of the region
JP4441322B2 (en) Cardiac CT system and method for planning and treatment of biventricular pacing using an epicardial lead
EP2908719B1 (en) Methods for numerically evaluating vasculature
US8515527B2 (en) Method and apparatus for registering 3D models of anatomical regions of a heart and a tracking system with projection images of an interventional fluoroscopic system
JP4345959B2 (en) Method, system and computer product for cardiac interventional treatment planning
JP4524284B2 (en) Cardiac imaging system and method for planning surgery
EP3954298A2 (en) Vascular characteristic determination with correspondence modeling of a vascular tree
CN107871531B (en) Fracture assessment and surgical intervention planning
JP2006051359A (en) Method and apparatus for medical intervention procedure planning and location and navigation of an intervention tool
WO2009044321A2 (en) Detection and tracking of interventional tools
CN107865692B (en) System and method for detecting pleural invasion in surgical and interventional planning
CN110248603A (en) 3D ultrasound and computer tomography are combined for guiding intervention medical protocol
JP2012115635A (en) Image processing method, image processing apparatus, imaging system, and program code
JP2006175229A (en) Method and system for registering 3d image within interventional system
JP2017217474A (en) Medical image diagnostic apparatus and medical image processing system
US20070265518A1 (en) Method and arrangement for locating a medical instrument at least partly inserted into an object under examination
US20220254131A1 (en) Methods, apparatus, and system for synchronization between a three-dimensional vascular model and an imaging device
EP3602485B1 (en) Interaction monitoring of non-invasive imaging based ffr
CN117958966A (en) Intraoperative path correction method and device for vascular interventional operation
CN115089294B (en) Interventional operation navigation method
Sun A Review of 3D-2D Registration Methods and Applications based on Medical Images
KR102423825B1 (en) Processing Method for Tailored Laser Ablation System and Automatic Laser Ablation Device using it
US20050222509A1 (en) Electrophysiology system and method

Legal Events

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